If you are not sure if the website you would like to visit is secure, you can verify it here. Enter the website address of the page and see parts of its content and the thumbnail images on this site. None (if any) dangerous scripts on the referenced page will be executed. Additionally, if the selected site contains subpages, you can verify it (review) in batches containing 5 pages.
favicon.ico: jankautz.com - Jan Kautz.

site address: jankautz.com

site title: Jan Kautz

Our opinion (on Thursday 09 July 2026 2:23:58 UTC):

GREEN status (no comments) - no comments
After content analysis of this website we propose the following hashtags:


page from cache: 2 days ago
Meta tags:
description=Personal webpage of Jan Kautz.;
author=;
keywords=Jan Kautz NVIDIA;

Headings (most frequently used words):

of, usa, university, research, nvidia, senior, professor, college, london, uk, visual, computing, student, learning, and, director, associate, lecturer, germany, vice, president, perception, machine, manager, scientist, reader, assistant, post, doctoral, researcher, massachusetts, institute, technology, phd, max, planck, institut, fur, informatik, graduate, waterloo, canada, erlangen, nurnberg,

Text of the page (most frequently used words):
the (916), and (734), for (401), kautz (329), pdf (283), that (212), todo (208), with (206), vision (185), conference (180), cvpr (179), our (166), computer (163), this (163), video (145), ieee (123), image (118), are (111), can (110), pages (110), arxiv (108), from (107), #learning (103), graphics (103), using (102), june (98), rendering (96), liu (96), illumination (95), recognition (92), method (91), based (90), which (86), pattern (85), models (83), supplemental (80), light (76), real (73), model (70), siggraph (69), time (67), dynamic (66), international (63), efficient (62), molchanov (61), data (60), lighting (60), neural (60), interactive (59), objects (59), images (58), yang (58), acm (57), wang (55), neurips (55), these (54), eccv (54), scene (53), 2025 (53), such (50), approach (49), information (49), iclr (48), used (47), techniques (47), propose (47), demonstrate (47), webpage (47), global (46), visibility (46), paper (45), well (45), have (45), show (45), visual (44), has (44), different (44), technique (44), high (44), scenes (44), methods (43), processing (43), hardware (42), maps (42), shadow (42), object (42), kim (42), view (41), december (41), more (40), algorithm (40), iccv (40), also (39), not (39), systems (39), point (37), surface (37), new (37), quality (37), space (36), sampling (36), estimation (36), appearance (35), present (35), depth (35), user (35), large (35), system (35), environment (34), local (34), allows (34), accurate (34), transfer (34), transactions (34), multi (34), 2024 (34), 2018 (33), each (33), but (33), color (33), may (32), into (32), camera (32), yin (32), use (31), seidel (31), reflectance (31), shading (31), 2023 (31), geometry (30), mapping (30), simple (30), been (30), over (30), results (30), september (30), algorithms (29), frame (29), radiance (29), novel (29), october (29), human (29), oral (29), all (28), display (28), other (28), proceedings (28), representations (28), many (27), low (27), however (27), while (27), field (27), between (27), 2020 (27), 2012 (26), representation (26), both (26), 2019 (26), research (25), even (25), single (25), eurographics (25), two (25), map (25), only (25), august (25), work (25), hand (25), state (25), videos (25), mello (25), language (25), complex (24), multiple (24), pixel (24), than (24), problem (24), reconstruction (24), april (24), analysis (24), one (24), applications (24), stereo (24), pose (24), aware (24), european (24), networks (24), how (23), brdfs (23), shadows (23), effects (23), precomputed (23), performance (23), virtual (23), july (23), input (23), spatial (23), motion (23), iqbal (23), texture (22), brdf (22), fast (22), world (22), computational (22), via (22), first (22), range (22), resolution (22), temporal (22), 2014 (21), rates (21), interface (21), under (21), previous (21), chen (21), study (21), 2026 (21), nvidia (20), perception (20), 2013 (20), 2017 (20), indirect (20), arbitrary (20), proposed (20), then (20), www (20), without (20), art (20), cost (20), filtering (20), 2009 (19), 2015 (19), existing (19), functions (19), often (19), introduce (19), they (19), spatially (19), varying (19), order (19), computation (19), common (19), modeling (19), flash (19), displays (19), edge (19), laplacian (19), gallo (19), network (19), huang (19), 2022 (19), realistic (18), ray (18), function (18), small (18), several (18), through (18), non (18), implementation (18), 2007 (18), exposure (18), filters (18), 2021 (18), editing (17), final (17), where (17), achieve (17), when (17), structure (17), self (17), incident (17), frequency (17), set (17), recent (17), sequence (17), training (17), supervised (17), vahdat (17), machine (16), hierarchical (16), possible (16), materials (16), synthesis (16), points (16), compared (16), code (16), papers (16), flow (16), detection (16), tasks (16), collections (16), pruning (16), sun (16), computing (15), requires (15), efficiently (15), number (15), distribution (15), approaches (15), variety (15), directly (15), allow (15), advances (15), scale (15), optimization (15), dong (15), hdr (15), gpu (15), context (15), classification (15), deep (15), yuan (15), 2011 (14), tracing (14), workshop (14), detail (14), applied (14), current (14), best (14), area (14), transport (14), per (14), symposium (14), gaussian (14), accuracy (14), framework (14), asia (14), registration (14), tompkin (14), diffusion (14), gesture (14), convolutional (14), zhu (14), catanzaro (14), byeon (14), head (13), within (13), bidirectional (13), render (13), glossy (13), reflections (13), anisotropic (13), direct (13), changes (13), rendered (13), towards (13), physically (13), need (13), because (13), very (13), 2004 (13), better (13), march (13), interaction (13), fusion (13), course (13), their (13), content (13), challenging (13), process (13), frames (13), foundation (13), november (13), standard (13), graph (13), propagation (13), matching (13), dataset (13), jampani (13), tao (13), icml (13), sources (12), step (12), end (12), bump (12), due (12), consistent (12), scattering (12), properties (12), spherical (12), soft (12), moving (12), including (12), subsurface (12), forum (12), importance (12), scheme (12), robust (12), artifacts (12), cameras (12), optical (12), facial (12), free (12), spatio (12), joint (12), imagery (12), multimodal (12), reasoning (12), gestures (12), han (12), 2003 (11), photography (11), parts (11), dimensional (11), presented (11), error (11), three (11), result (11), general (11), further (11), problems (11), environments (11), second (11), mertens (11), linear (11), generate (11), various (11), less (11), binary (11), create (11), same (11), imaging (11), 2008 (11), rate (11), cvmp (11), capture (11), reality (11), bmvc (11), shot (11), mixture (11), 2016 (11), tyree (11), spotlight (11), shi (11), lin (11), realism (10), computed (10), stored (10), heidrich (10), change (10), approximate (10), approximation (10), will (10), accelerated (10), achieves (10), levels (10), shadowing (10), finally (10), features (10), limited (10), lights (10), terms (10), them (10), component (10), material (10), important (10), generated (10), require (10), diffuse (10), response (10), vertex (10), mesh (10), pacific (10), bekaert (10), integration (10), perform (10), parametric (10), dependent (10), egsr (10), highlight (10), highly (10), its (10), provide (10), task (10), feature (10), theobalt (10), parallel (10), location (10), 2010 (10), design (10), database (10), edges (10), tracking (10), long (10), interfaces (10), subpixel (10), generative (10), hybrid (10), eckart (10), zhang (10), accepted (10), oct (9), increase (9), simulation (9), approximations (9), shape (9), resulting (9), 2000 (9), cases (9), game (9), address (9), most (9), screen (9), few (9), viewing (9), conditions (9), 2002 (9), parameters (9), presents (9), usually (9), significantly (9), enables (9), speed (9), source (9), structured (9), cgf (9), easy (9), size (9), effectiveness (9), ritschel (9), potential (9), tone (9), fully (9), doi (9), captured (9), pece (9), body (9), segmentation (9), convergence (9), array (9), mobile (9), transition (9), specific (9), mixed (9), printing (9), transitions (9), panoramic (9), layers (9), fonts (9), 3dv (9), frosio (9), polarization (9), hatamizadeh (9), team (9), some (8), post (8), 2006 (8), class (8), every (8), given (8), operations (8), required (8), uses (8), example (8), across (8), effectively (8), games (8), surfaces (8), effective (8), since (8), february (8), 2001 (8), extend (8), able (8), average (8), normal (8), far (8), provides (8), like (8), avoids (8), contrast (8), energy (8), compute (8), account (8), form (8), practical (8), leads (8), gradient (8), hair (8), static (8), occlusion (8), yields (8), being (8), rigid (8), enable (8), constraints (8), whether (8), coherent (8), values (8), selection (8), solution (8), scales (8), faster (8), dense (8), variance (8), pixels (8), adaptive (8), smoothness (8), continuous (8), open (8), lenslet (8), pen (8), patchmatch (8), pairwise (8), architecture (8), criteria (8), reinforcement (8), icra (8), alvarez (8), gr00t (8), please (8), stop (8), london (7), any (7), known (7), samples (7), what (7), during (7), still (7), fields (7), intensity (7), part (7), thus (7), measured (7), basis (7), generation (7), coefficients (7), includes (7), kernel (7), geometric (7), full (7), trade (7), interactively (7), search (7), plausible (7), acceleration (7), exploit (7), combination (7), underlying (7), decoupling (7), additional (7), durand (7), individual (7), challenge (7), parameter (7), variation (7), introducing (7), physical (7), rays (7), stochastic (7), angular (7), grosch (7), complexity (7), analyze (7), implicit (7), bounce (7), sparse (7), dachsbacher (7), commonly (7), movement (7), available (7), position (7), users (7), performing (7), strategy (7), find (7), pyramid (7), upon (7), automatic (7), optimal (7), related (7), belief (7), pmbp (7), dual (7), ijcv (7), subtitles (7), cvf (7), recurrent (7), criterion (7), birchfield (7), lee (7), song (7), you (7), fan (7), technology (6), university (6), usa (6), grid (6), lamp (6), synthetic (6), unfortunately (6), correct (6), describe (6), filter (6), reflection (6), prefiltered (6), unified (6), significant (6), benefits (6), sampled (6), micro (6), take (6), close (6), necessary (6), award (6), phenomena (6), capable (6), called (6), way (6), does (6), affect (6), january (6), displacement (6), test (6), similar (6), photorealistic (6), lensch (6), product (6), harmonics (6), handle (6), caustics (6), aliasing (6), making (6), journal (6), tools (6), translucent (6), effect (6), factors (6), kernels (6), derive (6), obtained (6), little (6), expensive (6), memory (6), patterns (6), generalization (6), monte (6), carlo (6), update (6), after (6), van (6), reeth (6), certain (6), much (6), acquisition (6), pre (6), main (6), perspective (6), extended (6), there (6), cross (6), matusik (6), target (6), creation (6), assembly (6), instance (6), compression (6), nature (6), computationally (6), bracketed (6), guided (6), luminance (6), specialized (6), match (6), face (6), experimental (6), media (6), weyrich (6), understanding (6), gathering (6), bispectral (6), visible (6), impact (6), particular (6), synthesize (6), actor (6), people (6), successful (6), higher (6), inverse (6), wise (6), subr (6), explore (6), see (6), extensive (6), sensing (6), pbp (6), correspondence (6), connected (6), potentially (6), domain (6), remote (6), central (6), participants (6), diverse (6), campbell (6), strategies (6), jittered (6), localization (6), datasets (6), reduce (6), layer (6), cascaded (6), tuning (6), troccoli (6), automotive (6), cloud (6), rnn (6), nips (6), semantic (6), breuel (6), aaai (6), jiang (6), mallya (6), shoeybi (6), choi (6), transformer (6), nagano (6), mardani (6), heinrich (6), mamba (6), cheng (6), diao (6), robot (6), jun (6), modal (5), jan (5), park (5), received (5), 1998 (5), working (5), costly (5), egwr (5), decomposition (5), improves (5), respect (5), advantages (5), compare (5), knowledge (5), previously (5), researchers (5), should (5), consistently (5), combines (5), variant (5), shown (5), phong (5), furthermore (5), place (5), community (5), amount (5), made (5), wide (5), conjunction (5), appropriate (5), aligned (5), warping (5), measurement (5), goesele (5), automatically (5), according (5), fly (5), harmonic (5), represent (5), factor (5), interreflections (5), represented (5), reducing (5), vertices (5), acquired (5), matrix (5), performs (5), expected (5), fashion (5), unlike (5), key (5), idea (5), solve (5), recently (5), radiosity (5), semi (5), accurately (5), applicability (5), remains (5), shows (5), vary (5), interest (5), were (5), demonstrated (5), application (5), compact (5), distant (5), interpolation (5), requiring (5), style (5), contribution (5), mask (5), aila (5), improve (5), discusses (5), strengths (5), prt (5), active (5), nonlinear (5), solving (5), traditional (5), background (5), pipeline (5), advantage (5), exploring (5), question (5), approximating (5), humans (5), cannot (5), control (5), limits (5), flat (5), textures (5), out (5), characterization (5), digital (5), defined (5), rgb (5), produces (5), collection (5), temperature (5), components (5), estimate (5), multiplexing (5), perceptual (5), evaluate (5), introduced (5), locations (5), attention (5), angles (5), production (5), paris (5), sequences (5), temporally (5), widely (5), building (5), online (5), performed (5), embedded (5), manipulation (5), devices (5), slow (5), british (5), rother (5), pair (5), comparing (5), make (5), good (5), places (5), honorable (5), mention (5), euclidean (5), types (5), prior (5), pulli (5), luebke (5), manifold (5), adaptation (5), variational (5), sensors (5), hands (5), action (5), gupta (5), pcd (5), loss (5), badki (5), intelligence (5), robotics (5), latent (5), zheng (5), weakly (5), transformers (5), muralidharan (5), fang (5), nemotron (5), posters (5), group (4), student (4), 1999 (4), professor (4), college (4), senior (4), vice (4), currently (4), instances (4), actual (4), parameterization (4), specular (4), fitting (4), preprocessing (4), height (4), offers (4), identify (4), discuss (4), development (4), directional (4), sophisticated (4), type (4), unable (4), reproduce (4), articles (4), level (4), detects (4), project (4), original (4), viewer (4), smooth (4), times (4), dot (4), vectors (4), direction (4), integral (4), achieved (4), creates (4), run (4), useful (4), throughput (4), distributed (4), combining (4), exit (4), lehtinen (4), i3d (4), natural (4), settings (4), addition (4), desired (4), case (4), tests (4), software (4), viewpoint (4), analytical (4), inspired (4), experiments (4), thousands (4), 130 (4), advanced (4), traditionally (4), support (4), areas (4), suited (4), compelling (4), gradients (4), annen (4), constructed (4), against (4), basic (4), bias (4), careful (4), differences (4), among (4), weaknesses (4), courses (4), 2005 (4), sub (4), difficult (4), remain (4), visually (4), reduction (4), technologies (4), understand (4), suitable (4), maintaining (4), queries (4), runs (4), occlusions (4), conduct (4), whose (4), operators (4), talk (4), elements (4), near (4), link (4), measures (4), brightness (4), signal (4), extends (4), deal (4), enabling (4), makes (4), magnitude (4), 128 (4), alternative (4), noise (4), powerful (4), allowing (4), examples (4), inaccurate (4), too (4), must (4), faces (4), trained (4), painting (4), improving (4), psychophysical (4), creating (4), become (4), exact (4), bilateral (4), 132 (4), fluorescent (4), reduced (4), reradiation (4), complete (4), another (4), intuitive (4), avoid (4), appropriately (4), artefacts (4), detailed (4), medical (4), exploration (4), iccp (4), was (4), motions (4), initial (4), preserving (4), smoothing (4), pyramids (4), halos (4), channel (4), cinemagraphs (4), loop (4), completion (4), build (4), regions (4), guide (4), portals (4), clips (4), unstructured (4), nodes (4), preference (4), yet (4), optimizing (4), ingredients (4), databases (4), identification (4), prediction (4), construction (4), labels (4), takes (4), planar (4), experience (4), steed (4), print (4), articulated (4), partial (4), conventional (4), usability (4), denoising (4), term (4), power (4), inference (4), fixed (4), arrays (4), fourier (4), artifact (4), desktop (4), uist (4), critical (4), layered (4), tensor (4), flexible (4), plane (4), priors (4), pajak (4), communications (4), cacm (4), subspace (4), directions (4), aspects (4), cpu (4), asynchronous (4), a3c (4), automation (4), indoor (4), tan (4), landmark (4), bayesian (4), sen (4), niessner (4), ren (4), unsupervised (4), translation (4), tremblay (4), shen (4), guo (4), wild (4), wacv (4), xiao (4), tpami (4), anandkumar (4), fox (4), contrastive (4), patwary (4), humanoid (4), scaling (4), corl (4), phd (3), director (3), version (3), away (3), separable (3), implement (3), reflectances (3), schmidt (3), mccool (3), isotropic (3), greedy (3), numbers (3), practice (3), improved (3), daubert (3), path (3), future (3), look (3), capabilities (3), determine (3), purpose (3), modulation (3), series (3), aspect (3), others (3), achieving (3), volume (3), polygons (3), call (3), subtle (3), needed (3), robustly (3), fits (3), truly (3), relatively (3), density (3), created (3), bottleneck (3), generalize (3), sloan (3), captures (3), representing (3), onto (3), matrices (3), cast (3), issues (3), highlights (3), bitmap (3), although (3), ways (3), modeled (3), triangle (3), fine (3), speeds (3), optimize (3), supported (3), instead (3), adapting (3), principal (3), computations (3), reuse (3), amounts (3), particularly (3), developed (3), finding (3), access (3), regular (3), volumes (3), success (3), renderings (3), amenable (3), typically (3), dynamically (3), computers (3), empirical (3), years (3), evaluated (3), hard (3), list (3), 184 (3), sufficient (3), taylor (3), expansion (3), interpolate (3), line (3), rasterization (3), clustered (3), along (3), integrating (3), obtain (3), precomputation (3), cues (3), introduction (3), improvements (3), details (3), provided (3), chan (3), challenges (3), family (3), addresses (3), theory (3), thereby (3), involved (3), storage (3), dimensionality (3), efficiency (3), resource (3), overall (3), help (3), toward (3), focused (3), casting (3), packets (3), coherence (3), primary (3), packet (3), precomputing (3), convolution (3), always (3), approximated (3), unchanged (3), perceived (3), visualization (3), btfs (3), core (3), subsets (3), fusing (3), converting (3), skipping (3), curve (3), calibration (3), exposures (3), done (3), comparable (3), device (3), solutions (3), consists (3), errors (3), imperfect (3), professional (3), apply (3), correlated (3), relighting (3), photometric (3), moreover (3), capturing (3), combine (3), choice (3), studied (3), acquire (3), generalized (3), cover (3), scalable (3), wavelengths (3), spectral (3), pairs (3), needs (3), artistic (3), facilitates (3), edit (3), vssm (3), theoretical (3), pcss (3), fps (3), feng (3), exceeds (3), configurations (3), fused (3), viewed (3), pfister (3), surrounding (3), experiment (3), viewpoints (3), specified (3), ubiquitous (3), decomposing (3), invariant (3), wealth (3), come (3), flexibility (3), relying (3), hasinoff (3), stream (3), now (3), codecs (3), bit (3), encoding (3), photographic (3), short (3), move (3), region (3), tool (3), broad (3), extremely (3), consuming (3), manual (3), left (3), functional (3), desirable (3), track (3), corresponding (3), touch (3), autostereoscopic (3), interesting (3), prototype (3), alexa (3), contain (3), propagate (3), steps (3), particle (3), spaces (3), illustrate (3), built (3), besse (3), fitzgibbon (3), matches (3), alignment (3), inpainting (3), absolute (3), telecommunication (3), acting (3), heterogeneous (3), steptoe (3), joints (3), printable (3), room (3), ambiguities (3), aperture (3), sensor (3), failure (3), conditional (3), yield (3), embedding (3), crfs (3), lenticular (3), prints (3), medium (3), off (3), output (3), validate (3), estimates (3), lead (3), feedback (3), discover (3), overlap (3), tablet (3), probe (3), custom (3), svbrdfs (3), apparent (3), sensitivity (3), adapted (3), train (3), experts (3), sparsity (3), combinations (3), estimators (3), negative (3), antithetic (3), spatiotemporal (3), slm (3), superresolution (3), thin (3), factorization (3), mounted (3), hmd (3), reddy (3), simultaneously (3), prone (3), induced (3), annotations (3), becoming (3), read (3), placement (3), enhancing (3), fov (3), either (3), cvprw (3), safety (3), showing (3), mode (3), weights (3), before (3), expectation (3), maximum (3), likelihood (3), distraction (3), modalities (3), benchmark (3), cnn (3), karras (3), critic (3), gaming (3), helpful (3), larger (3), davis (3), differentiable (3), featureless (3), polarimetric (3), autoencoder (3), zhong (3), deblurring (3), lai (3), learned (3), miller (3), super (3), zou (3), hilliges (3), gaze (3), schwing (3), omni (3), kreis (3), xiang (3), autonomous (3), fidler (3), zero (3), khamis (3), wen (3), avatars (3), ranzinger (3), cai (3), radhakrishnan (3), grounded (3), earth (3), generalist (3), llms (3), suhara (3), xue (3), man (3), darrell (3), cheung (3), magne (3), competition (3), released (3), gtc (3), hope (3), join (3), say (3), dec (3), text (2), drive (2), contact (2), msc (2), science (2), germany (2), max (2), fur (2), sep (2), researcher (2), supervision (2), assistant (2), lecturer (2), mar (2), associate (2), apr (2), president (2), geometries (2), greatly (2), simulate (2), repeated (2), lightfield (2), produced (2), later (2), utilized (2), 293 (2), reconstruct (2), difference (2), vector (2), minimizes (2), lobe (2), elevation (2), coarse (2), disadvantages (2), classify (2), develop (2), prefiltering (2), banks (2), 185 (2), hierarchy (2), exploited (2), inconsistencies (2), considers (2), mostly (2), inexpensive (2), illuminating (2), simulating (2), approximates (2), curvature (2), shift (2), simpler (2), fog (2), distance (2), attenuation (2), strict (2), incorporate (2), ultimately (2), developer (2), mapped (2), renders (2), slicing (2), intersection (2), accelerate (2), composed (2), measuring (2), formed (2), recovered (2), leading (2), realistically (2), reproduces (2), 104 (2), synthesizes (2), zoom (2), displayed (2), distances (2), assuming (2), table (2), represents (2), expressed (2), reduces (2), easily (2), versa (2), preprocessed (2), snyder (2), handled (2), rigidly (2), element (2), receivers (2), rather (2), quite (2), rarely (2), simply (2), gems (2), halftoning (2), printed (2), modi (2), fied (2), impulse (2), incoming (2), impinging (2), texel (2), shining (2), situation (2), filtered (2), magnor (2), lang (2), measurements (2), 234 (2), tog (2), illuminated (2), partially (2), incorporating (2), offer (2), locally (2), four (2), pca (2), therefore (2), once (2), established (2), nearby (2), store (2), discrete (2), storing (2), meshes (2), implementations (2), lets (2), reproduction (2), clustering (2), patch (2), consisting (2), incremental (2), 140 (2), deformable (2), operates (2), skin (2), geared (2), gouraud (2), unless (2), hence (2), five (2), combined (2), report (2), review (2), mesostructures (2), circumstances (2), renderer (2), 177 (2), alleviates (2), requirement (2), around (2), fewer (2), alone (2), calculate (2), shader (2), shadowed (2), constraint (2), sight (2), differs (2), estimating (2), animated (2), hemispherical (2), computes (2), blocker (2), requirements (2), about (2), incorporated (2), learn (2), begins (2), etc (2), describes (2), extensions (2), technical (2), throughout (2), stamminger (2), tom (2), poses (2), handling (2), difficulty (2), academic (2), practitioners (2), rich (2), gaussians (2), bandwidth (2), regression (2), green (2), characteristics (2), textured (2), correlation (2), guidance (2), offs (2), progress (2), refraction (2), unclear (2), complicated (2), share (2), interested (2), whitted (2), boulos (2), csms (2), exploits (2), entirely (2), opposed (2), assume (2), freely (2), inherently (2), weighted (2), naturally (2), implemented (2), demo (2), conducted (2), analyse (2), degree (2), apgv (2), btf (2), modification (2), favorably (2), yielding (2), moderately (2), evaluating (2), mutual (2), constructing (2), means (2), simplifies (2), blends (2), saturation (2), signals (2), raw (2), ldr (2), designed (2), unknown (2), assumed (2), cssms (2), covering (2), entire (2), exponential (2), 161 (2), prevent (2), flashes (2), atmosphere (2), white (2), photographers (2), illuminations (2), lit (2), photographs (2), lcd (2), cae (2), chromatic (2), scanning (2), becomes (2), multiplexed (2), reliably (2), goal (2), statistics (2), condition (2), considerable (2), synthesized (2), modifying (2), prince (2), quickly (2), increasing (2), quantify (2), adapt (2), exploiting (2), give (2), overview (2), equation (2), streams (2), topic (2), sharing (2), daily (2), perceptually (2), answer (2), influence (2), reveals (2), tap (2), instant (2), insight (2), vmv (2), running (2), photon (2), engelhardt (2), everyday (2), especially (2), concept (2), taken (2), drag (2), positions (2), edits (2), sketching (2), explicit (2), handles (2), vsm (2), 100 (2), exposed (2), reproducing (2), smallest (2), movements (2), ghosting (2), dramatically (2), adapts (2), clusters (2), ghost (2), explicitly (2), panoramas (2), gigapixel (2), let (2), recognized (2), degrees (2), lightness (2), increased (2), integrated (2), marker (2), actors (2), views (2), dai (2), characters (2), performances (2), believed (2), ill (2), tackle (2), neighborhood (2), wavelet (2), bases (2), price (2), accompanied (2), characterize (2), threshold (2), differentiate (2), enhancement (2), simplicity (2), nonlinearities (2), convolutions (2), degrading (2), kinect (2), vp8 (2), 264 (2), considerably (2), affects (2), encoders (2), indicate (2), jvrc (2), streaming (2), moment (2), versatile (2), moments (2), matter (2), processes (2), solved (2), inherent (2), interactions (2), article (2), discussed (2), removing (2), containing (2), removed (2), occluded (2), generalizes (2), stable (2), greater (2), granados (2), seen (2), perspectives (2), tedious (2), looking (2), down (2), 285 (2), photos (2), seminal (2), major (2), tablets (2), glasses (2), parallax (2), located (2), behind (2), literature (2), styles (2), drawing (2), emerging (2), muff (2), mccann (2), analyzes (2), videoscape (2), videoscapes (2), labelling (2), neighbourhood (2), unifying (2), orders (2), unary (2), borrowed (2), experimentally (2), verified (2), improvement (2), sparsely (2), marking (2), candidate (2), chosen (2), arrangement (2), piecewise (2), estimated (2), epipolar (2), rehearsal (2), collaborative (2), paradigm (2), define (2), asymmetric (2), transmission (2), actorsâ (2), embodiments (2), presence (2), oyekoya (2), tecchia (2), slater (2), produce (2), limitations (2), posable (2), internal (2), friction (2), designs (2), calian (2), beaming (2), virtually (2), immersive (2), office (2), meeting (2), telepresence (2), binocular (2), right (2), blur (2), iso (2), intermediate (2), maintain (2), panoinserts (2), teleconferencing (2), surround (2), windows (2), panorama (2), findings (2), conferencing (2), chi (2), selections (2), strokes (2), precise (2), inaccuracies (2), random (2), crf (2), similarity (2), metrics (2), metric (2), connect (2), neighbors (2), node (2), measure (2), conditioned (2), increases (2), whilst (2), popular (2), producing (2), lenslets (2)


Text of the page (random words):
work we evaluate the recognition accuracy of 25 different gestures for state of the art computer vision based gesture recognition algorithms and for human observers we show that some gestures are consistently recognized more accurately than others by both vision based algorithms and humans we further identify similarities in the hand gesture recognition abilities of vision based systems and humans lastly by merging pairs of gestures with high miss classification rates we propose ten robust hand gestures for automotive interfaces which are classified with high and equal accuracy by vision based algorithms 2015 iccv robust model based 3d head pose estimation g p meyer s gupta i frosio d reddy j kautz ieee international conference on computer vision iccv december 2015 pages 3649 3657 pdf cvf we introduce a method for accurate three dimensional head pose estimation using a commodity depth camera we perform pose estimation by registering a morphable face model to the measured depth data using a combination of particle swarm optimization pso and the iterative closest point icp algorithm which minimizes a cost function that includes a 3d registration and a 2d overlap term the pose is estimated on the fly without requiring an explicit initialization or training phase our method handles large pose angles and partial occlusions by dynamically adapting to the reliable visible parts of the face it is robust and generalizes to different depth sensors without modification on the biwi kinect dataset we achieve best in class performance with average angular errors of 2 1 2 1 and 2 4 degrees for yaw pitch and roll respectively and an average translational error of 5 9 mm while running at 6 fps on a graphics processing unit cgf interactive sketch driven image synthesis d turmukhambetov n campbell d goldman j kautz computer graphics forum 34 8 december 2015 pages 130 142 pdf doi we present an interactive system for composing realistic images of an object under arbitrary pose and appearance specified by sketching our system draws inspiration from a traditional illustration workflow the user first sketches rough â massesâ of the object as ellipses to define an initial abstract pose that can then be refined with more detailed contours as desired the system is made robust to partial or inaccurate sketches using a reduced dimensionality model of pose space learnt from a labelled collection of photos throughout the composition process interactive visual feedback is provided to guide the user finally the user s partial or complete sketch complemented with appearance requirements is used to constrain the automatic synthesis of a novel high quality realistic image uist joint 5d pen input for light field displays j tompkin s muff j mccann h pfister j kautz m alexa w matusik acm user interface software and technology uist november 2015 pdf video slides www light field displays allow viewers to see view dependent 3d content as if looking through a window however existing work on light field display interaction is limited yet they have the potential to parallel 2d pen and touch screen systems which present a joint input and display surface for natural interaction we propose a 4d display and interaction space using a dual purpose lenslet array which combines light field display and light field pen sensing and allows us to estimate the 3d position and 2d orientation of the pen this method is simple and fast 150 hz with position accuracy of 2â 3 mm and precision of 0 2â 0 6 mm from 0â 350 mm away from the lenslet array and orientation accuracy of 2â and precision of 0 2â 0 3â within 50â further we 3d print the lenslet array with embedded baffles to reduce out of bounds cross talk and use an optical relay to allow interaction behind the focal plane we demonstrate our joint display sensing system with interactive light field painting 3dv mlmd maximum likelihood mixture decoupling for fast and accurate point cloud registration b eckart k kim a troccoli a kelly j kautz international conference on 3d vision october 2015 pages 241 249 pdf video registration of point cloud data pcd forms a core component of many 3d vision algorithms such as object matching and environment reconstruction in this paper we introduce a pcd registration algorithm that utilizes gaussian mixture models gmm and a novel dual mode parameter optimization technique which we call mixture decoupling we show how this decoupling technique facilitates both faster and more robust registration by first optimizing over the mixture parameters decoupling the mixture weights means and covariances from the points before optimizing over the 6dof registration parameters furthermore we frame both the decoupling and registration process inside a unified dual mode expectation maximization em framework for which we derive a maximum likelihood estimation mle solution along with a parallel implementation on the gpu we evaluate our mle based mixture decoupling mlmd registration method over both synthetic and real data showing better convergence for a wider range of initial conditions and higher speeds than previous state of the art methods hpg an adaptive acceleration structure for screen space ray tracing s widmer d pajak a schulz k pulli j kautz m goesele d luebke high performance graphics 2015 august 2015 pages 67 76 pdf supplemental video we propose an efficient acceleration structure for real time screen space ray tracing the hybrid data structure represents the scene geometry by combining a bounding volume hierarchy with local planar approximations this enables fast empty space skipping while tracing and yields exact intersection points for the planar approximation in combination with an occlusion aware ray traversal our algorithm is capable to quickly trace even multiple depth layers compared to prior work our technique improves the accuracy of the results is more general and allows for advanced image trans formations as all pixels can cast rays to arbitrary directions we demonstrate real time performance for several applications including depth of field rendering stereo warping and screen space ray traced reflections egsr filtering environment illumination for interactive physically based rendering in mixed reality s mehta k kim d pajak k pulli j kautz r ramamoorthi eurographics symposium on rendering 2015 june 2015 pdf supplemental video doi physically correct rendering of environment illumination has been a long standing challenge in interactive graphics since monte carlo ray tracing requires thousands of rays per pixel we propose accurate filtering of a noisy monte carlo image using fourier analysis our novel analysis extends previous works by showing that the shape of illumination spectra is not always a line or wedge as in previous approximations but rather an ellipsoid our primary contribution is an axis aligned filtering scheme that preserves the frequency content of the illumination we also propose a novel application of our technique to mixed reality scenes in which virtual objects are inserted into a real video stream so as to become indistinguishable from the real objects the virtual objects must be shaded with the real lighting conditions and the mutual illumination between real and virtual objects must also be determined for this we demonstrate a novel two mode path tracing approach that allows ray tracing a scene with image based real geometry and mesh based virtual geometry finally we are able to de noise a sparsely sampled image and render physically correct mixed reality scenes at over 5 fps on the gpu cvpr modeling object appearance using context conditioned component analysis d turmukhambetov n campbell s prince j kautz ieee conference on computer vision and pattern recognition cvpr june 2015 pages 4156 4164 pdf subspace models have been very successful at modeling the appearance of structured image datasets when the visual objects have been aligned in the images for example faces even with extensions that allow for global transformations or dense warps of the image the set of visual objects whose appearance may be modeled by such methods is limited they are unable to account for visual objects where occlusion leads to changing visibility of different parts of the object without a strict layered structure and where a one to one mapping between parts is not preserved for example bunches of bananas contain different numbers of bananas but each individual banana shares an appearance subspace in this work we remove the image space alignment limitations of existing subspace models by conditioning the models on a shape dependent context that allows for complex non linear structure within the appearance of the visual object to be captured and shared this allows us to exploit the advantages of subspace appearance models with non rigid deformable objects whilst also dealing with complex occlusions and varying numbers of parts we demonstrate the effectiveness of our new model with examples of structured in painting and appearance transfer cvprw hand gesture recognition with 3d convolutional neural networks p molchanov s gupta k kim j kautz ieee cvpr workshop on observing and understanding hands in action june 2015 winner of the viva hand gesture challenge pdf touchless hand gesture recognition systems are becoming important in automotive user interfaces as they improve safety and comfort various computer vision algorithms have employed color and depth cameras for hand gesture recognition but robust classification of gestures from different subjects performed under widely varying lighting conditions is still challenging we propose an algorithm for driversâ hand gesture recognition from challenging depth and intensity data using 3d convolutional neural networks our solution combines information from multiple spatial scales for the final prediction it also employs spatio temporal data augmentation for more effective training and to reduce potential overfitting our method achieves a correct classification rate of 77 5 on the viva challenge dataset cvprw locally non rigid registration for mobile hdr photography o gallo a troccoli j hu k pulli j kautz ieee cvpr embedded vision workshop june 2015 pdf image registration for stack based hdr photography is challenging if not properly accounted for camera motion and scene changes result in artifacts in the composite image unfortunately existing methods to address this problem are either accurate but too slow for mobile devices or fast but prone to failing we propose a method that fills this void our approach is extremely fast under 700ms on a commercial tablet for a pair of 5mp images and prevents the artifacts that arise from insufficient registration quality app optics slim near eye display using pinhole aperture arrays k aksit j kautz d luebke applied optics 54 11 april 2015 pages 3422 3427 www doi we report a new technique for building a wide angle lightweight thin form factor cost effective easy to manufacture near eye head mounted display hmd for virtual reality applications our approach adopts an aperture mask containing an array of pinholes and a screen as a source of imagery we demonstrate a proof of concept hmd prototype with a binocular field of view fov of 70 45 or total diagonal fov of 83 this fov should increase with the increasing display panel size the optical angular resolution supported in our prototype can go down to 1 4 2 1 arcmin by adopting a display with 20 30 µm pixel pitch cacm local laplacian filters edge aware image processing with a laplacian pyramid s paris s hasinoff j kautz communications of the acm research highlight 58 3 march 2015 pages 81 91 cacm cacm cover cacm interview the laplacian pyramid is ubiquitous for decomposing images into multiple scales and is widely used for image analysis however because it is constructed with spatially invariant gaussian kernels the laplacian pyramid is widely believed as being unable to represent edges well and as being ill suited for edge aware operations such as edge preserving smoothing and tone mapping to tackle these tasks a wealth of alternative techniques and representations have been proposed e g anisotropic diffusion neighborhood filtering and specialized wavelet bases while these methods have demonstrated successful results they come at the price of additional complexity often accompanied by higher computational cost or the need to post process the generated results in this paper we show state of the art edge aware processing using standard laplacian pyramids we characterize edges with a simple threshold on pixel values that allows us to differentiate large scale edges from small scale details building upon this result we propose a set of image filters to achieve edge preserving smoothing detail enhancement tone mapping and inverse tone mapping the advantage of our approach is its simplicity and flexibility relying only on simple point wise nonlinearities and small gaussian convolutions no optimization or post processing is required as we demonstrate our method produces consistently high quality results without degrading edges or introducing halos acm mm speaker following video subtitles y hu j kautz y yu and w wang acm transactions on multimedia computing communications and applications 11 2 january 2015 pages 32 1 32 17 acm dl arxiv we propose a new method for improving the presentation of subtitles in video e g tv and movies with conventional subtitles the viewer has to constantly look away from the main viewing area to read the subtitles at the bottom of the screen which disrupts the viewing experience and causes unnecessary eyestrain our method places on screen subtitles next to the respective speakers to allow the viewer to follow the visual content while simultaneously reading the subtitles we use novel identification algorithms to detect the speakers based on audio and visual information then the placement of the subtitles is determined using global optimization a comprehensive usability study indicated that our subtitle placement method outperformed both conventional fixed position subtitling and another previous dynamic subtitling method in terms of enhancing the overall viewing experience and reducing eyestrain 2014 siggraph asia flexisp a flexible camera image processing framework f heide m steinberger y t tsai n rouf d pajak d reddy o gallo j liu w heidrich k egiazarian j kautz k pulli acm transactions on graphics proceedings siggraph asia 2014 33 6 december 2014 pages 231 1 231 13 pdf supplemental pdf supplemental webpage conventional pipelines for capturing displaying and storing images are usually defined as a series of cascaded modules each responsible for addressing a particular problem while this divide and conquer approach offers many benefits it also introduces a cumulative error as each step in the pipeline only considers the output of the previous step not the original sensor data we propose an end to end system that is aware of the camera and...
Images from subpage: "jankautz.com/publications/Intrinsic3D_3DV17_Sup.pdf" Verify
Images from subpage: "jankautz.com/publications/LightweightReflectance_ICCV17.pdf... " Verify
Images from subpage: "jankautz.com/publications/LightweightReflectance_ICCV17_Sup.... " Verify
Images from subpage: "jankautz.com/publications/CascadedSceneFlow_3DV17.pdf... " Verify
Images from subpage: "jankautz.com/publications/CascadedSceneFlow_3DV17_Sup.pdf... " Verify

Verified site has: 391 subpage(s). Do you want to verify them? Verify pages:

1-5 6-10 11-15 16-20 21-25 26-30 31-35 36-40 41-45 46-50
51-55 56-60 61-65 66-70 71-75 76-80 81-85 86-90 91-95 96-100
101-105 106-110 111-115 116-120 121-125 126-130 131-135 136-140 141-145 146-150
151-155 156-160 161-165 166-170 171-175 176-180 181-185 186-190 191-195 196-200
201-205 206-210 211-215 216-220 221-225 226-230 231-235 236-240 241-245 246-250
251-255 256-260 261-265 266-270 271-275 276-280 281-285 286-290 291-295 296-300
301-305 306-310 311-315 316-320 321-325 326-330 331-335 336-340 341-345 346-350
351-355 356-360 361-365 366-370 371-375 376-380 381-385 386-390 391-391


The site also has 84 references to external domain(s).

 research.nvidia.com  Verify  nvidia.com  Verify  cvpr.thecvf.com  Verify
 nitrogen.minedojo.org  Verify  annual.ametsoc.org  Verify  arxiv.org  Verify
 wsj.com  Verify  bloomberg.com  Verify  reuters.com  Verify
 techcrunch.com  Verify  neurips.cc  Verify  iccv.thecvf.com  Verify
 developer.nvidia.com  Verify  iclr.cc  Verify  github.com  Verify
 nvidianews.nvidia.com  Verify  venturebeat.com  Verify  techradar.com  Verify
 tomsguide.com  Verify  eccv2024.ecva.net  Verify  cvpr2024.thecvf.com  Verify
 TODO  Verify  dl.acm.org  Verify  cvpr2023.thecvf.com  Verify
 icra2023.org  Verify  ics.uci.edu  Verify  icvl.ee.ic.ac.uk  Verify
 sites.google.com  Verify  nvlabs.github.io  Verify  openaccess.thecvf.com  Verify
 openreview.net  Verify  vcai.mpi-inf.mpg.de  Verify  whj363636.github.io  Verify
 navila-bot.github.io  Verify  nature.com  Verify  anjiecheng.me  Verify
 sifeiliu.net  Verify  oasisyang.github.io  Verify  bundlesdf.github.io  Verify
 doi.org  Verify  youtu.be  Verify  deepimagination.cc  Verify
 authors.elsevier.com  Verify  a-vit.github.io  Verify  gradvit.github.io  Verify
 jerryxu.net  Verify  jitengmu.github.io  Verify  nv-tlabs.github.io  Verify
 ieeexplore.ieee.org  Verify  markboss.me  Verify  youtube.com  Verify
 vllab.ucmerced.edu  Verify  tcwang0509.github.io  Verify  mingyuliu.blog  Verify
 cvc.ucsb.edu  Verify  lmurmann.net  Verify  cv-foundation.org  Verify
 jamestompkin.com  Verify  dx.doi.org  Verify  cvrr.ucsd.edu  Verify
 opticsinfobase.org  Verify  cacm.acm.org  Verify  bit.ly  Verify
 imagine.enpc.fr  Verify  vecg.cs.ucl.ac.uk  Verify  visual.cs.ucl.ac.uk  Verify
 onlinelibrary.wiley.com  Verify  jvrb.org  Verify  doi.ieeecomputersociety.org  Verify
 gvv.mpi-inf.mpg.de  Verify  mpi-inf.mpg.de  Verify  s2012.siggraph.org  Verify
 cs.ucl.ac.uk  Verify  people.csail.mit.edu  Verify  doi.acm.org  Verify
 research.edm.uhasselt.be  Verify  diglib.eg.org  Verify  www3.interscience.wiley.com  Verify
 computer.org  Verify  acm.org  Verify  amazon.com  Verify
 gdcvault.com  Verify  twitter.com  Verify  linkedin.com  Verify


Top 50 hastags from of all verified websites.

Supplementary Information (add-on for SEO geeks)*- See more on header.verify-www.com

Header

HTTP/2 200
content-type text/html
last-modified Mon, 15 Jun 2026 17:36:37 GMT
accept-ranges bytes
content-encoding gzip
vary Accept-Encoding
content-length 101094
date Mon, 06 Jul 2026 18:24:29 GMT
server LiteSpeed
x-turbo-charged-by LiteSpeed

Meta Tags

title="Jan Kautz"
http-equiv="Content-Type" content="text/html; charset=iso-8859-1"
content="Jan Kautz"
name="description" content="Personal webpage of Jan Kautz."
name="author" content="Jan Kautz"
name="keywords" content="Jan Kautz NVIDIA"
name="viewport" content="width=device-width, initial-scale=1"

Load Info

page size434776
load time (s)0.985818
redirect count0
speed download102633
server IP 198.54.115.9
* all occurrences of the string "http://" have been changed to "htt???/"