Meta tags:
author=Christoph Lassner;
description=;

Headings (most frequently used words):

neural, for, volumetric, capture, and, dynamic, publications, lens, modeling, neuwigs, model, hair, animation, assets, object, rendering, interactive, environments, search, biography, featured, recent, christoph, lassner, scenerflow, time, consistent, reconstruction, of, general, scenes, relighting, with, subsurface, scattering, by, learning, the, radiance, transfer, gradient, cite,

Text of the page (most frequently used words):
and (29), for (23), the (16), rendering (14), #christoph (13), lassner (13), #neural (13), cite (9), pdf (8), that (8), can (8), create (8), aljaz (6), bozic (6), new (6), volumetric (6), hair (6), propose (6), lens (6), publications (5), assets (5), video (5), time (5), model (5), work (5), radiance (4), representation (4), used (4), with (4), capture (4), cvpr2023 (4), models (4), dynamic (4), calibration (4), was (4), meta (4), see (3), from (3), smartphone (3), rendered (3), object (3), interactive (3), environments (3), project (3), michael (3), using (3), use (3), gradient (3), based (3), modeling (3), systems (3), all (2), luke (2), doukakis (2), denis (2), gladkov (2), present (2), field (2), photorealistic (2), simple (2), volumetrically (2), real (2), state (2), art (2), game (2), engines (2), comparably (2), fast (2), mesh (2), but (2), includes (2), effects (2), suitable (2), fur (2), jessica (2), hodgins (2), zollhoefer (2), jason (2), saragih (2), chen (2), cao (2), stephen (2), lombardi (2), tuur (2), stuyck (2), giljoo (2), nam (2), ziyan (2), wang (2), drivable (2), accurate (2), primitives (2), temporal (2), neuwigs (2), animation (2), noah (2), snavely (2), wenqi (2), xian (2), versatile (2), easy (2), trivially (2), optimization (2), pipelines (2), point (2), projection (2), also (2), dataset (2), evaluation (2), strategy (2), marker (2), boards (2), method (2), reconstruct (2), faithfully (2), learning (2), scenes (2), 2022 (2), june (2), 2023 (2), featured (2), would (2), challenges (2), computer (2), engineering (2), research (2), labs (2), amazon (2), world (2), perception (2), example (2), system (2), your (2), download, copy, 2024, powered, hugo, academic, theme, trevor, darrell, carlos, aliaga, shunsuke, saito, shizhan, zhu, currently, best, performing, possible, lighting, relighting, subsurface, scattering, transfer, christian, theobalt, zollhöfer, vladislav, golyanik, edith, tretschk, novel, render, including, dense, scene, flow, establishing, correspondences, over, scenerflow, consistent, reconstruction, general, quickly, discover, relevant, content, filtering, recent, december, you, like, together, intersection, machine, graphics, vision, please, reach, out, previously, leading, teams, epic, games, reality, before, joining, worked, startup, acquired, completed, phd, tübingen, max, planck, institute, intelligent, bernstein, center, computational, neuroscience, bodylabs, same, very, interested, such, awarded, honorable, mention, acm, multimedia, open, source, software, competition, 2016, decision, forests, 2021, wrote, renderer, now, sphere, backend, love, find, better, ways, low, level, autodifferentiation, gpus, pytorch3d, pulsar, deeply, curious, about, how, build, virtual, representations, physical, optimized, efficiently, match, our, visual, beyond, lot, focuses, humans, created, human, pose, estimation, which, part, body, team, reconstructing, fields, interactively, presented, inverse, zhao, dong, cnet, connect, halo, nbf, arch, hvh, tava, nerf, veo, founder, spatial, intelligence, company, biography, home, search,

Text of the page (random words):
christoph lassner search christoph lassner christoph lassner home publications christoph lassner biography i am co founder of world labs the spatial intelligence company i am deeply curious about how we can build interactive virtual representations for the physical world that can be optimized and rendered efficiently to faithfully match our perception visual and beyond see for example neural assets veo neural 3d video nr nerf a lot of my work focuses on perception and rendering systems for humans see for example tava hvh arch nbf up i created the human pose estimation system for amazon halo which is part of a system to create a 3d model of your body using your smartphone my team s work at meta on reconstructing and rendering radiance fields interactively was featured at meta connect 2022 and on cnet co presented with zhao dong et al s work on inverse rendering at the same time i am very interested in the engineering challenges such systems create and was awarded an honorable mention at the acm multimedia open source software competition 2016 for my work on decision forests in 2021 i wrote the pulsar renderer now the sphere based rendering backend for pytorch3d and would love to find better ways to use low level autodifferentiation on gpus previously i was leading research teams at epic games and meta reality labs research before joining meta i worked at bodylabs a startup that was acquired by amazon i completed my phd at the bernstein center for computational neuroscience and the max planck institute for intelligent systems in tübingen if you would like to work together on challenges at the intersection of machine learning computer graphics and computer vision from modeling to engineering please reach out featured publications wenqi xian aljaz bozic noah snavely christoph lassner june 2023 cvpr2023 neural lens modeling we propose a neural lens model that is versatile easy to use and can be trivially used in gradient based optimization pipelines for point projection and rendering we also propose a new dataset for evaluation of lens and calibration models and a new strategy to create marker boards for calibration pdf cite ziyan wang giljoo nam tuur stuyck stephen lombardi chen cao jason saragih michael zollhoefer jessica hodgins christoph lassner june 2023 cvpr2023 neuwigs a neural dynamic model for volumetric hair capture and animation we create a drivable and accurate hair representation using neural rendering primitives and temporal models pdf cite project aljaz bozic denis gladkov luke doukakis christoph lassner december 2022 neural assets volumetric object capture and rendering for interactive environments we present a new radiance field representation that can be used to create photorealistic assets from a simple smartphone video that can be rendered volumetrically in real time in state of the art game engines rendering is comparably fast with mesh rendering but includes volumetric effects and is suitable for fur hair pdf cite recent publications quickly discover relevant content by filtering publications scenerflow time consistent reconstruction of general dynamic scenes we propose a novel method to reconstruct and render dynamic scenes including dense scene flow establishing correspondences over time edith tretschk vladislav golyanik michael zollhöfer aljaz bozic christoph lassner christian theobalt pdf cite project video neural relighting with subsurface scattering by learning the radiance transfer gradient we propose the currently best performing method to reconstruct object faithfully for all possible lighting environments shizhan zhu shunsuke saito aljaz bozic carlos aliaga trevor darrell christoph lassner pdf cite video neural lens modeling we propose a neural lens model that is versatile easy to use and can be trivially used in gradient based optimization pipelines for point projection and rendering we also propose a new dataset for evaluation of lens and calibration models and a new strategy to create marker boards for calibration wenqi xian aljaz bozic noah snavely christoph lassner cvpr2023 pdf cite neuwigs a neural dynamic model for volumetric hair capture and animation we create a drivable and accurate hair representation using neural rendering primitives and temporal models ziyan wang giljoo nam tuur stuyck stephen lombardi chen cao jason saragih michael zollhoefer jessica hodgins christoph lassner cvpr2023 pdf cite project neural assets volumetric object capture and rendering for interactive environments we present a new radiance field representation that can be used to create photorealistic assets from a simple smartphone video that can be rendered volumetrically in real time in state of the art game engines rendering is comparably fast with mesh rendering but includes volumetric effects and is suitable for fur hair aljaz bozic denis gladkov luke doukakis christoph lassner pdf cite see all publications 2024 christoph lassner powered by the academic theme for hugo cite copy download