Meta tags:
author=Ayush Saraf;

Headings (most frequently used words):

hyperscape, vibe, coded, projects, research, miscellanea, reviews, coverage,

Text of the page (most frequently used words):
video (16), the (13), ayush (12), saraf (12), your (11), paper (9), #project (9), page (9), and (9), browser (8), does (8), not (8), support (8), tag (8), jia (8), bin (8), huang (8), code (7), johannes (7), kopf (7), 2023 (6), cvpr (6), changil (6), kim (6), peer (5), reviewer (5), chen (5), gao (5), with (4), real (4), hyperscape (4), from (3), iccv (3), dynamic (3), for (3), research (3), world (3), github (3), log (3), claude (3), meta (3), wacv (2), 2024 (2), 2020 (2), suhib (2), alsisan (2), michael (2), google (2), 2021 (2), xuejian (2), rong (2), view (2), synthesis (2), hung (2), tseng (2), robust (2), yipeng (2), wang (2), modeling (2), qinbo (2), textured (2), time (2), 2025 (2), computer (2), worlds (2), live (2), workout (2), talking (2), logs (2), entirely (2), khana (2), tech (2), lead (2), spaces (2), gaussian (2), splatting (2), reality (2), new (2), template, jon, barron, ijcv, program, committe, xrnerf, miscellanea, siggraph, kevin, matzen, ocean, quigley, francis, yangming, chong, josh, patterson, jan, frahm, shu, matthew, peizhao, zhang, zijian, peter, vajda, cohen, one, shot, photography, colab, eccv, flow, edge, guided, completion, bmvc, peiye, zhuang, denis, demandolx, amico, amodal, instance, composition, monocular, 2022, boosting, residual, transfer, lun, liu, andreas, meuleman, yung, chuang, radiance, fields, geng, lin, matthias, zwicker, omnimatterf, omnimatte, background, jaehoon, choi, rajvi, shah, dinesh, manocha, ltm, lightweight, mesh, extraction, refinement, large, unbounded, scenes, efficient, storage, rendering, brian, chao, lorenzo, porzi, tuotuo, gordon, wetzstein, gaussians, enhanced, scene, appearance, interested, machine, learning, vision, graphics, reconstruction, genai, much, revolves, around, creating, observing, through, images, interpretting, user, imagination, via, geneative, models, self, hosted, athletic, clubs, members, snap, board, get, weight, suggestions, sets, track, prs, over, food, tracks, pantry, macros, grocery, list, runs, inside, session, vibe, coded, projects, gizmodo, ghost, howls, uploadvr, cnet, techcrunch, press, reviews, coverage, september, nbsp, lets, you, scan, quest, headset, explore, them, photorealistic, quality, technology, uses, recreate, physical, environments, virtual, start, led, development, core, pipeline, tooling, infrastructure, launched, connect, horizon, twitter, scholar, email, staff, software, engineer, york, where, work, generation, build, creative, tools, that, help, people, create, whether, capturing, imagining, ones, labs,

Text of the page (random words):
ayush saraf ayush saraf i am a staff software engineer at meta reality labs in new york where i work on hyperscape and 3d world generation i build creative tools that help people create 3d worlds whether capturing real spaces or imagining entirely new ones email google scholar twitter github hyperscape your browser does not support the video tag meta horizon hyperscape ayush saraf tech lead launched at meta connect september 2025 nbsp hyperscape lets you scan real world spaces with a quest headset and explore them in vr with photorealistic quality the technology uses gaussian splatting to recreate physical environments in virtual reality as tech lead from the start i led development of the core gaussian splatting pipeline tooling and research infrastructure reviews coverage press techcrunch cnet uploadvr the ghost howls gizmodo vibe coded projects khana khana log food by talking to claude tracks your pantry macros and grocery list runs entirely inside a claude code session live github ac logs ac logs a self hosted workout log for athletic clubs members snap the workout board get weight suggestions log your sets by talking to claude and track your prs over time live github research i m interested in machine learning computer vision computer graphics 3d reconstruction and genai much of my research revolves around creating 3d worlds by observing real world through images or by interpretting user s imagination via geneative models your browser does not support the video tag textured gaussians for enhanced 3d scene appearance modeling brian chao hung yu tseng lorenzo porzi chen gao tuotuo li qinbo li ayush saraf jia bin huang johannes kopf gordon wetzstein changil kim cvpr 2025 project page paper your browser does not support the video tag ltm lightweight textured mesh extraction and refinement of large unbounded scenes for efficient storage and real time rendering jaehoon choi rajvi shah qinbo li yipeng wang ayush saraf changil kim jia bin huang dinesh manocha suhib alsisan johannes kopf cvpr 2024 project page paper your browser does not support the video tag omnimatterf robust omnimatte with 3d background modeling geng lin chen gao jia bin huang changil kim yipeng wang matthias zwicker ayush saraf iccv 2023 project page video paper code your browser does not support the video tag robust dynamic radiance fields yu lun liu chen gao andreas meuleman hung yu tseng ayush saraf changil kim yung yu chuang johannes kopf jia bin huang cvpr 2023 project page video paper code boosting view synthesis with residual transfer xuejian rong jia bin huang ayush saraf changil kim johannes kopf cvpr 2022 project page video paper code your browser does not support the video tag dynamic view synthesis from dynamic monocular video chen gao ayush saraf johannes kopf jia bin huang iccv 2021 project page video paper code amico amodal instance composition peiye zhuang denis demandolx ayush saraf xuejian rong changil kim and jia bin huang bmvc 2021 project page paper your browser does not support the video tag flow edge guided video completion chen gao ayush saraf jia bin huang johannes kopf eccv 2020 project page video paper code google colab your browser does not support the video tag one shot 3d photography johannes kopf kevin matzen suhib alsisan ocean quigley francis ge yangming chong josh patterson jan michael frahm shu wu matthew yu peizhao zhang zijian he peter vajda ayush saraf michael f cohen siggraph 2020 project page video paper code miscellanea program committe xrnerf cvpr 2023 peer reviewer cvpr 2023 peer reviewer iccv 2023 peer reviewer wacv 2023 peer reviewer wacv 2024 peer reviewer ijcv template from jon barron