Meta tags:
Headings (most frequently used words):
video, from, image, 3d, the, and, learning, generation, generative, motion, in, view, neural, of, for, with, dynamic, videos, rendering, single, images, decomposition, zhengqi, li, self, interactive, world, model, time, autoregressive, diffusion, structure, casual, internet, estimation, large, scale, based, scenes, photos, by, people, watching, intrinsic, through, news, publications, technical, reports, media, coverage, evaluation, unlocks, any, step, text, to, relic, long, horizon, memory, editing, point, tracks, motionstream, real, controls, forcing, bridging, train, test, gap, megasam, accurate, fast, robust, stereo4d, how, things, move, stereo, can, models, help, pose, streetscapes, consistent, street, using, dynamics, tracking, everything, everywhere, all, at, once, dynibar, persistent, nature, unbounded, worlds, omnimatte3d, associating, objects, their, effects, unconstrained, monocular, infinitenature, zero, perpetual, natural, reconstruction, wild, moments, near, duplicate, deformable, sprites, unsupervised, iron, inverse, optimizing, sdfs, materials, photometric, scene, flow, fields, space, synthesis, crowdsampling, plenoptic, function, uprightnet, geometry, aware, camera, orientation, depths, moving, frozen, cgintrinsics, better, physically, megadepth, depth, prediction, mosaic, construction, agricultural, applications, high, speed, autonomous, quadrotor, navigation, paths,
Text of the page (most frequently used words):
paper (41), #zhengqi (33), cvpr (31), the (30), www (28), video (26), noah (23), snavely (23), was (22), and (19), your (17), browser (17), does (17), not (17), support (17), tag (17), accepted (15), best (13), google (11), learning (11), from (11), image (10), richard (10), oral (9), wang (9), 2022 (9), selected (9), research (8), tucker (8), 2023 (8), 2025 (8), our (8), for (7), 2018 (7), eccv (7), 2020 (7), honorable (7), mention (7), zhang (7), depth (6), people (6), view (6), iccv (6), eli (6), shechtman (6), qianqian (6), award (6), 2024 (6), two (5), moving (5), photos (5), 2019 (5), forrester (5), cole (5), dynamic (5), generative (5), with (5), videos (4), prediction (4), time (4), single (4), intrinsic (4), decomposition (4), tpami (4), neural (4), siggraph (4), motion (4), generation (4), aleksander (4), holynski (4), huang (4), adobe (4), fellowship (4), minute (3), papers (3), watching (3), camera (3), world (3), 2016 (3), internet (3), rendering (3), estimation (3), images (3), 2021 (3), scenes (3), angjoo (3), kanazawa (3), zhou (3), student (3), presentation (3), three (3), one (3), scientist (3), all (2), 雷锋网 (2), mannequin (2), challenge (2), this (2), about (2), frozen (2), you (2), robotics (2), cornell (2), into (2), technical (2), university (2), through (2), large (2), scale (2), demo (2), spotlight (2), cgintrinsics (2), based (2), supplementary (2), doc (2), liu (2), william (2), freeman (2), wenqi (2), xian (2), matthew (2), fisher (2), geometry (2), aware (2), orientation (2), crowdsampling (2), plenoptic (2), function (2), scene (2), space (2), synthesis (2), kai (2), vickie (2), unsupervised (2), david (2), zhoutong (2), structure (2), casual (2), model (2), dynibar (2), ruojin (2), cai (2), dynamics (2), autoregressive (2), diffusion (2), linyi (2), jin (2), megasam (2), xun (2), self (2), interactive (2), lee (2), publications (2), received (2), thanks (2), were (2), them (2), will (2), serve (2), area (2), chair (2), news (2), deepmind (2), design, html5, rights, reserved, 通过网络无标注延时摄影学习本征图像分解, 单个运动摄像头估计运动物体深度, 谷歌挑战新难题, robinly, cvpr2019爆款论文作者现场解读, 视觉语言导航, 运动视频深度预测, 6d姿态估计, 量子位, 谷歌预测景深新研究, 即使相机人物都在动, 单一视点也能合成3d深度图, seamless, シーン内の人とカメラの両方が移動していても1台の単眼カメラから深度を予測するdeep, learningを用いた手法を発表, venturebeat, leverages, youtube, improve, learns, movement, mit, technology, review, did, are, now, advancing, blog, deep, approach, chronicle, tool, transforms, landmark, experiences, learned, stop, new, fly, but, deeper, media, coverage, report, minnesota, twin, cities, tien, luis, carrillo, arce, stergios, roumeliotis, high, speed, autonomous, quadrotor, navigation, paths, ieee, automation, letters, icra, volkan, isler, mosaic, construction, agricultural, applications, also, invited, presented, bridges, workshop, megadepth, better, physically, tali, dekel, depths, indicates, equal, contribution, jonathan, eisenmann, uprightnet, abe, davis, simon, niklaus, oliver, flow, fields, fujun, luan, iron, inverse, optimizing, sdfs, materials, photometric, deformable, sprites, salesin, brian, curless, janne, kontkanen, moments, near, duplicate, conference, proceedings, jiaming, sun, chen, hadar, averbuch, elor, xiaowei, reconstruction, wild, michael, rubinstein, infinitenature, zero, perpetual, natural, mohammed, suhail, erika, leonid, sigal, omnimatte3d, associating, objects, their, effects, unconstrained, monocular, lucy, chai, phillip, isola, persistent, nature, unbounded, worlds, yen, chang, bharath, hariharan, tracking, everything, everywhere, once, boyang, deng, leo, guibas, gordon, wetzstein, streetscapes, consistent, street, using, highlight, jason, philipp, henzler, ricardo, martin, brualla, can, models, help, pose, fouhey, stereo4d, how, things, move, stereo, accurate, fast, robust, neurips, guande, mingyuan, forcing, bridging, train, test, gap, joonghyuk, shin, jun, yan, zhu, jaesik, park, motionstream, real, controls, yao, chih, jiahui, jui, hsien, joon, young, jia, bin, editing, point, tracks, yicong, hong, yiqun, mei, chongjian, yiran, yang, sai, yannick, hold, geoffroy, mike, roberts, kalyan, sunkavalli, feng, hao, tan, relic, long, horizon, memory, xin, xiaojuan, zhe, lin, tianyu, yotam, nitzan, evaluation, unlocks, any, step, text, reports, selcted, spolight, decompostion, worldwide, extended, phd, omnimotion, resume, previously, earned, computer, science, where, advised, prof, work, has, been, recognized, several, honors, including, baidu, global, top, 100, rising, stars, awards, email, github, scholar, linkedin, projects,
Text of the page (random words):
zhengqi li zhengqi li research scientist at google deepmind about news publications projects linkedin google scholar github email zhengqi li i am a research scientist at google deepmind previously i was a research scientist at google research and adobe research i earned my ph d in computer science from cornell university where i was advised by prof noah snavely my work has been recognized with several honors including the 2020 google ph d fellowship the 2020 adobe research fellowship the 2021 baidu global top 100 rising stars in ai best paper honorable mention awards at cvpr 2019 cvpr 2023 and cvpr 2025 the iccv 2023 best student paper award and the cvpr 2024 best paper award resume cv news three paper was accepted to cvpr 2025 megasam was selected as best paper honorable mention i will serve as an area chair for cvpr 2025 and iccv 2025 one paper was accepted to siggraph 2024 generative image dynamics was accepted to cvpr 2024 and selected as best paper award omnimotion was accepted to iccv 2023 and selected as best student paper award three paper was accepted to cvpr 2023 dynibar was selected as best paper honorable mention i will serve as an area chair for cvpr 2024 two paper was accepted to eccv 2022 one of them was selected as oral presentation one paper was accepted to siggraph 2022 three paper were accepted to cvpr 2022 two of them were selected as oral presentation our paper on dynamic scenes space time view synthesis was accepted to cvpr 2021 i received 2020 google phd fellowship thanks google our paper on crowdsampling the plenoptic function was accepted to eccv 2020 and was selected as oral presentation our extended paper on learning depth of moving people was accepted to tpami i received 2020 adobe research fellowship 10 selected worldwide thanks adobe our paper on geometry aware camera orientation estimation was accepted to iccv 2019 our paper on learning the depth of dynamic scene with moving people was selected as cvpr 2019 best paper honorable mention our paper on learning intrinsic image decompostion from cgintrinsics was accepted to eccv 2018 our paper on unsupervised learning intrinsic image decomposition was accepted to cvpr 2018 and was selcted for a spolight oral our paper on learning single view depth prediction from internet photos was accepted to cvpr 2018 publications technical reports self evaluation unlocks any step text to image generation xin yu xiaojuan qi zhengqi li kai zhang richard zhang zhe lin eli shechtman tianyu wang yotam nitzan www your browser does not support the video tag relic interactive video world model with long horizon memory yicong hong yiqun mei chongjian ge yiran xu yang zhou sai bi yannick hold geoffroy mike roberts matthew fisher eli shechtman kalyan sunkavalli feng liu zhengqi li hao tan www your browser does not support the video tag generative video motion editing with 3d point tracks yao chih lee zhoutong zhang jiahui huang jui hsien wang joon young lee jia bin huang eli shechtman zhengqi li www your browser does not support the video tag motionstream real time video generation with interactive motion controls joonghyuk shin zhengqi li richard zhang jun yan zhu jaesik park eli shechtman xun huang www your browser does not support the video tag self forcing bridging the train test gap in autoregressive video diffusion xun huang zhengqi li guande he mingyuan zhou eli shechtman in neurips 2025 spotlight www your browser does not support the video tag megasam accurate fast and robust structure and motion from casual dynamic videos zhengqi li richard tucker forrester cole qianqian wang linyi jin vickie ye angjoo kanazawa aleksander holynski noah snavely in cvpr 2025 best paper honorable mention www your browser does not support the video tag stereo4d learning how things move in 3d from internet stereo videos linyi jin richard tucker zhengqi li david fouhey noah snavely aleksander holynski in cvpr 2025 oral www can generative video models help pose estimation ruojin cai jason y zhang philipp henzler zhengqi li noah snavely ricardo martin brualla in cvpr 2025 highlight www your browser does not support the video tag streetscapes large scale consistent street view generation using autoregressive video diffusion boyang deng richard tucker zhengqi li leo guibas noah snavely gordon wetzstein in siggraph 2024 www your browser does not support the video tag generative image dynamics zhengqi li richard tucker noah snavely aleksander holynski in cvpr 2024 best paper award www your browser does not support the video tag tracking everything everywhere all at once qianqian wang yen yu chang ruojin cai zhengqi li bharath hariharan aleksander holynski noah snavely in iccv 2023 best student paper award www your browser does not support the video tag dynibar neural dynamic image based rendering zhengqi li qianqian wang forrester cole richard tucker noah snavely in cvpr 2023 best paper honorable mention www your browser does not support the video tag persistent nature a generative model of unbounded 3d worlds lucy chai richard tucker zhengqi li phillip isola noah snavely in cvpr 2023 www omnimatte3d associating objects and their effects in unconstrained monocular video mohammed suhail erika lu zhengqi li noah snavely leonid sigal forrester cole in cvpr 2023 www your browser does not support the video tag infinitenature zero learning perpetual view generation of natural scenes from single images zhengqi li qianqian wang noah snavely angjoo kanazawa in eccv 2022 oral www your browser does not support the video tag structure and motion for casual videos zhoutong zhang forrester cole zhengqi li michael rubinstein noah snavely william t freeman in eccv 2022 your browser does not support the video tag neural 3d reconstruction in the wild jiaming sun xi chen qianqian wang zhengqi li hadar averbuch elor xiaowei zhou noah snavely in siggraph 2022 conference proceedings paper www your browser does not support the video tag 3d moments from near duplicate photos qianqian wang zhengqi li david salesin noah snavely brian curless janne kontkanen in cvpr 2022 paper www your browser does not support the video tag deformable sprites for unsupervised video decomposition vickie ye zhengqi li richard tucker angjoo kanazawa noah snavely in cvpr 2022 oral paper www your browser does not support the video tag iron inverse rendering by optimizing neural sdfs and materials from photometric images kai zhang fujun luan zhengqi li noah snavely in cvpr 2022 oral paper www neural scene flow fields for space time view synthesis of dynamic scenes zhengqi li simon niklaus noah snavely oliver wang in cvpr 2021 paper www crowdsampling the plenoptic function zhengqi li wenqi xian abe davis noah snavely in eccv 2020 oral paper www uprightnet geometry aware camera orientation estimation from single images wenqi xian zhengqi li matthew fisher jonathan eisenmann eli shechtman noah snavely in iccv 2019 indicates equal contribution paper www learning the depths of moving people by watching frozen people zhengqi li tali dekel forrester cole richard tucker noah snavely ce liu william t freeman in cvpr 2019 best paper honorable mention in tpami 2020 cvpr paper cvpr supplementary doc tpami paper tpami supplementary doc www demo video cgintrinsics better intrinsic image decomposition through physically based rendering zhengqi li and noah snavely in eccv 2018 paper www learning intrinsic image decomposition from watching the world zhengqi li and noah snavely in cvpr 2018 spotlight paper www megadepth learning single view depth prediction from internet photos zhengqi li and noah snavely in cvpr 2018 also invited to be presented at bridges to 3d workshop cvpr 2018 paper www demo large scale image mosaic construction for agricultural applications zhengqi li and volkan isler in ieee robotics and automation letters 2016 in icra 2016 paper www high speed autonomous quadrotor navigation through image paths tien do luis c carrillo arce zhengqi li and stergios i roumeliotis technical report university of minnesota twin cities 2016 paper www media coverage two minute papers google s new ai fly into photos but deeper two minute papers this ai learned to stop time cornell chronicle tool transforms world landmark photos into 4d experiences google ai blog moving camera moving people a deep learning approach to depth prediction mit technology review if you did the mannequin challenge you are now advancing robotics research two minute papers this ai learns about movement by watching frozen people venturebeat google leverages on youtube videos of mannequin challenge to improve depth prediction seamless google シーン内の人とカメラの両方が移動していても1台の単眼カメラから深度を予測するdeep learningを用いた手法を発表 量子位 谷歌预测景深新研究 即使相机人物都在动 单一视点也能合成3d深度图 robinly cvpr2019爆款论文作者现场解读 视觉语言导航 运动视频深度预测 6d姿态估计 雷锋网 单个运动摄像头估计运动物体深度 谷歌挑战新难题 雷锋网 通过网络无标注延时摄影学习本征图像分解 zhengqi li all rights reserved design html5 up
|
