Meta tags:
author=Ziyu Chen;
description=Ziyu Chen - PhD Student in Computer Science at Stanford University.;
keywords=Ziyu Chen, Stanford University, Computer Science, PhD;

Headings (most frequently used words):

-

Text of the page (most frequently used words):
ziyu (9), chen (9), stanford (9), and (9), the (9), wang (8), fellowship (7), 2025 (7), for (7), university (6), 2026 (6), video (6), shanghai (5), sep (5), scene (5), reconstruction (5), not (5), paper (5), abstract (5), yue (5), jiao (4), tong (4), 2022 (4), your (4), browser (4), does (4), support (4), tag (4), with (4), code (4), visual (4), research (4), 2023 (3), graduate (3), qualcomm (3), innovation (3), jun (3), dynamic (3), urban (3), actors (3), tracing (3), framework (3), images (3), song (3), from (3), generation (3), omnire (3), website (3), yang (3), prof (3), 2024 (3), 2018 (2), electrical (2), engineering (2), mar (2), computer (2), science (2), education (2), 3dgs (2), simulation (2), rigid (2), vehicles (2), non (2), supported (2), based (2), realistic (2), light (2), visibility (2), estimation (2), wei (2), pipeline (2), that (2), 360 (2), panoramas (2), using (2), unregistered (2), nfov (2), conditioned (2), driving (2), iclr (2), spotlight (2), marco (2), pavone (2), benchmark (2), suite (2), real (2), iros (2), neverwhere (2), realwonder (2), jiajun (2), equal (2), advised (2), talk (2), accepted (2), all (2), honored (2), receive (2), student (2), about (2), zhiyuan, honor, national, scholarship, selected, awards, china, present, codebase, featuring, different, gaussian, representations, pedestrians, cyclists, etc, datasets, include, waymo, pandaset, argoverse2, kitti, nuscenes, nuplan, open, source, our, reflectance, factorization, produces, photo, novel, view, nearly, 10x, speedup, compared, same, applying, volumetric, integration, eccv, xuan, xiao, yikang, dongliang, jianfei, guo, chenjing, ding, fast, neural, surfaces, sphere, proposed, diffusion, generates, complete, one, more, captured, arbitrary, angles, this, only, delivers, superior, quality, but, also, offers, broader, range, outcomes, due, its, text, capability, acm, multimedia, rong, xie, ling, jionghao, degree, panorama, few, holistic, provides, comprehensive, coverage, including, static, backgrounds, rigidly, moving, review, sanja, fidler, zan, gojcic, litany, boris, ivanovic, janick, martinez, esturo, riccardo, lutio, jiahui, huang, jiawei, omni, toolchain, hyper, locomotion, building, high, fidelity, digital, twins, world, environments, closed, loop, evaluation, phillip, isola, xiaolong, john, leonard, yajvan, ravan, zhao, qiu, kevin, gio, huh, kai, mcclennen, ran, choi, alan, haoran, chang, henghui, bao, parkour, turns, single, image, into, interactive, controllable, model, incorporating, physics, enables, physically, grounded, interactions, arxiv, hong, xing, zizhang, liu, time, physical, action, contribution, advising, full, list, show, earlier, joined, intern, geometry, vision, learning, lab, released, system, drivestudio, aug, invited, liauto, mit, computing, seminar, visited, beautiful, boston, oct, shout, out, collaborators, feb, may, are, thanks, coauthors, instantsfm, updates, previously, worked, usc, collaborated, closely, received, degrees, working, generative, models, generously, ziyuchen, edu, email,

Text of the page (random words):
ziyu chen ziyu chen about research education ziyu chen ph d student in computer science stanford university email ziyuchen stanford edu about me i am a cs ph d student at stanford advised by jiajun wu i m working on visual generative models my research is generously supported by the stanford graduate fellowship and qualcomm innovation fellowship previously i worked with prof yue wang at usc and collaborated closely with prof marco pavone i received my m s and b s degrees from shanghai jiao tong university updates jun 2026 neverwhere and instantsfm are accepted to iros 2026 thanks to all coauthors may 2026 honored to receive the qualcomm innovation fellowship mar 2025 honored to receive the stanford graduate fellowship feb 2025 omnire is accepted to iclr 2025 as spotlight shout out to all my collaborators oct 2024 talk at mit visual computing seminar visited beautiful boston sep 2024 invited talk at liauto on urban scene reconstruction aug 2024 released drivestudio a 3dgs system for driving reconstruction simulation sep 2023 joined geometry vision and learning lab as a research intern advised by prof yue wang show earlier research equal contribution equal advising full list your browser does not support the video tag realwonder real time physical action conditioned video generation wei liu ziyu chen zizhang li yue wang hong xing yu jiajun wu arxiv 2026 abstract paper website code realwonder turns a single image into an interactive scene using a controllable video model by incorporating physics it enables physically grounded 3d interactions the neverwhere visual parkour benchmark suite ziyu chen henghui bao haoran chang alan yu ran choi kai mcclennen gio huh kevin yang ri zhao qiu yajvan ravan john j leonard xiaolong wang phillip isola ge yang yue wang iros 2026 abstract paper website a toolchain and benchmark suite for hyper realistic visual locomotion building high fidelity digital twins of real world environments for closed loop evaluation your browser does not support the video tag omnire omni urban scene reconstruction ziyu chen jiawei yang jiahui huang riccardo de lutio janick martinez esturo boris ivanovic or litany zan gojcic sanja fidler marco pavone li song yue wang iclr 2025 spotlight abstract paper website code review omnire is a holistic framework for dynamic scene reconstruction that provides comprehensive coverage including static backgrounds driving vehicles and non rigidly moving dynamic actors your browser does not support the video tag 360 degree panorama generation from few unregistered nfov images jionghao wang ziyu chen jun ling rong xie li song acm multimedia 2023 abstract paper code we proposed a diffusion based pipeline that generates complete 360 panoramas using one or more unregistered nfov images captured from arbitrary angles this pipeline not only delivers superior quality panoramas but also offers a broader range of outcomes due to its text conditioned generation capability l tracing fast light visibility estimation on neural surfaces by sphere tracing ziyu chen chenjing ding jianfei guo dongliang wang yikang li xuan xiao wei wu li song eccv 2022 abstract paper code our l tracing based reflectance factorization framework produces photo realistic novel view images with nearly 10x speedup compared with the same framework applying volumetric integration for light visibility estimation open source your browser does not support the video tag a 3dgs codebase for dynamic urban scene reconstruction and simulation featuring different gaussian representations for rigid actors vehicles and non rigid actors pedestrians cyclists etc supported datasets include waymo pandaset argoverse2 kitti nuscenes nuplan education stanford university ph d in computer science sep 2025 present stanford ca shanghai jiao tong university m s in electrical engineering sep 2022 mar 2025 b s in electrical engineering sep 2018 jun 2022 shanghai china selected awards qualcomm innovation fellowship 2026 stanford graduate fellowship stanford 2025 national scholarship shanghai jiao tong university 2023 zhiyuan honor fellowship shanghai jiao tong university 2018 2022 ziyu chen