Publications

Filter by type:

WonderJourney: Going from Anywhere to Everywhere

me, haoyi_duan, junhwa_hur, kyle_sargent, michael_rubinstein, bill_freeman, forrester_cole, deqing_sun, noah_snavely, jiajun_wu, charles_herrmann

ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Real Image

kyle_sargent, zizhang_li, tanmay_shah, charles_herrmann, me, yunzhi_zhang, eric_chan, dmitry_lagun, li_feifei, deqing_sun, jiajun_wu

BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation

yunhao_ge, yihe_tang, jiashu_xu, cem_gokmen, chengshu_li, wensi_ai, benjamin_martinez, arman_aydin, mona_anvari, ayush_chakravarthy, me, josiah_wong, sanjana_srivastava, sharon_lee, shengxin_zha, laurent_itti, yunzhu_li, roberto_martinmartin, miao_liu, pingchuan_zhang, ruohan_zhang, li_feifei, jiajun_wu

Neural Polynomial Gabor Fields for Macro Motion Analysis

chen_geng, me, sida_peng, xiaowei_zhou, jiajun_wu

Unsupervised 3D Scene Representation Learning via Movable Object Inference

honglin_chen, wanhee_lee, me, rahul_venkatesh, josh_tenenbaum, daniel_bear, jiajun_wu, daniel_yamins

Fluid Simulation on Neural Flow Maps

yitong_deng, me, diyang_zhang, jiajun_wu, bo_zhu

Inferring Hybrid Neural Fluid Fields from Videos

me, yang_zheng, yuan_gao, yitong_deng, bo_zhu, jiajun_wu

3D Copy-Paste: Physically-Plausible Object Insertion for Monocular 3D Detection

yunhao_ge, me, cheng_zhao, yuliang_guo, xinyu_huang, liu_ren, laurent_itti, jiajun_wu

Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark

zhengfei_kuang, yunzhi_zhang, me, samir_agarwala, shangzhe_wu, jiajun_wu

Are These the Same Apple? Comparing Images Based on Object Intrinsics

klemen_kotar, stephen_tian, me, dan_yamins, jiajun_wu

Tree-Structured Shading Decomposition

chen_geng, me, sharon_zhang, maneesh_agrawala, jiajun_wu

Accidental Light Probes

me, samir_agarwala, charles_herrmann, rick_szeliski, noah_snavely, jiajun_wu, deqing_sun

Multi-Object Manipulation via Object-Centric Neural Scattering Functions

stephen_tian, yancheng_cai, me, sergey_zakharov, katherine_liu, adrien_gaidon, yunzhu_li, jiajun_wu

Learning Vortex Dynamics for Fluid Inference and Prediction

yitong_deng, me, jiajun_wu, bo_zhu

Differentiable Physics Simulation of Dynamics-Augmented Neural Objects

simon_lc, me, michelle_guo, taylor_howell, ruohan_gao, jiajun_wu, zachary_manchester, mac_schwager

Learning Object-Centric Neural Scattering Functions for Free-Viewpoint Relighting and Scene Composition

me, michelle_guo, alireza_fathi, yenyu_chang, eric_chan, ruohan_gao, tom_funkhouser, jiajun_wu

Unsupervised Discovery and Composition of Object Light Fields

cameron_smith, me, sergey_zakharov, fredo_durand, josh_tenenbaum, jiajun_wu, vincent_sitzmann

Rotationally Equivariant 3D Object Detection

me, jiajun_wu, li_yi

Unsupervised Discovery of Object Radiance Fields

me, leonidas_guibas, jiajun_wu

Neural Radiance Flow for 4D View Synthesis and Video Processing

yilun_du, yinan_zhang, me, josh_tenenbaum, jiajun_wu

OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets

zhengqin_li, tingwei_yu, shen_sang, sarah_wang, sai_bi, zexiang_xu, me, kalyan_sunkavalli, milos_hasan, ravi_ramamoorthi, manmohan_chandraker

Letter-level Online Writer Identification

zelin_chen, me, ancong_wu, weishi_zheng

Weakly Supervised Discriminative Feature Learning with State Information for Person Identification

me, weishi_zheng

Unsupervised Person Re-identification by Soft Multilabel Learning

me, weishi_zheng, ancong_wu, xiaowei_guo, shaogang_gong, jianhuang_lai

Patch-based Discriminative Feature Learning for Unsupervised Person Re-identification

qize_yang, me, ancong_wu, weishi_zheng

MIXGAN: Learning Concepts from Different Domains for Mixture Generation

guangyuan_hao, me, weishi_zheng

Adversarial Attribute-Image Person Re-identification

zhou_yin, weishi_zheng, ancong_wu, me, hai_wan, xiaowei_guo, feiyue_huang, jianhuang_lai

Unsupervised Person Re-identification by Deep Asymmetric Metric Embedding

me, ancong_wu, weishi_zheng

Cross-view Asymmetric Metric Learning for Unsupervised Person Re-identification

me, ancong_wu, weishi_zheng

RGB-infrared Cross-modality Person Re-identification

ancong_wu, weishi_zheng, me, shaogang_gong, jianhuang_lai