Zexiang Xu (徐泽祥)

Research Scientist at Adobe Research

zexu AT adobe.com / zexiangxu AT gmail.com



I am a research scientist at Adobe Research. I obtained my Ph.D. at University of California, San Diego, working with Prof. Ravi Ramamoorthi. Before that, I received my Bachelor degree in 2012 and my Master degree in 2015 both from Beihang University.

My research interests lie at the intersection of computer graphics and computer vision; my focus is to make scene acquisition and rendering be efficient, practical and realistic, especially by introducing neural modules and representations in classic physically based pipelines. My research has been recognized by Adobe Research Fellowship (2019) and UCSD Chancellor’s Dissertation Medal (2021). My work has broadly covered 3D reconstruction, view synthesis, neural representations, relighting, rendering, appearance modeling, appearance acquisition, and light fields.


News

  • NEW! [Mar 1, 2022] Four papers (two oral presentations) get accepted to CVPR 2022!
  • [July 30, 2021] One paper gets accepted to SIGGRAPH Asia 2021.
  • [Jun 18, 2021] One paper gets accepted to TOG 2022.
  • [July 22, 2021] MVSNeRF gets accepted to ICCV 2021.
  • [Jun 8, 2021] One paper gets accepted to EGSR 2021.
  • [May 21, 2021] I am a recipient of the 2021 Chancellor's Dissertation Medal of UCSD!
  • [Mar 26, 2021] Two papers get accepted to SIGGRAPH 2021.
  • [Mar 1, 2021] Two papers (both oral) get accepted to CVPR 2021.
  • [July 31, 2020] One paper gets accepted to SIGGRAPH Asia 2020.
  • [July 6, 2020] I joined Adobe Research as a research scientist.
  • [July 2, 2020] Two papers (one spotlight) get accepted to ECCV 2020.
  • [May 27, 2020] One paper gets accepted to EGSR 2020 (CGF track).
  • [Feb 2, 2020] Two papers (one oral) get accepted to CVPR 2020.
  • [Jul 29, 2019] One paper gets accepted to SIGGRAPH Asia 2019.
  • [Mar 25, 2019] Two papers get accepted to SIGGRAPH 2019.
  • [Aug 11, 2018] One paper gets accepted to SIGGRAPH Asia 2018.
  • [Mar 26, 2018] One paper gets accepted to SIGGRAPH 2018.
  • [Feb 27, 2017] One paper gets accepted to CVPR 2017.
  • [Jul 23, 2016] One paper gets accepted to SIGGRAPH Asia 2016.
  • [Sep 27, 2015] I started as a Ph.D. student at UC San Diego.
  • [Aug 14, 2014] One paper gets accepted to SIGGRAPH Asia 2014.

Publications


* denotes equal contribution.
TensoRF: Tensorial Radiance fields
Anpei Chen*, Zexiang Xu*, Andreas Geiger, Jingyi Yu , Hao Su
arXiv 2022
NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction
Xiaoshuai Zhang, Sai Bi, Kalyan Sunkavalli, Hao Su, Zexiang Xu
CVPR 2022 (Oral)
Point-NeRF: Point-based Neural Radiance Fields
Qiangeng Xu, Zexiang Xu, Julien Philip, Sai Bi, Zhixin Shu Kalyan Sunkavalli , Ulrich Neumann
CVPR 2022 (Oral)
MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo
Anpei Chen*, Zexiang Xu*, Fuqiang Zhao, Xiaoshuai Zhang, Fanbo Xiang, Jingyi Yu, Hao Su
ICCV 2021
NeLF: Neural Light-transport Field for Portrait View Synthesis and Relighting
EGSR 2021
Path Graphs: Iterative Path Space Filtering
Xi Deng, Miloš Hašan, Nathan Carr, Zexiang Xu, Steve Marschner
SIGGRAPH Asia 2021 (TOG)
NeuMIP: Multi-Resolution Neural Materials
Alexandr Kuznetsov, Krishna Mullia, Zexiang Xu, Miloš Hašan, Ravi Ramamoorthi
SIGGRAPH 2021 (TOG)
Hierarchical Neural Reconstruction for Path Guiding Using Hybrid Path and Photon Samples
SIGGRAPH 2021 (TOG)
Photon-Driven Neural Path Guiding
TOG 2022
NeuTex: Neural Texture Mapping for Volumetric Neural Rendering
CVPR 2021 (Oral)
OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets
Zhengqin Li, Ting-Wei Yu, Shen Sang, Sarah Wang, Meng Song, Yuhan Liu, Yu-Ying Yeh, Rui Zhu, Nitesh Gundavarapu, Jia Shi, Sai Bi, Zexiang Xu, Hong-Xing Yu, Kalyan Sunkavalli, Miloš Hašan, Ravi Ramamoorthi, Manmohan Chandraker
CVPR 2021 (Oral)
Light stage super-resolution: continuous high-frequency relighting
Tiancheng Sun, Zexiang Xu, Xiuming Zhang, Sean Fanello, Christoph Rhemann, Paul Debevec, Yun-Ta Tsai, Jonathan T. Barron, Ravi Ramamoorthi
SIGGRAPH Asia 2020 (TOG)
Neural Reflectance Fields for Appearance Acquisition
arXiv 2020
Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Images
ECCV 2020 (Spotlight)
Deep Multi Depth Panoramas for View Synthesis
ECCV 2020
Deep Kernel Density Estimation for Photon Mapping
EGSR 2020 (CGF journal track)
Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness
CVPR 2020 (Oral)
Deep 3D Capture: Geometry and Reflectance from Sparse Multi-View Images
CVPR 2020
Learning Generative Models for Rendering Specular Microgeometry
SIGGRAPH Asia 2019 (TOG)
Deep View Synthesis from Sparse Photometric Images
SIGGRAPH 2019 (TOG)
Single Image Portrait Relighting
Tiancheng Sun, Jonathan T. Barron, Yun-Ta Tsai, Zexiang Xu, Xueming Yu, Graham Fyffe, Christoph Rhemann, Jay Busch, Paul Debevec, Ravi Ramamoorthi
SIGGRAPH 2019 (TOG)
Learning to Reconstruct Shape and Spatially-Varying Reflectance from a Single Image
SIGGRAPH Asia 2018 (TOG)
Deep Image-based Relighting from Optimal Sparse Samples
SIGGRAPH 2018 (TOG)
Robust Energy Minimization for BRDF-Invariant Shape from Light Fields
CVPR 2017
Minimal BRDF Sampling for Two-Shot Near-Field Reflectance Acquisition
Zexiang Xu, Jannik Boll Nielsen, Jiyang Yu, Henrik Wann Jensen, Ravi Ramamoorthi
SIGGRAPH Asia 2016
Dynamic Hair Capture using Spacetime Optimization
Zexiang Xu, Hsiang-Tao Wu, Lvdi Wang, Changxi Zheng, Xin Tong, Yue Qi
SIGGRAPH Asia 2014

Service

  • Conference reviewer: CVPR, ECCV, ICCV, SIGGRAPH, SIGGRAPH Asia, EG, PG,...
  • Journal reviewer: TOG, TIP, TPAMI, CGF...