Zexiang Xu (徐泽祥)

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

Publications

TensoRF: Tensorial Radiance fields

Anpei Chen*, Zexiang Xu*, Andreas Geiger, Jingyi Yu , Hao Su

arXiv 2022

[Project] [Paper]

NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction

Xiaoshuai Zhang, Sai Bi, Kalyan Sunkavalli, Hao Su, Zexiang Xu

CVPR 2022 (Oral)

[Project] [Paper]

Point-NeRF: Point-based Neural Radiance Fields

Qiangeng Xu, Zexiang Xu, Julien Philip, Sai Bi, Zhixin Shu Kalyan Sunkavalli , Ulrich Neumann

CVPR 2022 (Oral)

[Project] [Paper]

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

[arXiv] [Project]

NeLF: Neural Light-transport Field for Portrait View Synthesis and Relighting

Tiancheng Sun*, Kai-En Lin*,Sai Bi, Zexiang Xu, Ravi Ramamoorthi

EGSR 2021

[Project]

Path Graphs: Iterative Path Space Filtering

Xi Deng, Miloš Hašan, Nathan Carr, Zexiang Xu, Steve Marschner

SIGGRAPH Asia 2021 (TOG)

[Paper]

NeuMIP: Multi-Resolution Neural Materials

Alexandr Kuznetsov, Krishna Mullia, Zexiang Xu, Miloš Hašan, Ravi Ramamoorthi

SIGGRAPH 2021 (TOG)

[Project]

Hierarchical Neural Reconstruction for Path Guiding Using Hybrid Path and Photon Samples

Shilin Zhu, Zexiang Xu,Tiancheng Sun, Alexandr Kuznetsov, Mark Meyer, Henrik Wann Jensen, Hao Su, Ravi Ramamoorthi

SIGGRAPH 2021 (TOG)

[Paper]

Photon-Driven Neural Path Guiding

Shilin Zhu, Zexiang Xu,Tiancheng Sun, Alexandr Kuznetsov, Mark Meyer, Henrik Wann Jensen, Hao Su, Ravi Ramamoorthi

TOG 2022

[arXiv]

NeuTex: Neural Texture Mapping for Volumetric Neural Rendering

Fanbo Xiang, Zexiang Xu,Miloš Hašan, Yannick Hold-Geoffroy, Kalyan Sunkavalli, Hao Su

CVPR 2021 (Oral)

[arXiv] [Project]

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)

[Project]

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)

[Project]

Neural Reflectance Fields for Appearance Acquisition

Sai Bi*, Zexiang Xu*, Pratul P. Srinivasan, Ben Mildenhall, Kalyan Sunkavalli, Miloš Hašan, Yannick Hold-Geoffroy, David Kriegman, Ravi Ramamoorthi

arXiv 2020

[arXiv]

Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Images

Sai Bi, Zexiang Xu, Kalyan Sunkavalli, Miloš Hašan, Yannick Hold-Geoffroy, David Kriegman, Ravi Ramamoorthi

ECCV 2020 (Spotlight)

[arXiv] [video]

Deep Multi Depth Panoramas for View Synthesis

Kai-En Lin, Zexiang Xu, Ben Mildenhall, Pratul P. Srinivasan, Yannick Hold-Geoffroy, Stephen DiVerdi, Qi Sun, Kalyan Sunkavalli, Ravi Ramamoorthi

ECCV 2020

[arXiv] [video]

Deep Kernel Density Estimation for Photon Mapping

Shilin Zhu*, Zexiang Xu*, Henrik Wann Jensen, Hao Su, Ravi Ramamoorthi

EGSR 2020 (CGF journal track)

[paper]

Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness

Shuo Cheng*, Zexiang Xu*, Shilin Zhu, Zhuwen Li, Li Erran Li, Ravi Ramamoorthi, Hao Su

CVPR 2020 (Oral)

[arXiv]

Deep 3D Capture: Geometry and Reflectance from Sparse Multi-View Images

Sai Bi, Zexiang Xu, Kalyan Sunkavalli, David Kriegman, Ravi Ramamoorthi

CVPR 2020

[arXiv] [video]

Learning Generative Models for Rendering Specular Microgeometry

Alexandr Kuznetsov, Miloš Hašan,Zexiang Xu, Lingqi Yan, Bruce Walter, Nima Khademi Kalantari, Steve Marschner, Ravi Ramamoorthi

SIGGRAPH Asia 2019 (TOG)

[arXiv] [video]

Deep View Synthesis from Sparse Photometric Images

Zexiang Xu, Sai Bi, Kalyan Sunkavalli, Sunil Hadap, Hao Su, Ravi Ramamoorthi

SIGGRAPH 2019 (TOG)

[paper] [video]

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)

[paper] [video]

Learning to Reconstruct Shape and Spatially-Varying Reflectance from a Single Image

Zhengqin Li, Zexiang Xu, Ravi Ramamoorthi, Kalyan Sunkavalli, Manmohan Chandraker

SIGGRAPH Asia 2018 (TOG)

[paper] [video]

Deep Image-based Relighting from Optimal Sparse Samples

Zexiang Xu, Kalyan Sunkavalli, Sunil Hadap, Ravi Ramamoorthi

SIGGRAPH 2018 (TOG)

[paper] [project]

Robust Energy Minimization for BRDF-Invariant Shape from Light Fields

Zhengqin Li, Zexiang Xu, Ravi Ramamoorthi, Manmohan Chandraker

CVPR 2017

[paper]

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

[paper]

Dynamic Hair Capture using Spacetime Optimization

Zexiang Xu, Hsiang-Tao Wu, Lvdi Wang, Changxi Zheng, Xin Tong, Yue Qi

SIGGRAPH Asia 2014

[paper]