Haofei Xu

I am a PhD student at ETH Zurich and University of Tübingen under ELLIS, supervised by Marc Pollefeys and Andreas Geiger. I have broad interests in computer vision and deep learning, particularly in motion, dense correspondences and 3D scene representation learning.

Before starting my PhD, I spent two wonderful years working remotely with Jianfei Cai and Hamid Rezatofighi at Monash University, Australia. I obtained a master degree at University of Science and Technology of China (USTC) in 2021, where I was supervised by Juyong Zhang. During my master study, I interned at Nanyang Technological University (NTU), Singapore and Microsoft Research Asia (MSRA). I received the Outstanding Reviewer award in CVPR 2022.

Email  /  Scholar  /  Twitter  /  Github

photo
Research
MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images
Yuedong Chen, Haofei Xu, Chuanxia Zheng, Bohan Zhuang, Marc Pollefeys, Andreas Geiger, Tat-Jen Cham, Jianfei Cai
arXiv, 2024
project page / code

A cost volume representation for efficiently predicting 3D Gaussians from sparse multi-view images in a single forward pass.

MuRF: Multi-Baseline Radiance Fields
Haofei Xu, Anpei Chen, Yuedong Chen, Christos Sakaridis, Yulun Zhang, Marc Pollefeys, Andreas Geiger, Fisher Yu
Computer Vision and Pattern Recognition (CVPR), 2024
project page / code

A general feed-forward approach to solving sparse view synthesis under multiple different baseline settings.

GC-MVSNet: Geometrically Consistent Cost Aggregation for Multi-View Stereo
Jiang Wu, Rui Li, Haofei Xu, Wenxun Zhao, Yu Zhu, Jinqiu Sun, Yanning Zhang
Computer Vision and Pattern Recognition (CVPR), 2024

Geometrically consistent matching cost aggregation with monocular normals.
1st place on Tanks and Temples (Advanced) leaderboard.

Explicit Correspondence Matching for Generalizable Neural Radiance Fields
Yuedong Chen, Haofei Xu, Qianyi Wu, Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai
arXiv, 2023
project page / code

Employing explicit correspondence matching as a geometry prior enables NeRF to generalize across scenes.

Unifying Flow, Stereo and Depth Estimation
Haofei Xu, Jing Zhang, Jianfei Cai, Hamid Rezatofighi, Fisher Yu, Dacheng Tao, Andreas Geiger
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023
project page / slides / video(cn) / code / colab / demo

A unified dense correspondence matching formulation enables three motion and 3D perception tasks to be solved with a unified model.

GMFlow: Learning Optical Flow via Global Matching
Haofei Xu, Jing Zhang, Jianfei Cai, Hamid Rezatofighi, Dacheng Tao
Computer Vision and Pattern Recognition (CVPR), 2022 (Oral)
slides / video(cn) / poster / code

Learning strong features with a Transformer enables optical flow to be obtained by directly comparing feature similarities.

High-Resolution Optical Flow from 1D Attention and Correlation
Haofei Xu, Jiaolong Yang, Jianfei Cai, Juyong Zhang, Xin Tong
International Conference on Computer Vision (ICCV), 2021 (Oral)
code

Factorizing 2D optical flow with 1D attention and 1D correlation enables 4K resolution optical flow estimation on ordinary GPUs.

Recurrent Multi-view Alignment Network for Unsupervised Surface Registration
Wanquan Feng, Juyong Zhang, Hongrui Cai, Haofei Xu, Junhui Hou, Hujun Bao
Computer Vision and Pattern Recognition (CVPR), 2021
project page / code

A new non-rigid representation and a differentiable loss function enable end-to-end learning of non-rigid registration.

AANet: Adaptive Aggregation Network for Efficient Stereo Matching
Haofei Xu, Juyong Zhang
Computer Vision and Pattern Recognition (CVPR), 2020
code

A sparse points-based cost aggregation method leads to an efficient and accurate stereo matching architecture without any 3D convolutions.

Region Deformer Networks for Unsupervised Depth Estimation from Unconstrained Monocular Videos
Haofei Xu, Jianmin Zheng, Jianfei Cai, Juyong Zhang
International Joint Conference on Artificial Intelligence (IJCAI), 2019
code

A bicubic motion representation enables unsupervised depth estimation from monocular videos in dynamic scenes.

Invited Talks
  • Unifying Flow, Stereo and Depth Estimation [slides] [video(cn)], 机器之心, 2022.12.28
  • GMFlow: Learning Optical Flow via Global Matching [slides], Monash University, 2022.04.13
Academic Services
  • Conference Reviewer: ICCV 2021, CVPR 2022, ECCV 2022, CVPR 2023, NeurIPS 2023, CVPR 2024, ECCV 2024
  • Journal Reviewer: TIP, IJCV, TPAMI
Awards

awesome website template