Xiangyu Xu

I am a full Professor at Xi'an Jiaotong University. I work on computer vision and machine learning. I got my Bachelor degrees from Tsinghua University and Peking University. I did my PhD at Tsinghua University and my Postdoc at Carnegie Mellon University.

I am looking for PhD, Master, and Undergraduate students and Postdocs to join my lab. Please drop me an email if you are interested.

Email  /  Bio  /  Google Scholar

profile photo
News
  • 📢 Call for Papers! 📢 TPAMI Special Issue on "Generative AI in 3D Vision" (Deadline: Aug. 15 Oct. 15, 2024)
  •  
  • Invited as an Area Chair for ICLR 2025
  •  
  • InfNeRF accepted to SIGGRAPH Asia 2024
  •  
  • Invited as an Area Chair for NeurIPS 2024
Selected Publications

I'm interested in computer vision, machine learning, and image processing.

GoodDrag: Towards Good Practices for Drag Editing with Diffusion Models
Zewei Zhang, Huan Liu, Jun Chen, Xiangyu Xu
arXiv, 2024
Paper | Project

A new framework for drag editing with diffusion models.

InfNeRF: Towards Infinite Scale NeRF Rendering with O(log n) Space Complexity
Jiabin Liang, Lanqing Zhang, Zhuoran Zhao, Xiangyu Xu
SIGGRAPH Asia, 2024
Paper | Project

We combine Level of Detail (LoD) with NeRF.

Motion-Adaptive Separable Collaborative Filters for Blind Motion Deblurring
Chengxu Liu, Xuan Wang, Xiangyu Xu, Ruhao Tian, Shuai Li, Xueming Qian, Ming-Hsuan Yang
Computer Vision and Pattern Recognition Conference (CVPR), 2024
Paper

Learnable filters for image deblurring.

SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimation
Xiangyu Xu, Lijuan Liu, Shuicheng Yan
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024
Paper | Project

We propose a very simple Transformer for 3D human shape and pose estimation from a single image, which achieves SOTA accuracy with high efficiency in parameter and computation.

Instant3D: Instant Text-to-3D Generation
Ming Li, Pan Zhou, Jia-Wei Liu, Jussi Keppo, Min Lin, Shuicheng Yan, Xiangyu Xu
International Journal of Computer Vision (IJCV), 2024
Paper | Project

Text-to-3D generation without per-prompt training, taking only under a second.

Progressive Text-to-3D Generation for Automatic 3D Prototyping
Han Yi, Zhedong Zheng, Xiangyu Xu, Tat-seng Chua
arXiv, 2023
Paper | Project

A progressive strategy that learns text-to-3D in a coarse-to-fine manner

NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF
Stefan Lionar, Xiangyu Xu, Min Lin, Gim Hee Lee
Conference on Neural Information Processing Systems (NeurIPS), 2023
Paper | Project

We achieve new SOTA for single-view 3D reconstruction on CO3D.

Towards Garment Sewing Pattern Reconstruction from a Single Image
Lijuan Liu*, Xiangyu Xu*, Zhijie Lin*, Jiabin Liang*, Shuicheng Yan
ACM Transactions on Graphics (SIGGRAPH Asia), 2023
Paper | Code | New Scientist

We present the first solution for sewing pattern reconstruction from a single image.

STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition
Ming Li, Xiangyu Xu, Hehe Fan, Pan Zhou, Jun Liu, Jia-Wei Liu, Jiahe Li, Jussi Keppo, Mike Zheng Shou, Shuicheng Yan
International Conference on Computer Vision (ICCV), 2023
Paper | Code

We explore privacy-preserving action recognition from a spatio-temporal perspective.

Cylin-Painting: Seamless 360° Panoramic Image Outpainting and Beyond
Kang Liao, Xiangyu Xu, Chunyu Lin, Wenqi Ren, Yunchao Wei, Yao Zhao
IEEE Transactions on Image Processing (TIP), 2023
Paper | Code

We propose a cylinder-style convolution for completing panoramic views.

GLEAN: Generative Latent Bank for Image Super-Resolution and Beyond
Kelvin C.K. Chan, Xiangyu Xu, Xintao Wang, Jinwei Gu, and Chen Change Loy
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022
Paper | Code

We develop a lighter version of GLEAN.

Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering
Mingfei Chen, Jianfeng Zhang, Xiangyu Xu, Lijuan Liu, Yujun Cai, Jiashi Feng, Shuicheng Yan
European Conference on Computer Vision (ECCV), 2022
Paper | Code

We present an SMPL-based NeRF for multi-view human synthesis, which is efficient and generalizable to unseen subjects and sparse views.

Video Frame Interpolation Transformer
Zhihao Shi*, Xiangyu Xu*, Xiaohong Liu, Jun Chen, Ming-Hsuan Yang
Computer Vision and Pattern Recognition Conference (CVPR), 2022
Paper | Code

We present the first Transformer architecture for video frame interpolation.

Investigating Tradeoffs in Real-World Video Super-Resolution
Kelvin C.K. Chan, Shangchen Zhou, Xiangyu Xu, and Chen Change Loy
Computer Vision and Pattern Recognition Conference (CVPR), 2022
Paper | Code

Several useful techniques for real-world video super-resolution.

BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment
Kelvin C.K. Chan, Shangchen Zhou, Xiangyu Xu, and Chen Change Loy
Computer Vision and Pattern Recognition Conference (CVPR), 2022
Paper | Project

Winner algorithm for video enhancement challenges in NTIRE 2021.

3D Human Texture Estimation from a Single Image with Transformers
Xiangyu Xu, Chen Change Loy
International Conference on Computer Vision (ICCV), 2021   (Oral Presentation)
Paper | Code | Project

We present a Transformer for 3D human texture estimation from a single image.

3D Human Pose, Shape and Texture from Low-Resolution Images and Videos
Xiangyu Xu, Hao Chen, Francesc Moreno-Noguer, Laszlo A. Jeni, and Fernando De la Torre
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021
Paper | Code

We extend RSC-Net to videos and propose a human texture estimation model.

GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution
Kelvin C.K. Chan, Xintao Wang, Xiangyu Xu, Jinwei Gu, and Chen Change Loy
Computer Vision and Pattern Recognition Conference (CVPR), 2021   (Oral Presentation)
Paper | Project

We use StyleGAN for image super-resolution.

Super-Resolution Capacitive Touchscreens
Sven Mayer, Xiangyu Xu, and Chris Harrison
ACM Conference on Human Factors in Computing Systems (CHI), 2021
Paper | YouTube

For the first time, super-resolution is applied to human-computer interaction.

Exploiting Raw Images for Real-Scene Super-Resolution
Xiangyu Xu, Yongrui Ma, Wenxiu Sun, and Ming-Hsuan Yang
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020
Paper | Project | Code

We improve the RawSR architecture and extend it to image dehazing and depth upsampling.

3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning
Xiangyu Xu, Hao Chen, Francesc Moreno-Noguer, Laszlo A. Jeni, and Fernando De la Torre
European Conference on Computer Vision (ECCV), 2020
Paper | Project | Code

We propose a new algorithm for 3D human shape and pose estimation that is robust to low-resolution input.

Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoising
Xiangyu Xu, Muchen Li, Wenxiu Sun, and Ming-Hsuan Yang
IEEE Transactions on Image Processing (TIP), 2020
Paper | Code

We propose spatio-temporal deformable convolution kernels for image and video denoising.

Learning Factorized Weight Matrix for Joint Filtering
Xiangyu Xu, Yongrui Ma, Wenxiu Sun
International Conference on Machine Learning (ICML), 2020   (Long Talk)
Paper | Project

We propose deep Robust PCA for joint image filtering.

Quadratic Video Interpolation
Xiangyu Xu*, Siyao Li*, Wenxiu Sun, Qian Yin, and Ming-Hsuan Yang
Conference on Neural Information Processing Systems (NeurIPS), 2019   (Spotlight)
Paper | Code

We present the first nonlinear motion model for image interpolation. The method won the Champion of AIM 2019 video interpolation challenge.

Towards Real Scene Super-Resolution with Raw Images
Xiangyu Xu, Yongrui Ma, Wenxiu Sun
Computer Vision and Pattern Recognition Conference (CVPR), 2019
Paper | Code

We present the first neural network for raw image based super-resolution. It works very well on real-world input.

Low-Light Image Enhancement via a Deep Hybrid Network
Wenqi Ren, Sifei Liu, Lin Ma, Qianqian Xu, Xiangyu Xu, Xiaochun Cao, Junping Du, Ming-Hsuan Yang
IEEE Transactions on Image Processing (TIP), 2019
Paper

We present a hybrid structure of CNN and RNN for low-light image enhancement.

Rendering Portraitures from Monocular Camera and Beyond
Xiangyu Xu, Deqing Sun, Sifei Liu, Wenqi Ren, Yu-Jin Zhang, Ming-Hsuan Yang, Jian Sun
European Conference on Computer Vision (ECCV), 2018
Paper

We present a CRF-based pipeline and a deep neural filter for rendering shallow depth-of-field effect with monocular camera.


Monocular Depth Estimation with Affinity, Vertical Pooling and Label Enhancement
Yukang Gan*, Xiangyu Xu*, Wenxiu Sun, Liang Lin
European Conference on Computer Vision (ECCV), 2018
Paper

We propose to incorporate relative features, i.e., affinity, for monocular depth estimation.

Motion Blur Kernel Estimation via Deep Learning
Xiangyu Xu, Jinshan Pan, Yu-Jin Zhang, Ming-Hsuan Yang
IEEE Transactions on Image Processing (TIP), 2018
Paper | Project

We present a deep neural network to extract salient edges for blind image deblurring.

Deep Video Dehazing with Semantic Segmentation
Wenqi Ren*, Jingang Zhang*, Xiangyu Xu*, Lin Ma, Xiaochun Cao, Gaofeng Meng, Wei Liu
IEEE Transactions on Image Processing (TIP), 2018
Paper

We exploit a neural network to perform haze removal for videos.

Learning to Super-Resolve Blurry Face and Text Images
Xiangyu Xu, Deqing Sun, Jinshan Pan, Yu-Jin Zhang, Hanspeter Pfister, Ming-Hsuan Yang
International Conference on Computer Vision (ICCV), 2017
Paper | Project

We present the first deep neural network for blind image super-resolution.

Professional Services

Area Chair: CVPR 2023, BMVC 2023, CVPR 2024, ICLR 2024, ECCV 2024, BMVC 2024, NeurIPS 2024
Session Chair: SIGGRAPH Asia 2023
Senior Program Committee: IJCAI 2021, AAAI 2023, AAAI 2024

Students/Interns

Stefan Lionar, PhD (Sea AI Lab and NUS, 2023-2024)
Ming Li, Intern (Sea AI Lab, 2023)
Hao Chen, Master (CMU, 2019-2020), Now: PhD at CMU
Muchen Li, Intern (SenseTime, 2018-2019), Now: PhD at UBC
Yongrui Ma, Intern (SenseTime, 2018-2019), Now: PhD at CUHK


Website template from here