Nan Xue

Nan Xue

I'm a staff research scientist at Ant Research. My current research mainly lies on developing general learning algorithms for the computation of structured visual geometry in computer vision. Here is a research statement about my work. My profile photo is computed by my HAWPv3.


Google Scholar  /  Github  /  Email 		profile photo

Recent News

2024. 12: The paper, PlanarSplatting for indoor scene reconstruction, is available on arXiv.
2024. 08: Served as an Area Chair for WACV 2025.
2024. 04: SAGE has been selected as an oral paper, and SpatialTracker has been selected as a highlight at CVPR 2024.
2024. 03: Four papers (NEAT, SpatialTracker, SAGE, MvaCon) are accepted to CVPR 2024.
2023. 09: Two papers (NOPE-SAC and HAWP) are accepted to IEEE TPAMI. Congrats to Bin Tan for his first PAMI paper!

Selected Publications

PlanarSplatting: Accurate Planar Surface Reconstruction in 3 Minutes
Bin Tan, Rui Yu, Yujun Shen, Nan Xue
preprint, 2024
arXiv / Project
Rectified Diffusion Guidance for Conditional Generation
Mengfei Xia, Nan Xue, Yujun Shen, Ran Yi, Tieliang Gong, Yong-Jin Liu
preprint, 2024
arXiv
NEAT: Distilling 3D Wireframes from Neural Attraction Fields
Nan Xue, Bin Tan, Yuxi Xiao, Liang Dong, Gui-Song Xia, Tianfu Wu, Yujun Shen
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
arXiv / PDF / YouTube / Code
A neural 3D wireframe reconstruction approach without explicit line segment matching.
SpatialTracker: Tracking Any 2D Pixels in 3D Space
Yuxi Xiao*, Qianqian Wang*, Shangzhan Zhang, Nan Xue, Sida Peng, Yujun Shen†, Xiaowei Zhou†
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
arXiv / Project / Code
Highlight Presentation
Stratified Avatar Generation from Sparse Observations
Han Feng*, Wenchao Ma*, Quankai Gao, Xianwei Zheng, Nan Xue†, Huijuan Xu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
arXiv / Project / YouTube / Code
Oral Presentation
Multi-View Attentive Contextualization for Multi-View 3D Object Detection
Xianpeng Liu, Ce Zheng, Ming Qian, Nan Xue, Chen Chen, Zhebin Zhang, Chen Li, Tianfu Wu†
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
arXiv / Project
A simple yet effective method for improving 2D-to-3D feature lifting in query-based multi-view 3D (MV3D) object detection.
NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction
Bin Tan, Nan Xue†, Tianfu Wu, Gui-Song Xia
IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2023
arXiv / IEEE Xplore / Code
Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning
Nan Xue, Tianfu Wu, Song Bai, Fudong Wang, Gui-Song Xia, Liangpei Zhang, Philip H.S. Torr
IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2023
arXiv / IEEE Xplore / Code
Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs
Min Qian, Jincheng Xiong, Gui-Song Xia, Nan Xue†
IEEE/CVF International Conference on Computer Vision (ICCV), 2023
arXiv / Code
Level-S2fM: Structure from Motion on Neural Level Set of Implicit Surfaces
Yuxi Xiao, Nan Xue†, Tianfu Wu, Gui-Song Xia
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
arXiv / Project / Code
HiSup: Accurate Polygonal Mapping of Buildings in Satellite Imagery with Hierarchical Supervision
Bowen Xu*, Jiakun Xu*, Nan Xue†, Gui-Song Xia†
ISPRS Journal of Photogrammetry and Remote Sensing, 2023
arXiv / Code
HoW-3D: Holistic 3D Wireframe Perception from a Single Image
Wenchao Ma, Bin Tan, Nan Xue†, Tianfu Wu, Xianwei Zheng, Gui-Song Xia
IEEE International Conference on 3D Vision (3DV), 2022
arXiv / Code / Dataset / YouTube
Revisiting Document Image Dewarping by Grid Regularization
Xiangwei Jiang, Rujiao Long, Nan Xue, Zhibo Yang, Cong Yao, Gui-Song Xia
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
arXiv / Code
Decoupling Zero-Shot Semantic Segmentation
Jian Ding, Nan Xue, Gui-Song Xia, Dengxin Dai
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
arXiv / Code
Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation
Nan Xue, Tianfu Wu†, Gui-Song Xia, Liangpei Zhang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
arXiv / Code
Partial Wasserstein Adversarial Network for Non-rigid Point Set Registration
Ziming Wang, Nan Xue, Ling Lei, Gui-Song Xia
International Conference on Learning Representations (ICLR), 2022
arXiv / Code
Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection
Xianpeng Liu, Nan Xue, Tianfu Wu
AAAI Conference on Artificial Intelligence (AAAI), 2022
arXiv / Code
Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges
Jian Ding, Nan Xue, Gui-Song Xia, Xiang Bai, Wen Yang, Michael Ying Yang, Serge Belongie, Jiebo Luo, Mihai Datcu, Marcello Pelillo, Liangpei Zhang
IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2021
Paper
PlaneTR: Structure-Guided Transformers for 3D Plane Recovery
Bin Tan*, Nan Xue*, Song Bai, Tianfu Wu, Gui-Song Xia
IEEE International Conference on Computer Vision (ICCV), 2021
arXiv / Code
Unmixing Convolutional Features for Crisp Edge Detection
Linxi Huan*, Nan Xue*, Xianwei Zheng†, Wei He, Jianya Gong, Gui-Song Xia
IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2021
arXiv / IEEEXplore / Code
Learning Regional Attraction for Line Segment Detection
Nan Xue, Song Bai, Fudong Wang, Tianfu Wu, Gui-Song Xia, Liangpei Zhang, Philip H.S. Torr
IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2021
arXiv / IEEEXplore / Project
Deep Graph Matching under Quadratic Constraint
Quankai Gao, Fudong Wang, Nan Xue, Jin-Gang Yu, Gui-Song Xia
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
arXiv / Code
A Functional Representation for Graph Matching
Fudong Wang, Nan Xue, Yipeng Zhang, Gui-Song Xia, Marcello Pelillo
IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2020
arXiv / IEEEXplore / Code
Holistically-Attracted Wireframe Parsing
Nan Xue, Tianfu Wu, Song Bai, Fudong Wang, Gui-Song Xia, Liangpei Zhang, Philip H.S. Torr
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
arXiv / Paper / Code
Zero-Assignment Constraint for Graph Matching with Outliers
Fudong Wang, Nan Xue, Jin-Gang Yu, Gui-Song Xia
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
arXiv / Code
Learning Attraction Field Representation for Robust Line Segment Detection
Nan Xue, Song Bai, Fudong Wang, Tianfu Wu, Gui-Song Xia, Liangpei Zhang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
arXiv / Paper / Code
Learning to Calibrate Straight Lines for Fisheye Image Rectification
Zhu-Cun Xue, Nan Xue, Gui-Song Xia, Weiming Shen
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Paper
Learning RoI Transformer for Detecting Oriented Objects in Aerial Images
Jian Ding, Nan Xue, Yang Long, Gui-Song Xia, Qikai Lu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
arXiv / Code
Adaptively Transforming Graph Matching
Fudong Wang, Nan Xue, Yipeng Zhang, Xiang Bai, Gui-Song Xia
European Conference on Computer Vision (ECCV), 2018
arXiv
Anisotropic-Scale Junction Detection and Matching for Indoor Images
Nan Xue, Gui-Song Xia, Xiang Bai, Liangpei Zhang, Weiming Shen
IEEE Trans. on Image Processing (TIP), 2018
arXiv / IEEEXplore / Code