Publications

2025

1. Arxiv 2025

   

   ARSS: Taming Decoder-only Autoregressive Visual Generation for View Synthesis From Single View

   Wenbin Teng, Gonglin Chen, Haiwei Chen, and 1 more author

   arXiv preprint arXiv:2509.23008, 2025

   arXiv PDF Website
2. ICCV 2025

   

   FVGen: Accelerating Novel-View Synthesis with Adversarial Video Diffusion Distillation

   Wenbin Teng, Gonglin Chen, Haiwei Chen, and 1 more author

   In IEEE/CVF Conference on International Conference on Computer Vision (ICCV), 2025

   arXiv PDF Code Website
3. CVPR 2025

   

   RDD: Robust Feature Detector and Descriptor using Deformable Transformer

   Gonglin Chen, Tianwen Fu, Haiwei Chen, and 3 more authors

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

   arXiv Code Website
4. 3DV 2025

   

   Geometry-aware Feature Matching for Large-Scale Structure from Motion

   Gonglin Chen, Jinsen Wu, Haiwei Chen, and 5 more authors

   In International Conference on 3D Vision (3DV), 2025

   arXiv Website
5. WACV 2025

   

   Skyeyes: Ground Roaming using Aerial View Images

   Zhiyuan Gao, Wenbin Teng, Gonglin Chen, and 5 more authors

   In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025

   arXiv Video Website

2023

1. ICLR 2023

   

   Light Sampling Field and BRDF Representation for Physically-based Neural Rendering

   Jing Yang, Hanyuan Xiao, Wenbin Teng, and 2 more authors

   In International Conference on Learning Representations (ICLR), 2023

   arXiv Video Code Website

2021

1. FG2021

   

   Unimodal face classification with multimodal training

   Wenbin Teng, and Chongyang Bai

   In 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021), 2021

   arXiv Bib HTML Code

   @inproceedings{teng2021unimodal,
     title = {Unimodal face classification with multimodal training},
     author = {Teng, Wenbin and Bai, Chongyang},
     booktitle = {2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)},
     pages = {1--5},
     year = {2021},
     organization = {IEEE},
   }