Bin Tan
|
Bin Tan I'm currently a research scientist at Ant Group. I obtained Ph.D. degree from Wuhan University under the co-supervision of Prof. Nan Xue and Gui-Song Xia. I'm now interested in 3D reconstruction and scene representation with geometric structures. Email: tanbin[at]whu[dot]edu[dot]cn |
|
[05/2025]: Two papers (PlanarSplatting and ScaleLSD) are accepted to CVPR 2025!
[05/2024]: One paper (NEAT) is accepted to CVPR 2024!
[09/2023]: One paper (NOPE-SAC) is accepted to IEEE TPAMI!
* indicates equal contribution, † indicates the corresponding author
|
PlanarSplatting: Accurate Planar Surface Reconstruction in 3 Minutes
Bin Tan, Rui Yu, Yujun Shen, Nan Xue† CVPR, 2025 Highlight Presentation (All strong accept) arXiv / project page / code |
|
ScaleLSD: Scalable Deep Line Segment Detection Streamlined
Zeran Ke, Bin Tan, Xianwei Zheng, Yujun Shen, Tianfu Wu, Nan Xue† CVPR, 2025 arXiv / project page / code |
|
NEAT: Distilling 3D Wireframes from Neural Attraction Fields
Nan Xue, Bin Tan, Yuxi Xiao, Liang Dong, Gui-Song Xia, Tianfu Wu, Yujun Shen CVPR, 2024 arXiv / PDF / video / code We present a neural 3D wireframe reconstruction approach without explicit line segment matching. |
|
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), Accepted, 2023 arXiv / code We present a novel Neural One-PlanE RANSAC framework (NOPE-SAC) that learns one-plane pose hypotheses from 3D plane correspondences for sparse-view planar reconstruction. |
|
HoW-3D: Holistic 3D Wireframe Perception from a Single Image
Wenchao Ma, Bin Tan, Nan Xue, Tianfu Wu, Xianwei Zheng, Gui-Song Xia 3DV, 2022 arXiv / code / video |
|
PlaneTR: Structure-Guided Transformers for 3D Plane Recovery
Bin Tan*, Nan Xue*, Song Bai, Tianfu Wu, Gui-Song Xia† ICCV, 2021 arXiv / code We present a novel model, PlaneTR, that simultaneously leverages the context information and global structure cues to recover 3D planes from a single image. |
