|
I am currently a second-year Ph.D candidate. student in Software Engineering at the School of Software, Tsinghua University, advised by Prof. Yu-Shen Liu. I have been studying at Tsinghua University since 2017, where I also received bachelor and master degrees under the supervision of Prof. Yu-Shen Liu. My research interests lie at the intersection of 3D computer vision and computer graphics, with a focus on 3D surface reconstruction, 3D foundation models and feed-forward models. |
|
|
|
(* Equal Contribution) |
|
Takeshi Noda, Yu-Shen Liu, Zhizhong han IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026 project page | arXiv | code GSPrior reconstructs high-fidelity surfaces by deriving TSDF-based self-constrained priors from rendered depths to geometrically refine 3D Gaussians without external supervision. |
|
Takeshi Noda*, Chao Chen*, Junsheng Zhou, Weiqi Zhang, Yu-Shen Liu, Zhizhong han IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025 project page | arXiv | code Bijective-SDF improves 3D surface reconstruction from sparse point clouds by learning bijective surface parameterization and optimizing grid deformation. |
|
Takeshi Noda*, Chao Chen*, Weiqi Zhang, Xinhai Liu, Yu-Shen Liu, Zhizhong han Conference on Neural Information Processing Systems (NeurIPS), 2024 project page | arXiv | code MultiPull is a novel method that improves 3D surface reconstruction from point clouds by optimizing multi-scale implicit fields and leveraging frequency features. |
|
|
|
|
template adapted from
this awesome website
|