Nan Huang

Segment Any Motion in Videos
Nan Huang, Wenzhao Zheng, Chengfeng Xu, Kurt Keutzer, Shanghang Zhang, Angjoo Kanazawa, Qianqian Wang
CVPR, 2025
project page / arXiv / code

Learning which points are moving from the point tracks and using the moving point tracks to prompt SAM2 to get the final segmentation masks.

High-Quality 3D Creation from A Single Image Using Subject-Specific Knowledge Prior
Nan Huang, Ting Zhang, Yuhui Yuan, Dong Chen, Shanghang Zhang
ICRA, 2025
project page / arXiv / code

Leveraging multi-modal images to customize the diffusion prior, thereby incorporating subject-specific knowledge into the generation process.

S³Gaussian: Self-Supervised Street Gaussians for Autonomous Driving
Nan Huang, Xiaobao Wei, Wenzhao Zheng, Pengju An, Ming Lu, Wei Zhan, Masayoshi Tomizuka, Kurt Keutzer, Shanghang Zhang
arXiv, 2024
project page / arXiv / code

Employs 3D Gaussians to model dynamic scenes for autonomous driving without other supervisions (e.g., 3D bounding boxes).

	Segment Any Motion in Videos Nan Huang, Wenzhao Zheng, Chengfeng Xu, Kurt Keutzer, Shanghang Zhang, Angjoo Kanazawa, Qianqian Wang CVPR, 2025 project page / arXiv / code Learning which points are moving from the point tracks and using the moving point tracks to prompt SAM2 to get the final segmentation masks.
	EMD: Explicit Motion Modeling for High-Quality Street Gaussian Splatting Xiaobao Wei, Qingpo Wuwu, Zhongyu Zhao, Zhuangzhe Wu, Nan Huang, Ming Lu, Ningning Ma, Shanghang Zhang ICCV, 2025 project page / arXiv A plug-and-play approach which models the motions of dynamic objects by introducing learnable motion embeddings to the Gaussians.
	High-Quality 3D Creation from A Single Image Using Subject-Specific Knowledge Prior Nan Huang, Ting Zhang, Yuhui Yuan, Dong Chen, Shanghang Zhang ICRA, 2025 project page / arXiv / code Leveraging multi-modal images to customize the diffusion prior, thereby incorporating subject-specific knowledge into the generation process.
	S³Gaussian: Self-Supervised Street Gaussians for Autonomous Driving Nan Huang, Xiaobao Wei, Wenzhao Zheng, Pengju An, Ming Lu, Wei Zhan, Masayoshi Tomizuka, Kurt Keutzer, Shanghang Zhang arXiv, 2024 project page / arXiv / code Employs 3D Gaussians to model dynamic scenes for autonomous driving without other supervisions (e.g., 3D bounding boxes).