Nan Huang

	Self-Improving 4D Perception via Self-Distillation Nan Huang, Pengcheng Yu, Weijia Zeng, James M. Rehg, Angjoo Kanazawa, Haiwen Feng†, Qianqian Wang† (Equal contribution, †Equal advising)* arXiv, 2026 project page / arXiv / code Self-distillation on unlabeled video bootstraps stronger 4D perception without any 4D ground-truth, scaling beyond the limits of supervised data.
	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 ICRA, 2026 project page / arXiv / code Employs 3D Gaussians to model dynamic scenes for autonomous driving without other supervisions (e.g., 3D bounding boxes).

	Self-Improving 4D Perception via Self-Distillation Nan Huang, Pengcheng Yu, Weijia Zeng, James M. Rehg, Angjoo Kanazawa, Haiwen Feng†, Qianqian Wang† (Equal contribution, †Equal advising)* arXiv, 2026 project page / arXiv / code Self-distillation on unlabeled video bootstraps stronger 4D perception without any 4D ground-truth, scaling beyond the limits of supervised data.
	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 ICRA, 2026 project page / arXiv / code Employs 3D Gaussians to model dynamic scenes for autonomous driving without other supervisions (e.g., 3D bounding boxes).