Haotong Lin
I am a final-year PhD student in Computer Science at Zhejiang University, advised by Prof. Xiaowei Zhou and Sida Peng (expected to graduate in June 2026). I obtained my bachelor degree in Computer Science from Zhejiang University in 2021. In the summer of 2022, I had the opportunity to engage in a highly enjoyable collaboration with Noah Snavely at Cornell University.
My research focuses on spatial intelligence, with a particular interest in building human-level machine perception systems.
I’m always open to collaborations. Feel free to reach out!
Email: haotongl@outlook.com
Selected Publications
Depth Anything 3: recovering the visual space from any viewsHaotong Lin, Sili Chen, Hao Liew Jun, Y. Chen Donny, Zhenyu Li, Guang Shi, Jiashi Feng, and Bingyi KangarXiv 2025
Pixel-Perfect Depth with Semantics-Prompted Diffusion TransformersGangwei Xu, Haotong Lin*, Hongcheng Luo, Xianqi Wang, Jingfeng Yao, Lianghui Zhu, Yuechuan Pu, Cheng Chi, Haiyang Sun, Bing Wang, and othersNeurIPS 2025
Prompting Depth Anything for 4K Resolution Accurate Metric Depth EstimationHaotong Lin, Sida Peng, Jingxiao Chen, Songyou Peng, Jiaming Sun, Minghuan Liu, Hujun Bao, Jiashi Feng, Xiaowei Zhou, and Bingyi KangIn CVPR 2025
Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian SplattingYunzhi Yan, Haotong Lin, Chenxu Zhou, Weijie Wang, Haiyang Sun, Kun Zhan, Xianpeng Lang, Xiaowei Zhou, and Sida PengIn ECCV 2024
High-Fidelity and Real-Time Novel View Synthesis for Dynamic ScenesHaotong Lin, Sida Peng, Zhen Xu, Tao Xie, Xingyi He, Hujun Bao, and Xiaowei ZhouIn SIGGRAPH Asia 2023
Neural Scene ChronologyHaotong Lin, Qianqian Wang, Ruojin Cai, Sida Peng, Hadar Averbuch-Elor, Xiaowei Zhou, and Noah SnavelyIn CVPR 2023
Efficient Neural Radiance Fields for Interactive Free-viewpoint VideoHaotong Lin, Sida Peng, Zhen Xu, Yunzhi Yan, Qing Shuai, Hujun Bao, and Xiaowei ZhouIn SIGGRAPH ASIA 2022
Learning to Estimate Object Poses without Real Image AnnotationsHaotong Lin, Sida Peng, Zhize Zhou, and Xiaowei ZhouIn IJCAI 2022
All Publications
2025
-
Depth Anything 3: recovering the visual space from any viewsHaotong Lin, Sili Chen, Hao Liew Jun, Y. Chen Donny, Zhenyu Li, Guang Shi, Jiashi Feng, and Bingyi KangarXiv 2025
-
Pixel-Perfect Depth with Semantics-Prompted Diffusion TransformersGangwei Xu, Haotong Lin*, Hongcheng Luo, Xianqi Wang, Jingfeng Yao, Lianghui Zhu, Yuechuan Pu, Cheng Chi, Haiyang Sun, Bing Wang, and othersNeurIPS 2025
-
Prompting Depth Anything for 4K Resolution Accurate Metric Depth EstimationHaotong Lin, Sida Peng, Jingxiao Chen, Songyou Peng, Jiaming Sun, Minghuan Liu, Hujun Bao, Jiashi Feng, Xiaowei Zhou, and Bingyi KangIn CVPR 2025
2024
StreetCrafter: Street View Synthesis with Controllable Video Diffusion ModelsYunzhi Yan, Zhen Xu, Haotong Lin, Haian Jin, Haoyu Guo, Yida Wang, Kun Zhan, Xianpeng Lang, Hujun Bao, Xiaowei Zhou, and Sida PengIn arXiv 2024
Neural 3D Scene Reconstruction With Indoor Planar PriorsXiaowei Zhou, Haoyu Guo, Sida Peng, Yuxi Xiao, Haotong Lin, Qianqian Wang, Guofeng Zhang, and Hujun BaoTPAMI 2024
4K4D: Real-Time 4D View Synthesis at 4K ResolutionZhen Xu, Sida Peng, Haotong Lin, Guangzhao He, Jiaming Sun, Yujun Shen, Hujun Bao, and Xiaowei ZhouIn CVPR 2024-
Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian SplattingYunzhi Yan, Haotong Lin, Chenxu Zhou, Weijie Wang, Haiyang Sun, Kun Zhan, Xianpeng Lang, Xiaowei Zhou, and Sida PengIn ECCV 2024
2023
EasyVolcap: Accelerating Neural Volumetric Video ResearchZhen Xu, Tao Xie, Sida Peng, Haotong Lin, Qing Shuai, Zhiyuan Yu, Guangzhao He, Jiaming Sun, Hujun Bao, and Xiaowei Zhou2023-
High-Fidelity and Real-Time Novel View Synthesis for Dynamic ScenesHaotong Lin, Sida Peng, Zhen Xu, Tao Xie, Xingyi He, Hujun Bao, and Xiaowei ZhouIn SIGGRAPH Asia 2023
-
Neural Scene ChronologyHaotong Lin, Qianqian Wang, Ruojin Cai, Sida Peng, Hadar Averbuch-Elor, Xiaowei Zhou, and Noah SnavelyIn CVPR 2023
AutoRecon: Automated 3D Object Discovery and ReconstructionYuang Wang, Xingyi He, Sida Peng, Haotong Lin, Hujun Bao, and Xiaowei ZhouIn CVPR 2023
Painting 3D Nature in 2D: View Synthesis of Natural Scenes from a Single Semantic MaskShangzhan Zhang, Sida Peng, Tianrun Chen, Linzhan Mou, Haotong Lin, Kaicheng Yu, Yiyi Liao, and Xiaowei ZhouIn CVPR 2023
2022
-
Efficient Neural Radiance Fields for Interactive Free-viewpoint VideoHaotong Lin, Sida Peng, Zhen Xu, Yunzhi Yan, Qing Shuai, Hujun Bao, and Xiaowei ZhouIn SIGGRAPH ASIA 2022
-
Neural 3D Scene Reconstruction With the Manhattan-World AssumptionHaoyu Guo, Sida Peng, Haotong Lin, Qianqian Wang, Guofeng Zhang, Hujun Bao, and Xiaowei ZhouIn CVPR 2022
-
Learning to Estimate Object Poses without Real Image AnnotationsHaotong Lin, Sida Peng, Zhize Zhou, and Xiaowei ZhouIn IJCAI 2022
2021
PVNet: Pixel-Wise Voting Network for 6DoF Object Pose EstimationSida Peng, Xiaowei Zhou, Yuan Liu, Haotong Lin, Qixing Huang, and Hujun BaoTPAMI 2021
Experiences
| [04/2024 - now] | Research Intern, ByteDance Seed |
|---|---|
| [06/2022 - 12/2022] | Research Intern, Cornell University |
| [10/2021 - 04/2022] | Research Intern, Tao Technology Department, Alibaba Group |
| [12/2020 - 03/2021] | Algorithm Engineer Intern, Inceptio Technology |