Youtian Lin 林尤添

Brief Introduction简介

I am a first-year Ph.D. student at Nanjing University, supervised by Prof. Yao Yao, Prof. Xun Cao and Prof. Tieniu Tan. Previously, I pursued a Ph.D. at the Harbin Institute of Technology. I earned my M.S. from the Harbin Engineering University in 2021, where I was advised by Prof. Jian Guan.

我目前就读于 南京大学，师从 姚遥教授，并在 曹汛教授 和 谭铁牛教授 的联合指导下攻读博士学位。此前曾在 哈尔滨工业大学 学习。2021年于 哈尔滨工程大学 获得硕士学位，导师为 关健教授。

I’m currently a research intern at DreamTech. Previously, I worked at leading 3D generation startups Taichi (Meshy AI) and VAST (Tripo AI), where I contributed to their early 3D generation breakthroughs.

目前在 DreamTech 担任研究实习生。曾就职于顶尖的 3D 生成初创公司 Taichi（Meshy AI）和 VAST（Tripo AI），参与其早期 3D 生成技术的研发与突破。

Research Interests研究方向

My research interests are in computer vision and graphics, with a particular focus on 3D and 4D reconstruction and generation. I am also exploring recent advances in neural rendering and generative models. My work aims to reconstruct and synthesize realistic representations of the physical world.

我的研究领域为计算机视觉与图形学，专注于3D和4D场景的重建与生成技术。同时深入探索神经渲染和生成式模型的前沿发展，致力于构建物理世界的真实数字表征。

I'm also interested in high-performance GPU and Graphic programming, including CUDA and Vulkan (also kind of knowing OpenGL and Metal).

同时热衷于高性能GPU计算和图形编程，熟悉CUDA、Vulkan等技术栈（亦掌握OpenGL和Metal开发）。

Recent News最新动态

• 2025‑09‑24 – New paper: SpatialVID — for world model and spatial intelligence.新论文：SpatialVID —— 用于世界模型与空间智能。
• 2025‑09‑19 – Direct3D‑S2 is accepted to NeurIPS 2025.Direct3D‑S2 被 NeurIPS 2025 接收。
• 2025‑07-05 – Align Your Rhythm is accepted to ICCV 2025.Align Your Rhythm 被 ICCV 2025 接收。
• 2025‑05‑29 – New work release: Direct3D-S2.Direct3D-S2 发布。
• 2025‑05‑06 – In summer 2025, I will join Apple as a Research Intern.2025 年夏，将前往香港 Apple 3D Vision 团队实习。
• 2024‑09‑27 – Two papers (Direct3D, FastDrag) accepted to NeurIPS 2024.两篇论文 (Direct3D, FastDrag) 被 NeurIPS 2024 接收。
• 2024‑07‑01 – Three ECCV 2024 papers: Relightable 3D Gaussian, STAG4D, UniDream.三篇 ECCV 2024 论文：Relightable 3D Gaussian、STAG4D、UniDream。

Selected Publications论文发表

1. 

   SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

   Jiahao Wang, Yufeng Yuan, Rujie Zheng, Youtian Lin, Jian Gao, Lin‑Zhuo Chen, Yajie Bao, Yi Zhang, Chang Zeng, Yanxi Zhou, Xiao‑Xiao Long, Hao Zhu, Zhaoxiang Zhang, Xun Cao, Yao Yao

   Arxiv 2025
2. 

   Align Your Rhythm: Generating Highly Aligned Dance Poses with Gating-Enhanced Rhythm-Aware Feature Representation

   Congyi Fan, Jian Guan, Xuanjia Zhao, Dongli Xu, Youtian Lin, Tong Ye, Pengming Feng Haiwei Pan

   IEEE/CVF International Conference on Computer Vision (ICCV) 2025
3. 

   Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

   Shuang Wu *, Youtian Lin*, Yifei Zeng, Yikang Yang, Yajie Bao, Jiachen Qian, Siyu Zhu, Feihu Zhang, Xun Cao, Philip Torr, Yao Yao

   Conference on Neural Information Processing Systems (NeurIPS) 2025
4. 

   Flow Distillation Sampling: Regularizing 3D Gaussians with Pre‑trained Matching Priors

   Lin-Zhuo Chen *, Kangjie Liu *, Youtian Lin, Zhihao Li, Siyu Zhu, Xun Cao, Yao Yao

   International Conference on Learning Representations (ICLR) 2025
5. 

   Direct3D: Scalable Image‑to‑3D Generation via 3D Latent Diffusion Transformer

   Shuang Wu*, Youtian Lin*, Feihu Zhang, Yifei Zeng, Jingxi Xu, Philip Torr, Xun Cao, Yao Yao

   Conference on Neural Information Processing Systems (NeurIPS) 2024
6. 

   FastDrag: Manipulate Anything in One Step

   Xuanjia Zhao, Jian Guan, Congyi Fan, Dongli Xu, Youtian Lin, Haiwei Pan, Pengming Feng

   Conference on Neural Information Processing Systems (NeurIPS) 2024
7. 

   STAG4D: Spatial‑Temporal Anchored Generative 4D Gaussians

   Yifei Zeng*, Yanqin Jiang*, Siyu Zhu, Yuanxun Lu, Youtian Lin, Hao Zhu, Weiming Hu, Xun Cao, Yao Yao

   European Conference on Computer Vision (ECCV) 2024
8. 

   Gaussian‑Flow: 4D Reconstruction with Dynamic 3D Gaussian Particles

   Youtian Lin, Zuozhuo Dai, Siyu Zhu, Yao Yao

   IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024 (Highlight)
9. 

   Relightable 3D Gaussian: Real-time Point Cloud Relighting with BRDF Decomposition and Ray Tracing

   Jian Gao, Chun Gu, Youtian Lin, Hao Zhu, Xun Cao, Li Zhang, Yao Yao

   European Conference on Computer Vision (ECCV) 2024
10. 

    UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generation

    Zexiang Liu*, Yangguang Li*, Youtian Lin*, Xin Yu, Sida Peng, Yan-Pei Cao, Xiaojuan Qi, Xiaoshui Huang, Ding Liang, Wanli Ouyang

    European Conference on Computer Vision (ECCV) 2024
11. 

    Ced-NeRF: A Compact and Efficient Method for Dynamic Neural Radiance Fields

    Youtian Lin

    AAAI Conference on Artificial Intelligence (AAAI) 2024

Full list on 更多论文见 Google Scholar.

Community Service社区服务

• Conference Reviewer – SIGGRAPH Asia, ICCV, NeurIPS, ICLR, ICASSP, AAAI会议审稿 – SIGGRAPH Asia、ICCV、NeurIPS、ICLR、ICASSP、AAAI
• Journal Reviewer – TVCG, TCSVT期刊审稿 – TVCG、TCSVT

Open‑Source Projects开源项目