Youtian Lin (林尤添)

Ph.D. Student

Computer Vision & Graphics

NJU-3DV Lab

About Me

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

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.

This page was last updated in November 2025.

Interests

• 3D/4D Reconstruction & Generation
• Neural Rendering
• Generative Models
• High-Performance GPU Programming

Education

• PhD in Computer Science, 2024 - Present

  Nanjing University (NJU)

• PhD in Computer Science, 2021 - 2023

  Harbin Institute of Technology (HIT)

• M.S. in Computer Science, 2018 - 2021

  Harbin Engineering University (HEU)

• B.S. in Computer Science, 2014 - 2018

  Harbin University of Science and Technology (HRBUST)

News

2025-09-24

New paper: SpatialVID — for world model and spatial intelligence.

2025-09-19

Direct3D-S2 is accepted to NeurIPS 2025.

2025-07-05

Align Your Rhythm is accepted to ICCV 2025.

2025-05-29

New work release: Direct3D-S2.

2025-05-06

In summer 2025, I will join Apple as a Research Intern.

2024-09-27

Two papers (Direct3D, FastDrag) accepted to NeurIPS 2024.

2024-07-01

Three ECCV 2024 papers: Relightable 3D Gaussian, STAG4D, UniDream.

Highlight Publications

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

ArXiv 2025

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

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

Conference on Neural Information Processing Systems (NeurIPS) 2025

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

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

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

Youtian Lin, Zuozhuo Dai, Siyu Zhu, Yao Yao

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

European Conference on Computer Vision (ECCV) 2024

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

Publications

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

ArXiv 2025

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

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

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

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

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

Conference on Neural Information Processing Systems (NeurIPS) 2025

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

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

International Conference on Learning Representations (ICLR) 2025

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

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

Conference on Neural Information Processing Systems (NeurIPS) 2024

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

FastDrag: Manipulate Anything in One Step

Conference on Neural Information Processing Systems (NeurIPS) 2024

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

STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians

European Conference on Computer Vision (ECCV) 2024

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

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

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

Youtian Lin, Zuozhuo Dai, Siyu Zhu, Yao Yao

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

European Conference on Computer Vision (ECCV) 2024

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

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

European Conference on Computer Vision (ECCV) 2024

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

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

AAAI Conference on Artificial Intelligence (AAAI) 2024

Youtian Lin

See Full List

Service

• Conference Reviewer
• IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• IEEE/CVF International Conference on Computer Vision (ICCV)
• Conference on Neural Information Processing Systems (NeurIPS)
• International Conference on Learning Representations (ICLR)
• International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
• AAAI Conference on Artificial Intelligence (AAAI)
• ACM SIGGRAPH Asia
• Journal Reviewer
• IEEE Transactions on Visualization and Computer Graphics (TVCG)
• IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)

Projects

Pointrix

Differentiable point‑based rendering library for 3D reconstruction and rendering.

threestudio-3DGS

Gaussian Splatting extension for threestudio framework.

taichi-nerfs

Taichi + PyTorch Instant‑NGP training pipeline for neural radiance fields.

taichi-ngp-renderer

Instant‑NGP renderer implemented in pure Python using Taichi.

nerfacc

Fast NeRF acceleration toolkit (contributor).

Contact

• linyoutian.loyot@gmail.com
• Nanjing University (NJU), Suzhou, China