Youtian Lin

林尤添 (Youtian Lin)

博士研究生

计算机视觉与图形学

南京大学 NJU-3DV 实验室

关于我

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

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。

本页面最后更新于 2025年11月。

研究兴趣
  • 3D/4D 重建与生成
  • 神经渲染
  • 生成式模型
  • 高性能GPU编程
教育背景
  • 计算机科学博士,2024 - 至今

    南京大学 (NJU)

  • 计算机科学博士,2021 - 2023

    哈尔滨工业大学 (HIT)

  • 计算机科学硕士,2018 - 2021

    哈尔滨工程大学 (HEU)

  • 计算机科学学士,2014 - 2018

    哈尔滨理工大学 (HRBUST)

新闻

2025-09-24
新论文:SpatialVID —— 用于世界模型与空间智能。
2025-09-19
Direct3D-S2NeurIPS 2025 接收。
2025-07-05
Align Your RhythmICCV 2025 接收。
2025-05-29
Direct3D-S2 发布。
2025-05-06
2025 年夏,将前往香港 Apple 3D Vision 团队实习。
2024-09-27
两篇论文 (Direct3D, FastDrag) 被 NeurIPS 2024 接收。
2024-07-01
三篇 ECCV 2024 论文:Relightable 3D GaussianSTAG4DUniDream

代表论文

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
ArXiv 2025
Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
Conference on Neural Information Processing Systems (NeurIPS) 2025
Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particles
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024 - Highlight
Relightable 3D Gaussian: Real-time Point Cloud Relighting with BRDF Decomposition and Ray Tracing
European Conference on Computer Vision (ECCV) 2024

论文发表

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
ArXiv 2025
Align Your Rhythm: Generating Highly Aligned Dance Poses with Gating-Enhanced Rhythm-Aware Feature Representation
IEEE/CVF International Conference on Computer Vision (ICCV) 2025
Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
Conference on Neural Information Processing Systems (NeurIPS) 2025
Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors
International Conference on Learning Representations (ICLR) 2025
Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer
Conference on Neural Information Processing Systems (NeurIPS) 2024
FastDrag: Manipulate Anything in One Step
Conference on Neural Information Processing Systems (NeurIPS) 2024
STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians
European Conference on Computer Vision (ECCV) 2024
Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particles
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024 - Highlight
Relightable 3D Gaussian: Real-time Point Cloud Relighting with BRDF Decomposition and Ray Tracing
European Conference on Computer Vision (ECCV) 2024
UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generation
European Conference on Computer Vision (ECCV) 2024
Ced-NeRF: A Compact and Efficient Method for Dynamic Neural Radiance Fields
AAAI Conference on Artificial Intelligence (AAAI) 2024

查看完整列表

服务

  • 会议审稿
    • 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
  • 期刊审稿
    • IEEE Transactions on Visualization and Computer Graphics (TVCG)
    • IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)

联系方式