Lin-Zhuo Chen 陈林卓

PhD Student at Nanjing University

linzhuochen@foxmail.com

Research Interests

3D Foundation Models
World Models

I am a PhD student at Nanjing University, supervised by Prof. Yao Yao in 3DV-lab. I am also a member of CITE lab, working closely with Prof. Qiu Shen and Prof. Xun Cao. Currently, I am also a research intern at RobbyAnt, mentored by Prof. Yinghao Xu. Previously, I was a master student at Nankai University, supervised by Prof. Ming-Ming Cheng.

Outside of research, I am a vibe coding enthusiast — currently exploring how AI agents can help with both software development and teaching. video-to-notebook is one such experiment.

Constructive discussions and cooperations are always welcome. Please feel free to contact me via email.

Research Highlights

video-to-notebook

Open Source

Read open-course video as one merged notebook using claude/codex — textbook + concept encyclopedia in a single static site.

View Project

LingBot-Map

ArXiv 2026

Geometric Context Transformer for Streaming 3D Reconstruction

View Project

Flow Distillation Sampling

ICLR 2025

Regularizing 3D Gaussians with Pre-trained Matching Priors

View Project

Pointrix

Open Source

A differentiable point-based rendering library supporting 3D Gaussian Splatting

View Project

SG-Conv

IEEE TIP 2021

Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentation

View Project

SpatialVID

ArXiv 2025

A Large-Scale Video Dataset with Spatial Annotations

View Project

Publications

Representative works are highlighted (* denotes equal contribution)

LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction

Lin-Zhuo Chen*, Jian Gao*, Yihang Chen, Ka Leong Cheng, Yipengjing Sun, Liangxiao Hu, Nan Xue, Xing Zhu, Yujun Shen, Yao Yao†, Yinghao Xu†

ArXiv preprint 2604.14141, 2026

PDF Project Code Model

A feed-forward 3D foundation model unifying coordinate grounding, dense geometric cues, and long-range drift correction in a single streaming framework, enabling stable ~20 FPS inference over 10,000+ frames.

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, Xiaoxiao Long, Hao Zhu, Zhaoxiang Zhang, Xun Cao, Yao Yao†

IEEE CVPR, 2026, CCF-A

PDF Project Code

Denoise to Track: Harnessing Video Diffusion Priors for Robust Correspondence

Tianyu Yuan, Yuanbo Yang, Lin-Zhuo Chen, Yao Yao†, Zhuzhong Qian†

ArXiv preprint 2512.04619

PDF Project Code

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†

ICLR 2025, CCF-A

PDF Project Code

We propose Flow Distillation Sampling to regularize 3D Gaussians with pre-trained matching priors, improving reconstruction quality.

Pointrix: A differentiable point-based rendering library supporting 3D Gaussian Splatting and beyond

Open Source Project

Arxiv Pre-print 2024 (WIP)

PDF (Coming soon) Document Code

A differentiable point-based rendering library supporting 3D Gaussian Splatting and beyond.

Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentation

Lin-Zhuo Chen, Zheng Lin, Ziqin Wang, Yong-Liang Yang, Ming-Ming Cheng

IEEE TIP, 2021, SCI-1, CCF-A

PDF Code

We propose spatial information guided convolution for real-time RGBD semantic segmentation.

Interactive Image Segmentation with First Click Attention

Zheng Lin, Zhao Zhang, Lin-Zhuo Chen, Ming-Ming Cheng, Shao-Ping Lu

IEEE CVPR, 2020, CCF-A

PDF Project Code

Interactive image segmentation with first click attention mechanism for improved user interaction.

Blog

Notes on research, tools, and what I'm thinking about — written when the thought is worth keeping.

May 14, 2026 Meta

Hello, world: starting this blog

Why I'm setting up a writing corner on my homepage — and what to expect here.

Read post ›