Yurui Chen

Yurui Chen-陈毓锐

I received my Master's degree at Fudan University in 2025 under the supervision of Prof. Li Zhang, and earned my Bachelor's degree at Fudan University in 2022.

I'm interested in 3D reconstruction, generation and understanding.

Email / Google Scholar / Github

Publications & Projects

	UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding Yueming Xu, Jiahui Zhang, Ze Huang, Yurui Chen, Yanpeng Zhou, Zhenyu Chen, Yu-jie Yuan, Pengxiang Xia, Guowei Huang, Xinyue Cai, Zhongang Qi, Xingyue Quan, Jianye Hao, Hang Xu, Li Zhang Arxiv*, 2025 arXiv / project page / code The first unified framework that jointly supports understanding and generation for 3D modalities. Meanwhile, this work developed a geometry-aware vision encoder distillation strategy to enhance spatial perception.
	4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration Jiahui Zhang, Yurui Chen, Yueming Xu, Ze Huang, Yanpeng Zhou, Yu-jie Yuan, Xinyue Cai, Guowei Huang, Xingyue Quan, Hang Xu, Li Zhang NIPS, 2025 arXiv / code A 4D-aware VLA pretraining framework that resolves inefficiencies caused by misaligned coordinate systems and inconsistent states in prior methods.
	From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D Jiahui Zhang, Yurui Chen, Yueming Xu, Ze Huang, Jilin Mei, Junhui chen, Yanpeng Zhou, Yu-jie Yuan, Xinyue Cai, Guowei Huang, Xingyue Quan, Hang Xu, Li Zhang NIPS Datasets&Benchmarks, 2025 arXiv / project page / code An exploratory study on 3D scene understanding from multi-view images, introducing a spatial understanding benchmark that emphasizes numerical QA and feature matching across views, along with a multi-view 3D grounding method.
	BézierGS: Dynamic Urban Scene Reconstruction with Bézier Curve Gaussian Splatting Zipei Ma, Junzhe Jiang, Yurui Chen, Li Zhang ICCV, 2025 arXiv / code A method that models both rigid and non-rigid dynamic objects in urban scenes using Bézier curves, addressing inaccurate foreground poses and the challenges of modeling non-rigid objects.
	GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting Junzhe Jiang, Chun Gu, Yurui Chen, Li Zhang ICLR, 2025 arXiv / code A novel framework for generating realistic LiDAR point clouds with panoramic Gaussian splatting.
	S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation Yurui Chen, Junge Zhang, Ziyang Xie, Wenye Li, Feihu Zhang, Jiachen Lu, Li Zhang TPAMI, 2025 arXiv / project page / code An autonomous driving simulation system based on neural reconstruction and generation supporting scene editing, illumination adaptation, and foreground generation.
	Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Rendering Yurui Chen, Chun Gu, Junzhe Jiang, Xiatian Zhu, Li Zhang arXiv, 2023 arXiv / project page / code A unified representation model for large-scale dynamic urban scene reconstruction.
	Single-view Neural Radiance Fields with Depth Teacher Yurui Chen, Chun Gu, Feihu Zhang, Li Zhang, ICLR workshop 2023 arXiv Combining the (coarse) planar rendering and the (fine) volume rendering to achieve higher rendering quality and better generalizations. A depth teacher net that predicts dense pseudo depth maps is used to supervise the joint rendering mechanism and boost the learning of consistent 3D geometry.

The website template was borrowed from Jon Barron and Chun Gu.