|
Chaoyi Zhou I am a PhD student in Computer Science at Clemson University advised by Prof. Siyu Huang. Previously, I obtanined my M.S. in Computer Science from University of Southern California, where I worked advised by Prof. Yajie Zhao . I received my B.E. in Computer Science and Technology from Nanjing University of Posts and Telecommunications in 2020. My research interets including computer vision and generative model. Currently, I am focusing on 3D vision with implict representation and 3D content generation. |
|
News2025.09: One paper is accepted to NeurIPS. 2025.03: I will join Microsoft as a Research Intern! 2025.01: One paper is accepted to ICLR. 2024.09: One paper is accepted to NeurIPS as Spotlight (3.5% of 15671 submissions). 2024.01: I will join Vision and Learning Lab in Clemson University as a PhD student! |
Selected Publications* indicates equal contribution |
|
FlexMap: Generalized HD Map Construction from Flexible Camera Configurations
Run Wang, Chaoyi Zhou, Amir Salarpour, Xi Liu, Zhi-Qi Cheng, Feng Luo, Mert D. Pesé, Siyu Huang preprint arXiv We introduce FlexMap, a flexible HD map construction method that adapts to variable camera configurations without architectural changes or retraining. Unlike prior methods fixed to specific multi-camera setups, FlexMap uses a geometry-aware foundation model with cross-frame attention to implicitly encode 3D scene understanding, maintaining robustness to missing views and sensor variations for practical autonomous driving deployment. |
|
Bézier Splatting for Fast and Differentiable Vector Graphics
Xi Liu*, Chaoyi Zhou*, Nanxuan Zhao, Siyu Huang NeurIPS, 2025 project page / arXiv This work introduces a new differentiable VG representation, dubbed Bézier splatting, that enables fast yet high-fidelity VG rasterization. Bézier splatting samples 2D Gaussians along Bézier curves, which naturally provide positional gradients at object boundaries. |
|
Latent Radiance Fields with 3D-aware 2D Representations
Chaoyi Zhou*, Xi Liu*, Feng Luo, Siyu Huang ICLR, 2025 project page / arXiv / code In this work, we propose a method to achieve 3D-aware 2D representations and enable 3D reconstruction in the latent space. Our LRF enables 3D reconstruction on the 2D latent space instead of the image space. It can render high-quality and photorealistic novel views, even for the unbounded scenes. |
|
3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors
Xi Liu*, Chaoyi Zhou*, Siyu Huang NeurIPS, 2024 (Spotlight) project page / arXiv / code 3DGS-Enhancer restores view-consistent latent features of rendered novel views and integrates them with the input views through a spatial-temporal decoder. The enhanced views are then used to fine-tune the initial 3DGS model, significantly improving its rendering performance. |
ServiceConference Reviewer: CVPR'26, ICCV'25, ICML'25, ICLR'25, NeurIPS'24,25. |
Award2025.04: Rising Researcher Award from Clemson University 2025.03: ICLR Student Travel Award |