Fan Fei (费凡)

I am a third-year Ph.D. student at the Camera Intelligence Research Lab at Peking University, where I work on 3D computer vision. My PhD advisor is Prof. Boxin Shi.

Previously, I graduate from Turing Class at Peking University as a BS (Summa Cum Laude) in Intelligence Science and Technology.

Email  /  GitHub  /  Google Scholar  /  LinkedIn

profile photo

Research

I previously worked on 3D computer vision and computer graphics, especially inverse rendering, 3D reconstruction, and 3D generation. Now I am focusing on embodied AI.

project image

No Redundancy, No Stall: Lightweight Streaming 3D Gaussian Splatting for Real-time Rendering


Linye Wei, Jiajun Tang, Fan Fei, Boxin Shi, Runsheng Wang, Meng Li
The International Conference on Computer-Aided Design (ICCAD), 2025

We propose LS-Gaussian, an algorithm/hardware co-design framework for lightweight streaming 3D rendering which achieves 5.41× speedup over the edge GPU baseline on average and up to 17.3× speedup with the customized accelerator.

project image

PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models


Fan Fei, Jiajun Tang, Fei-Peng Tian, Boxin Shi#, Ping Tan
arXiv, 2025
paper /

We propose PacTure, a method to efficiently generate physically-based rendering (PBR) textures on a packed multi-view grid using a visual autoregressive model as multi-view generation backbone.

project image

SpecTRe-GS: Modeling Highly Specular Surfaces with Reflected Nearby Objects by Tracing Rays in 3D Gaussian Splatting


Jiajun Tang, Fan Fei, Zhihao Li, Xiao Tang, Shiyong Liu, Youyu Chen, Binxiao Huang, Zhenyu Chen, Xiaofei Wu, Boxin Shi#
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (Highlight), 2025
paper / website /

We propose a 3D reconstruction method which models highly specular surfaces that reflect nearby objects through ray tracing in 3D Gaussian Splatting.

project image

VMINer: Versatile Multi-view Inverse Rendering with Near- and Far-field Light Sources


Fan Fei, Jiajun Tang, Ping Tan, Boxin Shi#
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (Highlight), 2024
paper / code / poster / website / youtube /

We use near-field lights, such as flashlights, as sources of lighting variation to enhance both the practicality and the quality of multi-view inverse rendering.

project image

SPLiT: Single Portrait Lighting Estimation Via a Tetrad of Face Intrinsics


Fan Fei*, Yean Cheng*, Yongjie Zhu, Qian Zheng, Si Li, Gang Pan, Boxin Shi#
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023
paper / code / website /

From a single portrait image, we estimate a tetrad of face intrinsics and uses spherically distributed components to estimate lighting.


Design and source code from Jon Barron's website