Ruofan Liang
 (若凡, RF)

  Ph.D. Candidate
  University of Toronto
  ruofan [at] cs.toronto.edu

  CV

About

I am a 5th-year PhD student at the University of Toronto, supervised by Prof. Nandita Vijaykumar. Concurrently, I am also affiliated with the Vector Institute. I am currently doing a research intern at Meta Reality Labs in Zurich, focusing on XR World. I previously did the research intern at Nvidia Toronto AI Lab.

Prior to my Ph.D., I received my Bachelor's degree from the Department of Computer Science, Shanghai Jiao Tong University (SJTU), where I worked with Prof. Quanshi Zhang and Prof. Jingwen Leng. I had a wonderful exchange semester in 2019 with research internship at National University of Singapore, advised by Prof. Bingsheng He.

My current research interests are in computer vision and graphics, including but not limited neural field representations, efficient 3D scene learning tasks, SLAM system, neural rendering, inverse rendering, and generative models.


Research

UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting
Kai He, Ruofan Liang, Jacob Munkberg, Jon Hasselgren, Nandita Vijaykumar, Alexander Keller, Sanja Fidler, Igor Gilitschenski, Zan Gojcic, Zian Wang
arxiv preprint
[Project Page

Controllable Weather Synthesis and Removal with Video Diffusion Models
Chih-Hao Lin, Zian Wang, Ruofan Liang, Yuxuan Zhang, Sanja Fidler, Shenlong Wang, Zan Gojcic
ICCV 2025
[Project Page

LGM

ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction
Sankeerth Durvasula, Sharanshangar Muhunthan, Zain Moustafa, Richard Chen, Ruofan Liang, Yushi Guan, Nilesh Ahuja, Nilesh Jain, Selvakumar Panneer, Nandita Vijaykumar
ICCV 2025
[Coming Soon

VideoMat: Extracting PBR Materials from Video Diffusion Models
Jacob Munkberg, Zian Wang, Ruofan Liang, Tianchang Shen, Jon Hasselgren
EGSR 2025 (CGF Track)
[Project Page

DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models
Ruofan Liang*, Zan Gojcic, Huan Ling, Jacob Munkberg, Jon Hasselgren, Zhi-Hao Lin, Jun Gao, Alexander Keller, Nandita Vijaykumar, Sanja Fidler, Zian Wang* (* equal contribution)
CVPR 2025 (Oral)
[Project Page

Retri3D: 3D Neural Graphics Representation Retrieval
Yushi Guan, Daniel Kwan, Jean Sebastien Dandurand, Xi Yan, Ruofan Liang, Yuxuan Zhang, Nilesh Jain, Nilesh Ahuja, Selvakumar Panneer, Nandita Vijaykumar
ICLR 2025 (Spotlight)
[Project Page

Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering
Ruofan Liang, Zan Gojcic, Merlin Nimier-David, David Acuna, Nandita Vijaykumar, Sanja Fidler, Zian Wang
ECCV 2024
[Project Page

LGM

SCAR: Sub-Core and Atomic-Unit Collaborative Reduction for Efficient Raster-based Differentiable Rendering
Sankeerth Durvasula, Adrian Zhao, Fan Chen, Ruofan Liang, Pawan Kumar Sanjaya, Nandita Vijaykumar
ASPLOS 2025
[Github Repo

LGM

INRet: A General Framework for Accurate Retrieval of INRs for Shapes
Yushi Guan, Daniel Kwan, Ruofan Liang, Selvakumar Panneer, Nilesh Jain, Nilesh Ahuja, Nandita Vijaykumar
3DV 2025
[Paper

GaussianObject: Just Taking Four Images to Get A High-Quality 3D Object with Gaussian Splatting
Chen Yang, Sikuang Li, Jiemin Fang, Ruofan Liang, Lingxi Xie, Xiaopeng Zhang, Wei Shen, Qi Tian
SIGGRAPH Asia 2024 (Journal Track)
[Project Page

DISORF: A Distributed Online 3D Reconstruction Framework for Mobile Robots
Chunlin Li, Hanrui Fan, Xiaorui Huang, Ruofan Liang* (*project leader), Sankeerth Durvasula, Nandita Vijaykumar
RA-L 2025
[Github Repo

LGM

ENVIDR: Implicit Differentiable Renderer with Neural Environment Lighting
Ruofan Liang, Huiting Chen, Chunlin Li, Fan Chen, Selvakumar Panneer, Nandita Vijaykumar
ICCV 2023 (Oral)
[Project Page

LGM

SPIDR: SDF-based Neural Point Fields for Illumination and Deformation
Ruofan Liang, Jiahao Zhang, Haoda Li, Chen Yang, Yushi Guan, Nandita Vijaykumar
CVPRW 2023
[Project Page

LGM

CoordX: Accelerating Implicit Neural Representation with a Split MLP Architecture
Ruofan Liang, Hongyi Sun, Nandita Vijaykumar
ICLR 2022
[Paper]  [Slides]  [Code

LGM

Knowledge Consistency between Neural Networks and Beyond
Ruofan Liang*, Tianlin Li*, Longfei Li, Jing Wang, Quanshi Zhang
ICLR 2020 (* equal contribution)
[Paper]  [Code


Previous Projects

LGM

Accel-RF
A general programming framework towards the efficient implementation of neural radiance fields (NeRF) and its variants (e.g., NSVF, VolSDF, NeuS).
JIT compilation + multi-GPU training
Jan, 2022
[Code

LGM

FPGA RAM Mapper
A FPGA CAD tool that maps the logic RAMs required by the circuit to the physical RAMs with circuit area on FPGA as small as possible.
1st place in the competition of Prof. Vaughn Betz's FPGA course (ECE1756).
Nov, 2021
[Code

LGM

Tetris-RL
A RL-based Tetris playing agent. A model-based value iteration algorithm is proposed to make AI to play Tetris with promising performance (1000+ lines per game).
UofT CSC2515 Course Project, Dec, 2020
[Code

LGM

Accel-Video Pipe (AVPipe)
AVPipe is an integrated C++ library for AI video inference tasks on customers' devices, aiming to provide easily-used and high-performance experience.
3rd prize of the excellent bachelor thesis @ SJTU
Jun, 2020
[Code


Miscellaneous

I am a geek always excited to discover something Fun. Now, I am still on my long long way to obtaining knowledge & experience, hoping to exploit my potential.

X

Put on a happy face🙃~



Last updated: July, 2025