Biography

I am a Ph.D. student in the School of Computer Science at Peking University, advised by Sheng Li (Professor), Guoping Wang (Professor), and Jiaguang Sun (Member of the Chinese Academy of Engineering). My research focuses on photorealistic rendering and high-performance real-time rendering, with particular interest in practical methods for efficient light transport simulation.

Research Interests

  • Monte Carlo Rendering
  • Path Tracing / Ray Tracing
  • Neural Rendering

Education

Bachelor in Intelligent Science and Technology, 2022

Peking University

Selected
Publications

NRRS: Neural Russian Roulette and Splitting

We propose a novel framework for Russian Roulette and Splitting (RRS) tailored to wavefront path tracing, a highly parallel rendering architecture ...

Haojie Jin, Jierui Ren, Yisong Chen, Guoping Wang, Sheng Li

IEEE Transactions on Visualization and Computer Graphics, 32(7): 7001-7016, 2026

Representative NRRS results comparing rendering quality and efficiency across Apartment2, Sponza Caustic, and Sun Temple Interior

Occlusion-Point Reuse for Ray-Traced Ambient Occlusion and Shadow

Ambient occlusion (AO) and soft shadows are critical visibility cues for spatial perception in real-time rendering. Hardware ray tracing provides a direct way ...

Haojie Jin, Fujia Su, Zehui Lin, Chenxiao Hu, Jierui Ren, Yuqing Yuan, Yanchen Zhang, Zhongtao Wang, Yisong Chen, Kangying Cai, Guoping Wang, Sheng Li

Representative results for AO and soft-shadow using Occlusion-Point Reuse

OctaOctree Neural Radiosity for Real-time Glossy Material Rendering

Modeling high-frequency outgoing radiance distributions remains a fundamental challenge in global illumination, especially for glossy and specular materials. ...

Jierui Ren, Haojie Jin, Bo Pang, Meng Gai, Fei Zhu, Yisong Chen, Sheng Li

Conditionally accepted to SIGGRAPH Asia 2026 Conference Papers

Pipeline and representative results of OctaOctree Neural Radiosity for real-time glossy material rendering

Vertex Features for Neural Global Illumination

Recent research on learnable neural representations has been widely adopted in the field of 3D scene reconstruction and neural rendering applications. ...

Rui Su, Honghao Dong, Haojie Jin, Yisong Chen, Guoping Wang, Sheng Li

SIGGRAPH Asia 2025 Conference Papers

Representative Vertex Features results comparing rendering quality and memory cost across Dining Room and Veach Ajar

Dynamic Neural Radiosity with Multi-grid Decomposition

Prior approaches to the neural rendering of global illumination typically rely on complex network architectures and training strategies to model ...

Rui Su, Honghao Dong, Jierui Ren, Haojie Jin, Guoping Wang, Yisong Chen, Sheng Li

SIGGRAPH Asia 2024 Conference Papers

Representative Dynamic Neural Radiosity results comparing rendering quality across Dining Room, Living Room, and Bedroom