Hongxiang Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Hongxiang Huang has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Hongtao Sheng
State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China
2 shared publications - Hujun Bao
State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China
2 shared publications - Rui Wang
State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China
2 shared publications - Yuchi Huo
State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China
2 shared publications - Chuankun Zheng
Zhejiang University
1 shared publication - Hao Zhu
Manycore Tech Inc., Hangzhou, China
1 shared publication
Latest Publications
- Open Access
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Neural Global Illumination via Superposed Deformable Feature Fields
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessNeural Global Illumination via Superposed Deformable Feature Fields
- Open Access
- 19 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (4) , 1-14
LightFormer: Light-Oriented Global Neural Rendering in Dynamic Scene
The generation of global illumination in real time has been a long-standing challenge in the graphics community, particularly in dynamic scenes with complex illumination. Recent neural rendering techniques have shown great promise by utilizing neural networks to represent the illumination of scenes and then decoding the final radiance. However, incorporating object parameters into the representation may limit their effectiveness in handling fully dynamic scenes. This work presents a neural rendering approach, dubbed LightFormer , that can generate realistic global illumination for fully dynamic scenes, including dynamic lighting, materials, cameras, and animated objects, in real time. Inspired by classic many-lights methods, the proposed approach focuses on the neural representation of light sources in the scene rather than the entire scene, leading to the overall better generalizability. The neural prediction is achieved by leveraging the virtual point lights and shading clues for each light. Specifically, two stages are explored. In the light encoding stage, each light generates a set of virtual point lights in the scene, which are then encoded into an implicit neural light representation, along with screen-space shading clues like visibility. In the light gathering stage, a pixel-light attention mechanism composites all light representations for each shading point. Given the geometry and material representation, in tandem with the composed light representations of all lights, a lightweight neural network predicts the final radiance. Experimental results demonstrate that the proposed LightFormer can yield reasonable and realistic global illumination in fully dynamic scenes with real-time performance.
- 19 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (4) , 1-14
Open AccessLightFormer: Light-Oriented Global Neural Rendering in Dynamic Scene
The generation of global illumination in real time has been a long-standing challenge in the graphics community, particularly in dynamic scenes with complex illumination. Recent neural rendering techniques have shown great promise by utilizing neural networks to represent the illumination of scenes and then decoding the final radiance. However, incorporating object parameters into the representation may limit their effectiveness in handling fully dynamic scenes. This work presents a neural rendering approach, dubbed LightFormer , that can generate realistic global illumination for fully dynamic scenes, including dynamic lighting, materials, cameras, and animated objects, in real time. Inspired by classic many-lights methods, the proposed approach focuses on the neural representation of light sources in the scene rather than the entire scene, leading to the overall better generalizability. The neural prediction is achieved by leveraging the virtual point lights and shading clues for each light. Specifically, two stages are explored. In the light encoding stage, each light generates a set of virtual point lights in the scene, which are then encoded into an implicit neural light representation, along with screen-space shading clues like visibility. In the light gathering stage, a pixel-light attention mechanism composites all light representations for each shading point. Given the geometry and material representation, in tandem with the composed light representations of all lights, a lightweight neural network predicts the final radiance. Experimental results demonstrate that the proposed LightFormer can yield reasonable and realistic global illumination in fully dynamic scenes with real-time performance.