Zhihua Zhong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Zhihua Zhong has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Chuankun Zheng
Zhejiang University
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 - Xuanyang Huang
Computational Media and Arts, The Hong Kong University of Science and Technology (Guangzhou), Guangdong, China
2 shared publications - Yuchi Huo
State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China
2 shared publications - David Yip
Hong Kong University of Science and Technology, Guangzhou, Guangzhou, China and Hong Kong University of Science and Technology, Hong Kong, Hong Kong
1 shared publication
Latest Publications
- Open Access
- 18 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Immersive-woven into the Interactive Silk Road
- 18 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessImmersive-woven into the Interactive Silk Road
- Open Access
- 19 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Cinema Meowdiso: Films Co-Created by Human, Large Language Models and a Cat
- 19 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessCinema Meowdiso: Films Co-Created by Human, Large Language Models and a Cat
- Open Access
- 10 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-10
FuseSR: Super Resolution for Real-time Rendering through Efficient Multi-resolution Fusion
The workload of real-time rendering is steeply increasing as the demand for high resolution, high refresh rates, and high realism rises, overwhelming most graphics cards. To mitigate this problem, one of the most popular solutions is to render images at a low resolution to reduce rendering overhead, and then manage to accurately upsample the low-resolution rendered image to the target resolution, a.k.a. super-resolution techniques. Most existing methods focus on exploiting information from low-resolution inputs, such as historical frames. The absence of high frequency details in those LR inputs makes them hard to recover fine details in their high-resolution predictions. In this paper, we propose an efficient and effective super-resolution method that predicts high-quality upsampled reconstructions utilizing low-cost high-resolution auxiliary G-Buffers as additional input. With LR images and HR G-buffers as input, the network requires to align and fuse features at multi resolution levels. We introduce an efficient and effective H-Net architecture to solve this problem and significantly reduce rendering overhead without noticeable quality deterioration. Experiments show that our method is able to produce temporally consistent reconstructions in 4 × 4 and even challenging 8 × 8 upsampling cases at 4K resolution with real-time performance, with substantially improved quality and significant performance boost compared to existing works.Project page: https://isaac-paradox.github.io/FuseSR/
- 10 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessFuseSR: Super Resolution for Real-time Rendering through Efficient Multi-resolution Fusion
The workload of real-time rendering is steeply increasing as the demand for high resolution, high refresh rates, and high realism rises, overwhelming most graphics cards. To mitigate this problem, one of the most popular solutions is to render images at a low resolution to reduce rendering overhead, and then manage to accurately upsample the low-resolution rendered image to the target resolution, a.k.a. super-resolution techniques. Most existing methods focus on exploiting information from low-resolution inputs, such as historical frames. The absence of high frequency details in those LR inputs makes them hard to recover fine details in their high-resolution predictions. In this paper, we propose an efficient and effective super-resolution method that predicts high-quality upsampled reconstructions utilizing low-cost high-resolution auxiliary G-Buffers as additional input. With LR images and HR G-buffers as input, the network requires to align and fuse features at multi resolution levels. We introduce an efficient and effective H-Net architecture to solve this problem and significantly reduce rendering overhead without noticeable quality deterioration. Experiments show that our method is able to produce temporally consistent reconstructions in 4 × 4 and even challenging 8 × 8 upsampling cases at 4K resolution with real-time performance, with substantially improved quality and significant performance boost compared to existing works.Project page: https://isaac-paradox.github.io/FuseSR/
- Open Access
- 29 August 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 42 (5) , 1-16
NeLT: Object-Oriented Neural Light Transfer
This article presents object-oriented neural light transfer (NeLT), a novel neural representation of the dynamic light transportation between an object and the environment. Our method disentangles the global illumination of a scene into individual objects’ light transportation represented via neural networks, then composes them explicitly. It therefore enables flexible rendering with dynamic lighting, cameras, materials, and objects. Our rendering features various important global illumination effects, such as diffuse illumination, glossy illumination, dynamic shadowing, and indirect illumination, which completes the capability of existing neural object representation. Experiments show that NeLT does not require path tracing or shading results as input but achieves rendering quality comparable to state-of-the-art rendering frameworks, including the recent deep learning based denoisers.
- 29 August 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 42 (5) , 1-16
Open AccessNeLT: Object-Oriented Neural Light Transfer
This article presents object-oriented neural light transfer (NeLT), a novel neural representation of the dynamic light transportation between an object and the environment. Our method disentangles the global illumination of a scene into individual objects’ light transportation represented via neural networks, then composes them explicitly. It therefore enables flexible rendering with dynamic lighting, cameras, materials, and objects. Our rendering features various important global illumination effects, such as diffuse illumination, glossy illumination, dynamic shadowing, and indirect illumination, which completes the capability of existing neural object representation. Experiments show that NeLT does not require path tracing or shading results as input but achieves rendering quality comparable to state-of-the-art rendering frameworks, including the recent deep learning based denoisers.