FuseSR+: Spatial-Temporal Fusion for High-Scale Super-Resolution
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 lower resolution to reduce rendering overhead and then manage to accurately upsample the low-resolution (LR) rendered image to the high-resolution (HR) results, a.k.a. super-resolution techniques. Theoretically, reconstructing a higher-resolution image requires integrating additional information beyond the rendered low-resolution image. Most existing methods predominantly rely on temporal information from low-resolution sources, such as historical frames. However, the temporal information accumulated frame-by-frame is generally too sparse to recover the fine details for high-scale super-resolution. To break the limit, this paper proposes an efficient and effective neural super-resolution method that utilizes non-aligned spatial and temporal information to achieve stable large-scale super-resolution. We introduce low-cost historical and current high-resolution auxiliary G-buffers as additional cues to enhance high-frequency detail reconstruction, spatial coherence, and temporal stability. To efficiently align and fuse various features — including spatial and temporal, low- and high-resolution features — under runtime constraints, we propose several novel technical modules, specifically, an H-Net architecture, a corresponding pixel shuffling and unshuffling layers for aligning low- and high-resolution features in a compact network, and a lightweight temporal feature recurrent module for aggregating HR temporal features. These techniques significantly reduce rendering overhead without noticeable quality deterioration. Experiments demonstrate that our method is able to produce temporally consistent reconstructions in both 4 × 4 and the more challenging 8 × 8 large-scale upsampling tasks at 4K resolution with real-time performance, while delivering substantially improved visual quality, significant performance gains, and remarkable temporal stability compared to existing methods.
Authors
- Jingsen Zhu (ORCID: https://orcid.org/0009-0003-2707-1044)
- Chuankun Zheng (ORCID: https://orcid.org/0000-0001-6369-6592)
- Yuchi Huo (ORCID: https://orcid.org/0000-0003-3296-7999)
- Weijia Xue (ORCID: https://orcid.org/0009-0005-5996-5362)
- Rui Wang (ORCID: https://orcid.org/0000-0003-4267-0347)
- Shi Li (ORCID: https://orcid.org/0009-0009-3664-5509)
- Tian Xie (ORCID: https://orcid.org/0000-0003-0204-1124)
- Suiliang Mai (ORCID: https://orcid.org/0009-0001-1077-8479)
Institutions
- Cornell University (US)
- Zhejiang University (CN)
Publication Details
- Journal
- ACM Transactions on Graphics
- Published
- 2026-11-19
- DOI
- https://doi.org/10.1145/3859872
- Primary Topic
- Advanced Image Processing Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00