English

PlainUSR: Chasing Faster ConvNet for Efficient Super-Resolution

Image and Video Processing 2024-09-23 v1

Abstract

Reducing latency is a roaring trend in recent super-resolution (SR) research. While recent progress exploits various convolutional blocks, attention modules, and backbones to unlock the full potentials of the convolutional neural network (ConvNet), achieving real-time performance remains a challenge. To this end, we present PlainUSR, a novel framework incorporating three pertinent modifications to expedite ConvNet for efficient SR. For the convolutional block, we squeeze the lighter but slower MobileNetv3 block into a heavier but faster vanilla convolution by reparameterization tricks to balance memory access and calculations. For the attention module, by modulating input with a regional importance map and gate, we introduce local importance-based attention to realize high-order information interaction within a 1-order attention latency. As to the backbone, we propose a plain U-Net that executes channel-wise discriminate splitting and concatenation. In the experimental phase, PlainUSR exhibits impressively low latency, great scalability, and competitive performance compared to both state-of-the-art latency-oriented and quality-oriented methods. In particular, compared to recent NGswin, the PlainUSR-L is 16.4x faster with competitive performance.

Keywords

Cite

@article{arxiv.2409.13435,
  title  = {PlainUSR: Chasing Faster ConvNet for Efficient Super-Resolution},
  author = {Yan Wang and Yusen Li and Gang Wang and Xiaoguang Liu},
  journal= {arXiv preprint arXiv:2409.13435},
  year   = {2024}
}

Comments

Accepted by ACCV 2024. Under camera-ready revision

R2 v1 2026-06-28T18:51:18.082Z