# PlainUSR: Chasing Faster ConvNet for Efficient Super-Resolution

arXiv: https://arxiv.org/abs/2409.13435 · HTML: https://mlsanity.com/paper/2409.13435/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2024.

## Built on by (most cited first, 4 of 4)

- [The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report](https://mlsanity.com/paper/2504.10686/) (2025)
- [DA-Font: Few-Shot Font Generation via Dual-Attention Hybrid Integration](https://mlsanity.com/paper/2509.16632/) (2025)
- [Lung Nodule Image Synthesis Driven by Two-Stage Generative Adversarial Networks](https://mlsanity.com/paper/2602.02171/) (2026)
- [LiAuto-MindViT: A Hybrid Vision Backbone with Adaptive Bidirectional Mamba](https://mlsanity.com/paper/2609.24337/) (2026)

## Abstract (arXiv)

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.