Learning Single-Image Super-Resolution in the JPEG Compressed Domain

TL;DR

This paper introduces a method for training single-image super-resolution models directly on JPEG compressed data, significantly reducing data loading and training time while maintaining visual quality.

Contribution

It is the first to explore JPEG DCT coefficients for SISR, enabling faster training without sacrificing image restoration quality.

Findings

2.6x faster data loading

2.5x faster training

Comparable visual quality to standard methods

Abstract

Deep learning models have grown increasingly complex, with input data sizes scaling accordingly. Despite substantial advances in specialized deep learning hardware, data loading continues to be a major bottleneck that limits training and inference speed. To address this challenge, we propose training models directly on encoded JPEG features, reducing the computational overhead associated with full JPEG decoding and significantly improving data loading efficiency. While prior works have focused on recognition tasks, we investigate the effectiveness of this approach for the restoration task of single-image super-resolution (SISR). We present a lightweight super-resolution pipeline that operates on JPEG discrete cosine transform (DCT) coefficients in the frequency domain. Our pipeline achieves a 2.6x speedup in data loading and a 2.5x speedup in training, while preserving visual quality comparable to standard SISR approaches.