Boosting High-Level Vision with Joint Compression Artifacts Reduction and Super-Resolution

TL;DR

This paper introduces CAJNN, a neural network that jointly reduces compression artifacts and super-resolves images, significantly improving high-level vision tasks like text recognition and tiny face detection.

Contribution

The paper presents a novel joint CAR and SR neural network that integrates local and non-local features in one stage, outperforming previous methods in quality and speed.

Findings

Outperforms previous methods in benchmark datasets

Reduces runtime by 26.2%

Improves text recognition accuracy and face detection precision

Abstract

Due to the limits of bandwidth and storage space, digital images are usually down-scaled and compressed when transmitted over networks, resulting in loss of details and jarring artifacts that can lower the performance of high-level visual tasks. In this paper, we aim to generate an artifact-free high-resolution image from a low-resolution one compressed with an arbitrary quality factor by exploring joint compression artifacts reduction (CAR) and super-resolution (SR) tasks. First, we propose a context-aware joint CAR and SR neural network (CAJNN) that integrates both local and non-local features to solve CAR and SR in one-stage. Finally, a deep reconstruction network is adopted to predict high quality and high-resolution images. Evaluation on CAR and SR benchmark datasets shows that our CAJNN model outperforms previous methods and also takes 26.2% shorter runtime. Based on this model, we explore addressing two critical challenges in high-level computer vision: optical character recognition of low-resolution texts, and extremely tiny face detection. We demonstrate that CAJNN can serve as an effective image preprocessing method and improve the accuracy for real-scene text recognition (from 85.30% to 85.75%) and the average precision for tiny face detection (from 0.317 to 0.611).