Component Divide-and-Conquer for Real-World Image Super-Resolution

By Pengxu Wei, Ziwei Xie, Hannan Lu, Zongyuan Zhan, Qixiang Ye, Wangmeng Zuo, Liang Lin. European Conference on Computer Vision, 2020

385 citations recorded by the source corpus.

In this paper, we present a large-scale Diverse Real-world image Super-Resolution dataset, i.e., DRealSR, as well as a divide-and-conquer Super-Resolution (SR) network, exploring the utility of guiding SR model with low-level image components. DRealSR establishes a new SR benchmark with diverse real-world degradation processes, mitigating the limitations of conventional simulated image degradation. In general, the targets of SR vary with image regions with different low-level image components, e.g., smoothness preserving for flat regions, sharpening for edges, and detail enhancing for textures. Learning an SR model with conventional pixel-wise loss usually is easily dominated by flat regions and edges, and fails to infer realistic details of complex textures. We propose a Component Divide-and-Conquer (CDC) model and a Gradient-Weighted (GW) loss for SR. Our CDC parses an image with three components, employs three Component-Attentive Blocks (CABs) to learn attentive masks and intermediate SR predictions with an intermediate supervision learning strategy, and trains an SR model following a divide-and-conquer learning principle. Our GW loss also provides a feasible way to balance the difficulties of image components for SR. Extensive experiments validate the superior performance of our CDC and the challenging aspects of our DRealSR dataset related to diverse real-world scenarios. Our dataset and codes are publicly available at this https URL

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/45597186c691ce72f4bffba066d46f6a613b0a13

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior (2023, methodology): “More Quantitative and Qualitative Comparisons for BSR on Synthetic Datasets The quantitative results on DRealSR [62] and RealSR [3] are presented in Table 10.”
Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization (2023, neutral): “2019) and DRealSR (Wei et al. 2020), for evaluation.”
Real-World Single Image Super-Resolution: A Brief Review (2021, methodology): “3DRealSR [81] is available at https://github.”
Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild (2024, methodology): “We collect a total of 60 real-world LQ images from RealSR [8], DRealSR [80], Real47 [49], and online sources, featuring diverse content including animals, plants, faces, buildings, and landscapes.”
SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution (2023, positive): “To this end, some researchers proposed to collect real-world LR-HR image pairs using long-short camera focal lens [3, 61].”
Exploiting Diffusion Prior for Real-World Image Super-Resolution (2023, neutral): “5 ) achieves the highest CLIP-IQA scores on the two commonly used real-world benchmarks [5, 67], which clearly demonstrates the superiority of StableSR.”