Selective Image Super-Resolution

TL;DR

This paper introduces a selective image super-resolution system that enhances specific regions and objects within images by leveraging segmentation, sparse coding, and multi-task learning, improving resolution quality for targeted areas.

Contribution

The paper presents a novel framework for selective super-resolution that incorporates region, source, and refinement selectivity using advanced learning techniques and over-segmented images.

Findings

Effective super-resolution on object regions in benchmark datasets

Improved figure-ground separation through joint SR and segmentation

Demonstrated applications in various vision tasks

Abstract

In this paper we propose a vision system that performs image Super Resolution (SR) with selectivity. Conventional SR techniques, either by multi-image fusion or example-based construction, have failed to capitalize on the intrinsic structural and semantic context in the image, and performed "blind" resolution recovery to the entire image area. By comparison, we advocate example-based selective SR whereby selectivity is exemplified in three aspects: region selectivity (SR only at object regions), source selectivity (object SR with trained object dictionaries), and refinement selectivity (object boundaries refinement using matting). The proposed system takes over-segmented low-resolution images as inputs, assimilates recent learning techniques of sparse coding (SC) and grouped multi-task lasso (GMTL), and leads eventually to a framework for joint figure-ground separation and interest object SR. The efficiency of our framework is manifested in our experiments with subsets of the VOC2009 and MSRC datasets. We also demonstrate several interesting vision applications that can build on our system.