Geometry-Aware Reference Synthesis for Multi-View Image Super-Resolution

TL;DR

This paper introduces MVSRnet, a geometry-aware method for multi-view image super-resolution that synthesizes pixel-aligned references from multiple views to enhance resolution, outperforming existing approaches.

Contribution

The paper presents a novel geometry-aware reference synthesis module and a high-frequency search network for improved multi-view image super-resolution.

Findings

Significant performance improvements over state-of-the-art methods.

Effective handling of large-angle view transformations.

Enhanced detail recovery in super-resolved images.

Abstract

Recent multi-view multimedia applications struggle between high-resolution (HR) visual experience and storage or bandwidth constraints. Therefore, this paper proposes a Multi-View Image Super-Resolution (MVISR) task. It aims to increase the resolution of multi-view images captured from the same scene. One solution is to apply image or video super-resolution (SR) methods to reconstruct HR results from the low-resolution (LR) input view. However, these methods cannot handle large-angle transformations between views and leverage information in all multi-view images. To address these problems, we propose the MVSRnet, which uses geometry information to extract sharp details from all LR multi-view to support the SR of the LR input view. Specifically, the proposed Geometry-Aware Reference Synthesis module in MVSRnet uses geometry information and all multi-view LR images to synthesize pixel-aligned HR reference images. Then, the proposed Dynamic High-Frequency Search network fully exploits the high-frequency textural details in reference images for SR. Extensive experiments on several benchmarks show that our method significantly improves over the state-of-the-art approaches.