Similarity Matters: A Novel Depth-guided Network for Image Restoration and A New Dataset

TL;DR

This paper introduces a depth-guided network for image restoration that leverages depth information to improve quality, supported by a new large-scale dataset of plant images, achieving state-of-the-art results.

Contribution

The paper presents a novel depth-guided network architecture and a large-scale high-resolution plant image dataset for improved image restoration.

Findings

Achieves state-of-the-art performance on standard benchmarks.

Effectively generalizes to unseen plant images.

Demonstrates robustness and effectiveness of the proposed method.

Abstract

Image restoration has seen substantial progress in recent years. However, existing methods often neglect depth information, which hurts similarity matching, results in attention distractions in shallow depth-of-field (DoF) scenarios, and excessive enhancement of background content in deep DoF settings. To overcome these limitations, we propose a novel Depth-Guided Network (DGN) for image restoration, together with a novel large-scale high-resolution dataset. Specifically, the network consists of two interactive branches: a depth estimation branch that provides structural guidance, and an image restoration branch that performs the core restoration task. In addition, the image restoration branch exploits intra-object similarity through progressive window-based self-attention and captures inter-object similarity via sparse non-local attention. Through joint training, depth features contribute to improved restoration quality, while the enhanced visual features from the restoration branch in turn help refine depth estimation. Notably, we also introduce a new dataset for training and evaluation, consisting of 9,205 high-resolution images from 403 plant species, with diverse depth and texture variations. Extensive experiments show that our method achieves state-of-the-art performance on several standard benchmarks and generalizes well to unseen plant images, demonstrating its effectiveness and robustness.