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

2025-08-10

AI Summary

Existing image restoration methods neglect depth information, leading to scattered attention in shallow-depth scenes and excessive background enhancement in deep-depth scenes. To address this, we propose the Depth-Guided Image Restoration Network (DGIR-Net), the first framework to jointly model structured depth estimation and image restoration within a dual-branch collaborative architecture. DGIR-Net introduces progressive window-based self-attention and sparse non-local attention mechanisms, leveraging depth-aware features to guide intra- and inter-object similarity modeling. To support this work, we construct a new high-resolution plant image dataset comprising 9,205 images. Extensive experiments demonstrate state-of-the-art performance across multiple standard benchmarks and strong generalization to unseen plant imagery. Our method significantly improves fine-detail recovery and ensures superior depth consistency in restored outputs.

Technology Category

• Computer Vision: Image and Video Retrieval
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

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.

Problem

• Addresses depth information neglect in image restoration methods
• Solves attention distractions in shallow depth-of-field scenarios
• Reduces excessive background enhancement in deep DoF settings

Innovation

• Depth-guided network with two interactive branches
• Progressive window-based self-attention mechanism
• Novel high-resolution plant species dataset