Manifold-aware Representation Learning for Degradation-agnostic Image Restoration

• URL: http://arxiv.org/abs/2505.18679v1
• Date: Sat, 24 May 2025 12:52:10 GMT
• Title: Manifold-aware Representation Learning for Degradation-agnostic Image Restoration
• Authors: Bin Ren, Yawei Li, Xu Zheng, Yuqian Fu, Danda Pani Paudel, Ming-Hsuan Yang, Luc Van Gool, Nicu Sebe,
• Abstract summary: Image Restoration (IR) aims to recover high quality images from degraded inputs affected by various corruptions such as noise, blur, haze, rain, and low light conditions.<n>We present MIRAGE, a unified framework for all in one IR that explicitly decomposes the input feature space into three semantically aligned parallel branches.<n>This modular decomposition significantly improves generalization and efficiency across diverse degradations.
• Score: 135.90908995927194
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image Restoration (IR) aims to recover high quality images from degraded inputs affected by various corruptions such as noise, blur, haze, rain, and low light conditions. Despite recent advances, most existing approaches treat IR as a direct mapping problem, relying on shared representations across degradation types without modeling their structural diversity. In this work, we present MIRAGE, a unified and lightweight framework for all in one IR that explicitly decomposes the input feature space into three semantically aligned parallel branches, each processed by a specialized module attention for global context, convolution for local textures, and MLP for channel-wise statistics. This modular decomposition significantly improves generalization and efficiency across diverse degradations. Furthermore, we introduce a cross layer contrastive learning scheme that aligns shallow and latent features to enhance the discriminability of shared representations. To better capture the underlying geometry of feature representations, we perform contrastive learning in a Symmetric Positive Definite (SPD) manifold space rather than the conventional Euclidean space. Extensive experiments show that MIRAGE not only achieves new state of the art performance across a variety of degradation types but also offers a scalable solution for challenging all-in-one IR scenarios. Our code and models will be publicly available at https://amazingren.github.io/MIRAGE/.

Related papers

• URWKV: Unified RWKV Model with Multi-state Perspective for Low-light Image Restoration [22.746234919635018]
  We introduce a Unified Receptance Weighted Key Value (URWKV) model with multi-state perspective.<n>We customize the core URWKV block to perceive and analyze complex degradations by leveraging multiple intra- and inter-stage states.<n>In comparison to state-of-the-art models, our URWKV model achieves superior performance on various benchmarks.
  arXiv  Detail & Related papers  (2025-05-29T04:17:09Z)
• Any Image Restoration via Efficient Spatial-Frequency Degradation Adaptation [158.37640586809187]
  Restoring any degraded image efficiently via just one model has become increasingly significant.<n>Our approach, termed AnyIR, takes a unified path that leverages inherent similarity across various degradations.<n>To fuse the degradation awareness and the contextualized attention, a spatial-frequency parallel fusion strategy is proposed.
  arXiv  Detail & Related papers  (2025-04-19T09:54:46Z)
• An Efficient and Mixed Heterogeneous Model for Image Restoration [71.85124734060665]
  Current mainstream approaches are based on three architectural paradigms: CNNs, Transformers, and Mambas.<n>We propose RestorMixer, an efficient and general-purpose IR model based on mixed-architecture fusion.
  arXiv  Detail & Related papers  (2025-04-15T08:19:12Z)
• UniUIR: Considering Underwater Image Restoration as An All-in-One Learner [49.35128836844725]
  We propose a Universal Underwater Image Restoration method, termed as UniUIR.<n>To decouple degradation-specific issues and explore the inter-correlations among various degradations in UIR task, we designed the Mamba Mixture-of-Experts module.<n>This module extracts degradation prior information in both spatial and frequency domains, and adaptively selects the most appropriate task-specific prompts.
  arXiv  Detail & Related papers  (2025-01-22T16:10:42Z)
• OneRestore: A Universal Restoration Framework for Composite Degradation [33.556183375565034]
  In real-world scenarios, image impairments often manifest as composite degradations, presenting a complex interplay of elements such as low light, haze, rain, and snow. Our study proposes a versatile imaging model that consolidates four physical corruption paradigms to accurately represent complex, composite degradation scenarios. OneRestore is a novel transformer-based framework designed for adaptive, controllable scene restoration.
  arXiv  Detail & Related papers  (2024-07-05T16:27:00Z)
• Multi-Scale Cascading Network with Compact Feature Learning for RGB-Infrared Person Re-Identification [35.55895776505113]
  Multi-Scale Part-Aware Cascading framework (MSPAC) is formulated by aggregating multi-scale fine-grained features from part to global. Cross-modality correlations can thus be efficiently explored on salient features for distinctive modality-invariant feature learning.
  arXiv  Detail & Related papers  (2020-12-12T15:39:11Z)
• Learning Enriched Features for Real Image Restoration and Enhancement [166.17296369600774]
  convolutional neural networks (CNNs) have achieved dramatic improvements over conventional approaches for image restoration task. We present a novel architecture with the collective goals of maintaining spatially-precise high-resolution representations through the entire network. Our approach learns an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details.
  arXiv  Detail & Related papers  (2020-03-15T11:04:30Z)
• Image Fine-grained Inpainting [89.17316318927621]
  We present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields. To better train this efficient generator, except for frequently-used VGG feature matching loss, we design a novel self-guided regression loss. We also employ a discriminator with local and global branches to ensure local-global contents consistency.
  arXiv  Detail & Related papers  (2020-02-07T03:45:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.