Restore What Matters: Lessons from Joint Restoration and Recognition

• URL: http://arxiv.org/abs/2609.13791v1
• Date: Sat, 12 Sep 2026 08:08:08 GMT
• Title: Restore What Matters: Lessons from Joint Restoration and Recognition
• Abstract summary: Recognition pipelines typically adopt a restore-then-recognize workflow, yet decades of experience show that generating visually pleasing images seldom to improved recognition.<n>We propose a Joint Restoration-for-Recognition paradigm: restore only what downstream tasks truly require, with task signals dictating where, how much, and whether restoration is necessary.<n>We conclude that better-looking images are neither necessary nor sufficient; restoration modules must be task-driven, selective, and physically aware.
• Score: 72.91692240810536
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recognition pipelines typically adopt a restore-then-recognize workflow, yet decades of experience show that generating visually pleasing images seldom translates to improved recognition. We propose a Joint Restoration-for-Recognition (JR$^2$) paradigm: restore only what downstream tasks truly require, with task signals dictating where, how much, and whether restoration is necessary. JR$^2$ rests on three pillars: (i) Physics, employing optics-accurate turbulence simulation, extensible to blur and noise, to ground restoration in real image formation; (ii) Neuroscience, drawing on selective attention and neuroplasticity to direct model capacity toward identity-critical regions and frames while bypassing already-clean inputs; and (iii) Vision & Learning, coupling recognition loss end-to-end through restoration and alignment so that low-level edits maximize high-level identity stability. Evaluations on IARPA-BRIAR show consistent improvements (e.g., TAR@0.01% FAR +0.6; FNIR@1% FPIR -2.5), while a quality gate skips ~70% of clean frames, reducing cost. Ablations confirm physics priors enhance realism, joint training prevents catastrophic forgetting, and selective restoration suffices in many cases. We conclude that better-looking images are neither necessary nor sufficient; restoration modules must be task-driven, selective, and physically aware. Code, pretrained models, and recipes are provided for integration.

Related papers

• Restoration-Aligned Generative Flow Models for Blind Motion Deblurring [57.425021485907756]
  We present DeFlow, a framework that resolves misalignment by reformulating the flow trajectory itself.<n>Under this formulation, the standard flow matching loss naturally takes the form of a residual loss.<n>Experiments on GoPro, HIDE, RealBlur, and RWBI demonstrate that DeFlow achieves strong restoration fidelity and perceptual realism.
  arXiv  Detail & Related papers  (2026-05-09T10:05:51Z)
• Restore, Assess, Repeat: A Unified Framework for Iterative Image Restoration [84.3817904120563]
  Image restoration aims to recover high quality images from inputs degraded by various factors, such as adverse weather, blur, or low light.<n>We propose RAR, a Restore, Assess and Repeat process, that integrates Image Quality Assessment (IQA) and Image Restoration (IR) into a unified framework.<n> Specifically, we introduce a restoration process that operates entirely in the latent domain to jointly perform degradation identification, image restoration, and quality verification.
  arXiv  Detail & Related papers  (2026-03-27T13:13:44Z)
• Degradation-Aware All-in-One Image Restoration via Latent Prior Encoding [46.146259918814735]
  Real-world images often suffer from spatially diverse degradations such as haze, rain, snow, and low-light.<n>Existing all-in-one restoration approaches either depend on external text prompts or embed hand-crafted architectural priors.<n>We propose to reframe AIR as learned latent prior inference, where degradation-aware representations are automatically inferred from the input.
  arXiv  Detail & Related papers  (2025-09-22T13:51:09Z)
• Continual Learning-Based Unified Model for Unpaired Image Restoration Tasks [2.7241418453016792]
  For applications such as autonomous driving, a unified model is necessary to perform restoration of corrupted images due to different weather conditions.<n>We propose a continual learning approach to propose a unified framework for image restoration.<n>Experiments on standard benchmark datasets for dehazing, desnowing and deraining tasks demonstrate significant improvements in PSNR, SSIM, and perceptual quality over the state-of-the-art.
  arXiv  Detail & Related papers  (2025-07-25T11:47:40Z)
• ReFIR: Grounding Large Restoration Models with Retrieval Augmentation [52.00990126884406]
  We propose a solution called the Retrieval-augmented Framework for Image Restoration (ReFIR) Our ReFIR incorporates retrieved images as external knowledge to extend the knowledge boundary of existing LRMs. Our experiments demonstrate that ReFIR can achieve not only high-fidelity but also realistic restoration results.
  arXiv  Detail & Related papers  (2024-10-08T01:27:45Z)
• Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restoration [33.163161549726446]
  Perceive-IR is a novel backbone-agnostic All-in-One image restoration framework for fine-grained quality control.<n>Its modular structure allows core components to function independently of specific backbones, enabling seamless integration into advanced restoration models.
  arXiv  Detail & Related papers  (2024-08-28T17:58:54Z)
• DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior [70.46245698746874]
  We present DiffBIR, a general restoration pipeline that could handle different blind image restoration tasks. DiffBIR decouples blind image restoration problem into two stages: 1) degradation removal: removing image-independent content; 2) information regeneration: generating the lost image content. In the first stage, we use restoration modules to remove degradations and obtain high-fidelity restored results. For the second stage, we propose IRControlNet that leverages the generative ability of latent diffusion models to generate realistic details.
  arXiv  Detail & Related papers  (2023-08-29T07:11:52Z)
• Implicit Subspace Prior Learning for Dual-Blind Face Restoration [66.67059961379923]
  A novel implicit subspace prior learning (ISPL) framework is proposed as a generic solution to dual-blind face restoration. Experimental results demonstrate significant perception-distortion improvement of ISPL against existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-10-12T08:04:24Z)

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.