VeraRetouch: A Lightweight Fully Differentiable Framework for Multi-Task Reasoning Photo Retouching

• URL: http://arxiv.org/abs/2604.27375v1
• Date: Thu, 30 Apr 2026 03:39:32 GMT
• Title: VeraRetouch: A Lightweight Fully Differentiable Framework for Multi-Task Reasoning Photo Retouching
• Abstract summary: VeraRetouch is a lightweight and fully differentiable framework for multi-task photo retouching.<n>We employ a 0.5B Vision-Language Model (VLM) as the central intelligence to formulate retouching plans.<n>We develop a fully differentiable Retouch Renderer that replaces external tools.
• Score: 27.18046653314556
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Reasoning photo retouching has gained significant traction, requiring models to analyze image defects, give reasoning processes, and execute precise retouching enhancements. However, existing approaches often rely on non-differentiable external software, creating optimization barriers and suffering from high parameter redundancy and limited generalization. To address these challenges, we propose VeraRetouch, a lightweight and fully differentiable framework for multi-task photo retouching. We employ a 0.5B Vision-Language Model (VLM) as the central intelligence to formulate retouching plans based on instructions and scene semantics. Furthermore, we develop a fully differentiable Retouch Renderer that replaces external tools, enabling direct end-to-end pixel-level training through decoupled control latents for lighting, global color, and specific color adjustments. To overcome data scarcity, we introduce AetherRetouch-1M+, the first million-scale dataset for professional retouching, constructed via a new inverse degradation workflow. Furthermore, we propose DAPO-AE, a reinforcement learning post-training strategy that enhances autonomous aesthetic cognition. Extensive experiments demonstrate that VeraRetouch achieves state-of-the-art performance across multiple benchmarks while maintaining a significantly smaller footprint, enabling mobile deployment. Our code and models are publicly available at https://github.com/OpenVeraTeam/VeraRetouch.

Related papers

• Universal Image Restoration via Internalized Chain-of-Thought Reasoning [52.763760468548504]
  Image restoration seeks to recover high-quality images from degraded inputs but becomes highly ill-posed under complex, mixed degradations.<n>Recent works adopt Chain-of-Thought (CoT) reasoning for multi-round restoration using specialized modules.<n>We introduce CoTIR, a universal image restoration framework that internalizes CoT reasoning within a single model.
  arXiv  Detail & Related papers  (2026-06-16T06:01:36Z)
• UniSER: A Foundation Model for Unified Soft Effects Removal [72.60782767314713]
  We introduce UniSER, capable of addressing diverse degradations caused by soft effects within a single framework.<n>Our methodology centers on curating a massive 3.8M-pair dataset to ensure robustness and generalization.<n>This synergistic approach allows UniSER to significantly outperform both specialist and generalist models.
  arXiv  Detail & Related papers  (2025-11-18T06:39:39Z)
• Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark [58.61079960074608]
  Existing infrared image enhancement methods focus on tackling individual degradations.<n>All-in-one enhancement methods, commonly applied to RGB sensors, often demonstrate limited effectiveness.
  arXiv  Detail & Related papers  (2025-10-10T12:55:54Z)
• DSwinIR: Rethinking Window-based Attention for Image Restoration [109.38288333994407]
  We propose the Deformable Sliding Window Transformer (DSwinIR) as a new foundational backbone architecture for image restoration.<n>At the heart of DSwinIR is the proposed novel Deformable Sliding Window (DSwin) Attention.<n>Extensive experiments show that DSwinIR sets a new state-of-the-art across a wide spectrum of image restoration tasks.
  arXiv  Detail & Related papers  (2025-04-07T09:24:41Z)
• UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Prior [56.35236964617809]
  Image restoration aims to recover content from inputs degraded by various factors, such as adverse weather, blur, and noise.<n>This paper introduces UniRestore, a unified image restoration model that bridges the gap between PIR and TIR.<n>We propose a Complementary Feature Restoration Module (CFRM) to reconstruct degraded encoder features and a Task Feature Adapter (TFA) module to facilitate adaptive feature fusion in the decoder.
  arXiv  Detail & Related papers  (2025-01-22T08:06:48Z)
• FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration [66.61201445650323]
  Existing methods suffer from a generalization bottleneck in real-world scenarios.<n>We contribute a million-scale dataset with two notable advantages over existing training data.<n>We propose a robust model, FoundIR, to better address a broader range of restoration tasks in real-world scenarios.
  arXiv  Detail & Related papers  (2024-12-02T12:08:40Z)
• Adaptive Blind All-in-One Image Restoration [15.726917603679716]
  Blind all-in-one image restoration models aim to recover a high-quality image from an input degraded with unknown distortions.<n>We introduce ABAIR, a simple yet effective adaptive blind all-in-one restoration model that handles multiple degradations and generalizes well to unseen distortions.<n>Our model not only surpasses state-of-the-art performance on five- and three-task IR setups but also demonstrates superior generalization to unseen degradations and composite distortions.
  arXiv  Detail & Related papers  (2024-11-27T14:58:08Z)
• Multi-task Image Restoration Guided By Robust DINO Features [88.74005987908443]
  We propose mboxtextbfDINO-IR, a multi-task image restoration approach leveraging robust features extracted from DINOv2. We first propose a pixel-semantic fusion (PSF) module to dynamically fuse DINOV2's shallow features. By formulating these modules into a unified deep model, we propose a DINO perception contrastive loss to constrain the model training.
  arXiv  Detail & Related papers  (2023-12-04T06:59:55Z)
• Spectral Graphormer: Spectral Graph-based Transformer for Egocentric Two-Hand Reconstruction using Multi-View Color Images [33.70056950818641]
  We propose a novel transformer-based framework that reconstructs two high fidelity hands from multi-view RGB images. We show that our framework is able to produce realistic two-hand reconstructions and demonstrate the generalisation of synthetic-trained models to real data.
  arXiv  Detail & Related papers  (2023-08-21T20:07:02Z)
• DRM-IR: Task-Adaptive Deep Unfolding Network for All-In-One Image Restoration [5.573836220587265]
  This work proposes an efficient Dynamic Reference Modeling paradigm (DRM-IR) DRM-IR consists of task-adaptive degradation modeling and model-based image restoring. Experiments on multiple benchmark datasets show that our DRM-IR achieves state-of-the-art in All-In-One IR.
  arXiv  Detail & Related papers  (2023-07-15T02:42:19Z)
• Very Lightweight Photo Retouching Network with Conditional Sequential Modulation [42.311196534333284]
  We propose an extremely lightweight framework -- Conditional Sequential Retouching Network (CSRNet) CSRNet only contains less than 37K trainable parameters, which are orders of magnitude smaller than existing learning-based methods. Experiments show that our method achieves state-of-the-art performance on the benchmark MIT-Adobe FiveK dataset.
  arXiv  Detail & Related papers  (2021-04-13T15:11:02Z)

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.