Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restoration

• URL: http://arxiv.org/abs/2504.15159v1
• Date: Mon, 21 Apr 2025 15:05:22 GMT
• Title: Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restoration
• Authors: Junyuan Deng, Xinyi Wu, Yongxing Yang, Congchao Zhu, Song Wang, Zhenyao Wu,
• Abstract summary: We find that the well-trained large T2I model (i.e., Flux) is able to produce a variety of high-quality images aligned with real-world distributions.<n>A novel light-weighted adapter (FluxIR) with squeeze-and-excitation layers is also carefully designed to control the large Diffusion Transformer (DiT)-based T2I model.
• Score: 25.65952375846516
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, pre-trained text-to-image (T2I) models have been extensively adopted for real-world image restoration because of their powerful generative prior. However, controlling these large models for image restoration usually requires a large number of high-quality images and immense computational resources for training, which is costly and not privacy-friendly. In this paper, we find that the well-trained large T2I model (i.e., Flux) is able to produce a variety of high-quality images aligned with real-world distributions, offering an unlimited supply of training samples to mitigate the above issue. Specifically, we proposed a training data construction pipeline for image restoration, namely FluxGen, which includes unconditional image generation, image selection, and degraded image simulation. A novel light-weighted adapter (FluxIR) with squeeze-and-excitation layers is also carefully designed to control the large Diffusion Transformer (DiT)-based T2I model so that reasonable details can be restored. Experiments demonstrate that our proposed method enables the Flux model to adapt effectively to real-world image restoration tasks, achieving superior scores and visual quality on both synthetic and real-world degradation datasets - at only about 8.5\% of the training cost compared to current approaches.

Related papers

• 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)
• Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models [54.052963634384945]
  We introduce the Image Regeneration task to assess text-to-image models. We use GPT4V to bridge the gap between the reference image and the text input for the T2I model. We also present ImageRepainter framework to enhance the quality of generated images.
  arXiv  Detail & Related papers  (2024-11-14T13:52:43Z)
• DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation [46.22939360256696]
  We present a dual strategy: GenIR, an innovative data curation pipeline, and DreamClear, a cutting-edge Diffusion Transformer (DiT)-based image restoration model. GenIR, our pioneering contribution, is a dual-prompt learning pipeline that overcomes the limitations of existing datasets. DreamClear, is a DiT-based image restoration model. It utilizes the generative priors of text-to-image (T2I) diffusion models and the robust perceptual capabilities of multi-modal large language models (MLLMs) to achieve restoration.
  arXiv  Detail & Related papers  (2024-10-24T11:57:20Z)
• Timestep-Aware Diffusion Model for Extreme Image Rescaling [47.89362819768323]
  We propose a novel framework called Timestep-Aware Diffusion Model (TADM) for extreme image rescaling.<n>TADM performs rescaling operations in the latent space of a pre-trained autoencoder.<n>It effectively leverages powerful natural image priors learned by a pre-trained text-to-image diffusion model.
  arXiv  Detail & Related papers  (2024-08-17T09:51:42Z)
• Review Learning: Advancing All-in-One Ultra-High-Definition Image Restoration Training Method [7.487270862599671]
  We propose a new training paradigm for general image restoration models, which we name bfReview Learning. This approach begins with sequential training of an image restoration model on several degraded datasets, combined with a review mechanism. We design a lightweight all-purpose image restoration network that can efficiently reason about degraded images with 4K resolution on a single consumer-grade GPU.
  arXiv  Detail & Related papers  (2024-08-13T08:08:45Z)
• Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Models [14.25759541950917]
  This work leverages a capable vision-language model and a synthetic degradation pipeline to learn image restoration in the wild (wild IR) Our base diffusion model is the image restoration SDE (IR-SDE)
  arXiv  Detail & Related papers  (2024-04-15T12:34:21Z)
• Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction [62.955327005837475]
  Image super-resolution (SR) aims to learn a mapping from low-resolution (LR) to high-resolution (HR) using paired HR-LR training images. We present an efficient test-time adaptation framework for SR, named SRTTA, which is able to quickly adapt SR models to test domains with different/unknown degradation types.
  arXiv  Detail & Related papers  (2023-10-29T13:58:57Z)
• 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)
• Restormer: Efficient Transformer for High-Resolution Image Restoration [118.9617735769827]
  convolutional neural networks (CNNs) perform well at learning generalizable image priors from large-scale data. Transformers have shown significant performance gains on natural language and high-level vision tasks. Our model, named Restoration Transformer (Restormer), achieves state-of-the-art results on several image restoration tasks.
  arXiv  Detail & Related papers  (2021-11-18T18:59:10Z)
• Two-shot Spatially-varying BRDF and Shape Estimation [89.29020624201708]
  We propose a novel deep learning architecture with a stage-wise estimation of shape and SVBRDF. We create a large-scale synthetic training dataset with domain-randomized geometry and realistic materials. Experiments on both synthetic and real-world datasets show that our network trained on a synthetic dataset can generalize well to real-world images.
  arXiv  Detail & Related papers  (2020-04-01T12:56:13Z)
• A Two-step-training Deep Learning Framework for Real-time Computational Imaging without Physics Priors [0.0]
  We propose a two-step-training DL (TST-DL) framework for real-time computational imaging without physics priors. First, a single fully-connected layer (FCL) is trained to directly learn the model. Then, this FCL is fixed and fixed with an un-trained U-Net architecture for a second-step training to improve the output image fidelity.
  arXiv  Detail & Related papers  (2020-01-10T15:05:43Z)

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.