RFSR: Improving ISR Diffusion Models via Reward Feedback Learning

• URL: http://arxiv.org/abs/2412.03268v1
• Date: Wed, 04 Dec 2024 12:23:17 GMT
• Title: RFSR: Improving ISR Diffusion Models via Reward Feedback Learning
• Authors: Xiaopeng Sun, Qinwei Lin, Yu Gao, Yujie Zhong, Chengjian Feng, Dengjie Li, Zheng Zhao, Jie Hu, Lin Ma,
• Abstract summary: We propose a timestep-aware training strategy with reward feedback learning. In the initial denoising stages of ISR diffusion, we apply low-frequency constraints to super-resolution (SR) images. In the later denoising stages, we use reward feedback learning to improve the perceptual and aesthetic quality of the SR images.
• Score: 20.627228463213854
• License:
• Abstract: Generative diffusion models (DM) have been extensively utilized in image super-resolution (ISR). Most of the existing methods adopt the denoising loss from DDPMs for model optimization. We posit that introducing reward feedback learning to finetune the existing models can further improve the quality of the generated images. In this paper, we propose a timestep-aware training strategy with reward feedback learning. Specifically, in the initial denoising stages of ISR diffusion, we apply low-frequency constraints to super-resolution (SR) images to maintain structural stability. In the later denoising stages, we use reward feedback learning to improve the perceptual and aesthetic quality of the SR images. In addition, we incorporate Gram-KL regularization to alleviate stylization caused by reward hacking. Our method can be integrated into any diffusion-based ISR model in a plug-and-play manner. Experiments show that ISR diffusion models, when fine-tuned with our method, significantly improve the perceptual and aesthetic quality of SR images, achieving excellent subjective results. Code: https://github.com/sxpro/RFSR

Related papers

• RAP-SR: RestorAtion Prior Enhancement in Diffusion Models for Realistic Image Super-Resolution [36.137383171027615]
  We introduce RAP-SR, a restoration prior enhancement approach in pretrained diffusion models for Real-SR. First, we develop the High-Fidelity Aesthetic Image dataset (HFAID), curated through a Quality-Driven Aesthetic Image Selection Pipeline (QDAISP) Second, we propose the Restoration Priors Enhancement Framework, which includes Restoration Priors Refinement (RPR) and Restoration-Oriented Prompt Optimization (ROPO) modules.
  arXiv  Detail & Related papers  (2024-12-10T03:17:38Z)
• Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors [75.24313405671433]
  Diffusion-based image super-resolution (SR) methods have achieved remarkable success by leveraging large pre-trained text-to-image diffusion models as priors. We introduce a novel one-step SR model, which significantly addresses the efficiency issue of diffusion-based SR methods. Unlike existing fine-tuning strategies, we designed a degradation-guided Low-Rank Adaptation (LoRA) module specifically for SR.
  arXiv  Detail & Related papers  (2024-09-25T16:15:21Z)
• Burst Super-Resolution with Diffusion Models for Improving Perceptual Quality [12.687175237915019]
  Prior SR networks accepting the burst LR images are trained in a deterministic manner, which is known to produce a blurry SR image. Since such blurry images are perceptually degraded, we aim to reconstruct the sharp high-fidelity boundaries. In our proposed method, on the other hand, burst LR features are used to reconstruct the initial burst SR image.
  arXiv  Detail & Related papers  (2024-03-28T13:58:05Z)
• Denoising Autoregressive Representation Learning [13.185567468951628]
  Our method, DARL, employs a decoder-only Transformer to predict image patches autoregressively. We show that the learned representation can be improved by using tailored noise schedules and longer training in larger models.
  arXiv  Detail & Related papers  (2024-03-08T10:19:00Z)
• Reconstruct-and-Generate Diffusion Model for Detail-Preserving Image Denoising [16.43285056788183]
  We propose a novel approach called the Reconstruct-and-Generate Diffusion Model (RnG) Our method leverages a reconstructive denoising network to recover the majority of the underlying clean signal. It employs a diffusion algorithm to generate residual high-frequency details, thereby enhancing visual quality.
  arXiv  Detail & Related papers  (2023-09-19T16:01:20Z)
• ACDMSR: Accelerated Conditional Diffusion Models for Single Image Super-Resolution [84.73658185158222]
  We propose a diffusion model-based super-resolution method called ACDMSR. Our method adapts the standard diffusion model to perform super-resolution through a deterministic iterative denoising process. Our approach generates more visually realistic counterparts for low-resolution images, emphasizing its effectiveness in practical scenarios.
  arXiv  Detail & Related papers  (2023-07-03T06:49:04Z)
• RBSR: Efficient and Flexible Recurrent Network for Burst Super-Resolution [57.98314517861539]
  Burst super-resolution (BurstSR) aims at reconstructing a high-resolution (HR) image from a sequence of low-resolution (LR) and noisy images. In this paper, we suggest fusing cues frame-by-frame with an efficient and flexible recurrent network.
  arXiv  Detail & Related papers  (2023-06-30T12:14:13Z)
• Low-Light Image Enhancement with Wavelet-based Diffusion Models [50.632343822790006]
  Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration. We propose a robust and efficient Diffusion-based Low-Light image enhancement approach, dubbed DiffLL.
  arXiv  Detail & Related papers  (2023-06-01T03:08:28Z)
• Frequency Consistent Adaptation for Real World Super Resolution [64.91914552787668]
  We propose a novel Frequency Consistent Adaptation (FCA) that ensures the frequency domain consistency when applying Super-Resolution (SR) methods to the real scene. We estimate degradation kernels from unsupervised images and generate the corresponding Low-Resolution (LR) images. Based on the domain-consistent LR-HR pairs, we train easy-implemented Convolutional Neural Network (CNN) SR models.
  arXiv  Detail & Related papers  (2020-12-18T08:25:39Z)
• Characteristic Regularisation for Super-Resolving Face Images [81.84939112201377]
  Existing facial image super-resolution (SR) methods focus mostly on improving artificially down-sampled low-resolution (LR) imagery. Previous unsupervised domain adaptation (UDA) methods address this issue by training a model using unpaired genuine LR and HR data. This renders the model overstretched with two tasks: consistifying the visual characteristics and enhancing the image resolution. We formulate a method that joins the advantages of conventional SR and UDA models.
  arXiv  Detail & Related papers  (2019-12-30T16:27:24Z)

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.