Step-level Reward for Free in RL-based T2I Diffusion Model Fine-tuning

• URL: http://arxiv.org/abs/2505.19196v1
• Date: Sun, 25 May 2025 15:43:54 GMT
• Title: Step-level Reward for Free in RL-based T2I Diffusion Model Fine-tuning
• Authors: Xinyao Liao, Wei Wei, Xiaoye Qu, Yu Cheng,
• Abstract summary: Recent advances in text-to-image (T2I) diffusion model fine-tuning leverage reinforcement learning (RL) to align generated images with learnable reward functions.<n>Existing approaches reformulate denoising as a Markov decision process for RL-driven optimization.<n>We propose a credit assignment framework that dynamically distributes dense rewards across denoising steps.
• Score: 23.02076024811612
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in text-to-image (T2I) diffusion model fine-tuning leverage reinforcement learning (RL) to align generated images with learnable reward functions. The existing approaches reformulate denoising as a Markov decision process for RL-driven optimization. However, they suffer from reward sparsity, receiving only a single delayed reward per generated trajectory. This flaw hinders precise step-level attribution of denoising actions, undermines training efficiency. To address this, we propose a simple yet effective credit assignment framework that dynamically distributes dense rewards across denoising steps. Specifically, we track changes in cosine similarity between intermediate and final images to quantify each step's contribution on progressively reducing the distance to the final image. Our approach avoids additional auxiliary neural networks for step-level preference modeling and instead uses reward shaping to highlight denoising phases that have a greater impact on image quality. Our method achieves 1.25 to 2 times higher sample efficiency and better generalization across four human preference reward functions, without compromising the original optimal policy.

Related papers

• Two-Stage Random Alternation Framework for One-Shot Pansharpening [12.385955231193675]
  We introduce a two-stage random alternating framework (TRA-PAN) that performs instance-specific optimization for any given Multispectral(MS)/Panchromatic(PAN) pair.<n>TRA-PAN effectively integrates strong supervision constraints from reduced-resolution images with the physical characteristics of the full-resolution images.<n> Experimental results demonstrate that TRA-PAN outperforms state-of-the-art (SOTA) methods in quantitative metrics and visual quality in real-world scenarios.
  arXiv  Detail & Related papers  (2025-05-10T09:26:22Z)
• Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards [52.90573877727541]
  reinforcement learning (RL) has been considered for diffusion model fine-tuning.<n>RL's effectiveness is limited by the challenge of sparse reward.<n>$textB2text-DiffuRL$ is compatible with existing optimization algorithms.
  arXiv  Detail & Related papers  (2025-03-14T09:45:19Z)
• One-Step Diffusion Model for Image Motion-Deblurring [85.76149042561507]
  We propose a one-step diffusion model for deblurring (OSDD), a novel framework that reduces the denoising process to a single step.<n>To tackle fidelity loss in diffusion models, we introduce an enhanced variational autoencoder (eVAE), which improves structural restoration.<n>Our method achieves strong performance on both full and no-reference metrics.
  arXiv  Detail & Related papers  (2025-03-09T09:39:57Z)
• PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution [95.98801201266099]
  Diffusion-based image super-resolution (SR) models have shown superior performance at the cost of multiple denoising steps.<n>We propose a novel post-training quantization approach with adaptive scale in one-step diffusion (OSD) image SR, PassionSR.<n>Our PassionSR achieves significant advantages over recent leading low-bit quantization methods for image SR.
  arXiv  Detail & Related papers  (2024-11-26T04:49:42Z)
• Learning Efficient and Effective Trajectories for Differential Equation-based Image Restoration [59.744840744491945]
  We reformulate the trajectory optimization of this kind of method, focusing on enhancing both reconstruction quality and efficiency. We propose cost-aware trajectory distillation to streamline complex paths into several manageable steps with adaptable sizes. Experiments showcase the significant superiority of the proposed method, achieving a maximum PSNR improvement of 2.1 dB over state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-10-07T07:46:08Z)
• DGNet: Dynamic Gradient-Guided Network for Water-Related Optics Image Enhancement [77.0360085530701]
  Underwater image enhancement (UIE) is a challenging task due to the complex degradation caused by underwater environments. Previous methods often idealize the degradation process, and neglect the impact of medium noise and object motion on the distribution of image features. Our approach utilizes predicted images to dynamically update pseudo-labels, adding a dynamic gradient to optimize the network's gradient space.
  arXiv  Detail & Related papers  (2023-12-12T06:07:21Z)
• Effective Invertible Arbitrary Image Rescaling [77.46732646918936]
  Invertible Neural Networks (INN) are able to increase upscaling accuracy significantly by optimizing the downscaling and upscaling cycle jointly. A simple and effective invertible arbitrary rescaling network (IARN) is proposed to achieve arbitrary image rescaling by training only one model in this work. It is shown to achieve a state-of-the-art (SOTA) performance in bidirectional arbitrary rescaling without compromising perceptual quality in LR outputs.
  arXiv  Detail & Related papers  (2022-09-26T22:22:30Z)
• Image reconstruction algorithms in radio interferometry: from handcrafted to learned denoisers [7.1439425093981574]
  We introduce a new class of iterative image reconstruction algorithms for radio interferometry, inspired by plug-and-play methods. The approach consists in learning a prior image model by training a deep neural network (DNN) as a denoiser. We plug the learned denoiser into the forward-backward optimization algorithm, resulting in a simple iterative structure alternating a denoising step with a gradient-descent data-fidelity step.
  arXiv  Detail & Related papers  (2022-02-25T20:26:33Z)

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.