Self-Reflective Reinforcement Learning for Diffusion-based Image Reasoning Generation

• URL: http://arxiv.org/abs/2505.22407v1
• Date: Wed, 28 May 2025 14:37:21 GMT
• Title: Self-Reflective Reinforcement Learning for Diffusion-based Image Reasoning Generation
• Authors: Jiadong Pan, Zhiyuan Ma, Kaiyan Zhang, Ning Ding, Bowen Zhou,
• Abstract summary: Diffusion models have recently demonstrated exceptional performance in image generation task.<n>We propose SRRL, a self-reflective RL algorithm for diffusion models to achieve reasoning generation of logical images.
• Score: 24.247140501653547
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion models have recently demonstrated exceptional performance in image generation task. However, existing image generation methods still significantly suffer from the dilemma of image reasoning, especially in logic-centered image generation tasks. Inspired by the success of Chain of Thought (CoT) and Reinforcement Learning (RL) in LLMs, we propose SRRL, a self-reflective RL algorithm for diffusion models to achieve reasoning generation of logical images by performing reflection and iteration across generation trajectories. The intermediate samples in the denoising process carry noise, making accurate reward evaluation difficult. To address this challenge, SRRL treats the entire denoising trajectory as a CoT step with multi-round reflective denoising process and introduces condition guided forward process, which allows for reflective iteration between CoT steps. Through SRRL-based iterative diffusion training, we introduce image reasoning through CoT into generation tasks adhering to physical laws and unconventional physical phenomena for the first time. Notably, experimental results of case study exhibit that the superior performance of our SRRL algorithm even compared with GPT-4o. The project page is https://jadenpan0.github.io/srrl.github.io/.

Related papers

• 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)
• 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)
• One-Step Effective Diffusion Network for Real-World Image Super-Resolution [11.326598938246558]
  We propose a one-step effective diffusion network, namely OSEDiff, for the Real-ISR problem. We finetune the pre-trained diffusion network with trainable layers to adapt it to complex image degradations. Our OSEDiff model can efficiently and effectively generate HQ images in just one diffusion step.
  arXiv  Detail & Related papers  (2024-06-12T13:10:31Z)
• RL for Consistency Models: Faster Reward Guided Text-to-Image Generation [15.238373471473645]
  We propose a framework for fine-tuning consistency models viaReinforcement Learning (RL) Our framework, called Reinforcement Learning for Consistency Model (RLCM), frames the iterative inference process of a consistency model as an RL procedure. Comparing to RL finetuned diffusion models, RLCM trains significantly faster, improves the quality of the generation measured under the reward objectives, and speeds up the inference procedure by generating high quality images with as few as two inference steps.
  arXiv  Detail & Related papers  (2024-03-25T15:40:22Z)
• Iterative Token Evaluation and Refinement for Real-World Super-Resolution [77.74289677520508]
  Real-world image super-resolution (RWSR) is a long-standing problem as low-quality (LQ) images often have complex and unidentified degradations. We propose an Iterative Token Evaluation and Refinement framework for RWSR. We show that ITER is easier to train than Generative Adversarial Networks (GANs) and more efficient than continuous diffusion models.
  arXiv  Detail & Related papers  (2023-12-09T17:07:32Z)
• SinSR: Diffusion-Based Image Super-Resolution in a Single Step [119.18813219518042]
  Super-resolution (SR) methods based on diffusion models exhibit promising results. But their practical application is hindered by the substantial number of required inference steps. We propose a simple yet effective method for achieving single-step SR generation, named SinSR.
  arXiv  Detail & Related papers  (2023-11-23T16:21:29Z)
• Deep Equilibrium Diffusion Restoration with Parallel Sampling [120.15039525209106]
  Diffusion model-based image restoration (IR) aims to use diffusion models to recover high-quality (HQ) images from degraded images, achieving promising performance. Most existing methods need long serial sampling chains to restore HQ images step-by-step, resulting in expensive sampling time and high computation costs. In this work, we aim to rethink the diffusion model-based IR models through a different perspective, i.e., a deep equilibrium (DEQ) fixed point system, called DeqIR.
  arXiv  Detail & Related papers  (2023-11-20T08:27:56Z)
• Deep Variational Network Toward Blind Image Restoration [60.45350399661175]
  Blind image restoration is a common yet challenging problem in computer vision. We propose a novel blind image restoration method, aiming to integrate both the advantages of them. Experiments on two typical blind IR tasks, namely image denoising and super-resolution, demonstrate that the proposed method achieves superior performance over current state-of-the-arts.
  arXiv  Detail & Related papers  (2020-08-25T03:30:53Z)
• 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.