P-PatchDiff: Progressive Patch Diffusion Models for Low-light Image Enhancement

• URL: http://arxiv.org/abs/2609.01123v1
• Date: Tue, 01 Sep 2026 12:01:17 GMT
• Title: P-PatchDiff: Progressive Patch Diffusion Models for Low-light Image Enhancement
• Abstract summary: We propose P-PatchDiff, a scalable progressive patch diffusion framework for low-light image enhancement.<n>It dynamically adjusts patch size throughout the denoising process, enabling a gradual shift from local to global views.<n>We empirically demonstrate that P-PatchDiff effectively enhances images ranging from 400 $times$ 600 to 4K.
• Score: 16.721528049675424
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent advancements in low-light image enhancement have leveraged diffusion models for their strong ability to generate perceptually realistic, detailed images. Patch diffusion models further offer a promising solution to size-agnostic image restoration while improving efficiency. However, existing methods typically rely on small, fixed patches (e.g., 64$\times$64) that cannot capture image-level brightness context, whereas enlarging the receptive field improves brightness and colour estimation but substantially increases computational cost. Moreover, low-light images often exhibit uneven brightness across regions, making it necessary to ensure that locally enhanced patches remain visually coherent when combined into the full image. To address these limitations, we propose P-PatchDiff, a scalable progressive patch diffusion framework for low-light image enhancement that dynamically adjusts patch size throughout the denoising process, enabling a gradual shift from local to global views. A Multi-Patch Alignment strategy is also introduced to normalise features across varying patch scales using an estimated global brightness proxy. Rather than pursuing pixel-level reconstruction accuracy, P-PatchDiff focuses on scalability and coherent brightness across the whole image, allowing the model to perceive multi-scale information and better enhance regions with varying brightness. We empirically demonstrate that P-PatchDiff effectively enhances images ranging from 400 $\times$ 600 to 4K and is 80$\times$ faster than existing patch diffusion models while using less than 9GB of memory. The code is available at https://github.com/RuoyuGuo/P-PatchDiff.

Related papers

• MOSAIK: Multi-Patch Content-Aware Spatial Allocation of Image Tokens for Efficient Generation [26.941280093248263]
  MOSAIK is a damage-guided framework that varies patch size across regions and denoising steps.<n>Our approach delivers highly competitive performance at moderate budgets.
  arXiv  Detail & Related papers  (2026-08-05T22:52:41Z)
• APT: Improving Diffusion Models for High Resolution Image Generation with Adaptive Path Tracing [24.33819371470651]
  Latent Diffusion Models (LDMs) are generally trained at fixed resolutions, limiting their capability when scaling to high-resolution images.<n>We propose Adaptive Path Tracing (APT), a framework that combines Statistical Matching to ensure patch distributions remain consistent.<n>As a result, APT produces clearer and more refined details in high-resolution images.
  arXiv  Detail & Related papers  (2025-07-29T11:13:03Z)
• Unveiling Advanced Frequency Disentanglement Paradigm for Low-Light Image Enhancement [61.22119364400268]
  We propose a novel low-frequency consistency method, facilitating improved frequency disentanglement optimization. Noteworthy improvements are showcased across five popular benchmarks, with up to 7.68dB gains on PSNR achieved for six state-of-the-art models. Our approach maintains efficiency with only 88K extra parameters, setting a new standard in the challenging realm of low-light image enhancement.
  arXiv  Detail & Related papers  (2024-09-03T06:19:03Z)
• PatchScaler: An Efficient Patch-Independent Diffusion Model for Image Super-Resolution [44.345740602726345]
  PatchScaler is an efficient patch-independent diffusion pipeline for single image super-resolution. A texture prompt adaptively retrieves texture priors for the target patch from a common reference texture memory. Our code achieves superior performance in both quantitative and qualitative evaluations, while significantly speeding up inference.
  arXiv  Detail & Related papers  (2024-05-27T13:31:46Z)
• CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement [97.95330185793358]
  Low-light image enhancement (LLIE) aims to improve low-illumination images.<n>Existing methods face two challenges: uncertainty in restoration from diverse brightness degradations and loss of texture and color information.<n>We propose a novel enhancement approach, CodeEnhance, by leveraging quantized priors and image refinement.
  arXiv  Detail & Related papers  (2024-04-08T07:34:39Z)
• A Non-Uniform Low-Light Image Enhancement Method with Multi-Scale Attention Transformer and Luminance Consistency Loss [11.585269110131659]
  Low-light image enhancement aims to improve the perception of images collected in dim environments. Existing methods cannot adaptively extract the differentiated luminance information, which will easily cause over-exposure and under-exposure. We propose a multi-scale attention Transformer named MSATr, which sufficiently extracts local and global features for light balance to improve the visual quality.
  arXiv  Detail & Related papers  (2023-12-27T10:07:11Z)
• Global Structure-Aware Diffusion Process for Low-Light Image Enhancement [64.69154776202694]
  This paper studies a diffusion-based framework to address the low-light image enhancement problem. We advocate for the regularization of its inherent ODE-trajectory. Experimental evaluations reveal that the proposed framework attains distinguished performance in low-light enhancement.
  arXiv  Detail & Related papers  (2023-10-26T17:01:52Z)
• Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network [69.96295927854042]
  Low-light environments usually lead to less informative large-scale dark areas. We propose to integrate the effectiveness of gamma correction with the strong modelling capacities of deep networks. Because exponential operation introduces high computational complexity, we propose to use Taylor Series to approximate gamma correction.
  arXiv  Detail & Related papers  (2023-08-16T08:46:51Z)
• CERL: A Unified Optimization Framework for Light Enhancement with Realistic Noise [81.47026986488638]
  Low-light images captured in the real world are inevitably corrupted by sensor noise. Existing light enhancement methods either overlook the important impact of real-world noise during enhancement, or treat noise removal as a separate pre- or post-processing step. We present Coordinated Enhancement for Real-world Low-light Noisy Images (CERL), that seamlessly integrates light enhancement and noise suppression parts into a unified and physics-grounded framework.
  arXiv  Detail & Related papers  (2021-08-01T15:31:15Z)
• Degrade is Upgrade: Learning Degradation for Low-light Image Enhancement [52.49231695707198]
  We investigate the intrinsic degradation and relight the low-light image while refining the details and color in two steps. Inspired by the color image formulation, we first estimate the degradation from low-light inputs to simulate the distortion of environment illumination color, and then refine the content to recover the loss of diffuse illumination color. Our proposed method has surpassed the SOTA by 0.95dB in PSNR on LOL1000 dataset and 3.18% in mAP on ExDark dataset.
  arXiv  Detail & Related papers  (2021-03-19T04:00:27Z)

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.