Zero-Shot Low Light Image Enhancement with Diffusion Prior

• URL: http://arxiv.org/abs/2412.13401v4
• Date: Mon, 24 Mar 2025 00:01:58 GMT
• Title: Zero-Shot Low Light Image Enhancement with Diffusion Prior
• Authors: Joshua Cho, Sara Aghajanzadeh, Zhen Zhu, D. A. Forsyth,
• Abstract summary: "Free lunch" solution for low-light image enhancement (LLIE)<n>We leverage a pre-trained text-to-image diffusion prior, learned from training on a large collection of natural images, and the features present in the model itself to guide the inference.
• Score: 2.102429358229889
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we present a simple yet highly effective "free lunch" solution for low-light image enhancement (LLIE), which aims to restore low-light images as if acquired in well-illuminated environments. Our method necessitates no optimization, training, fine-tuning, text conditioning, or hyperparameter adjustments, yet it consistently reconstructs low-light images with superior fidelity. Specifically, we leverage a pre-trained text-to-image diffusion prior, learned from training on a large collection of natural images, and the features present in the model itself to guide the inference, in contrast to existing methods that depend on customized constraints. Comprehensive quantitative evaluations demonstrate that our approach outperforms SOTA methods on established datasets, while qualitative analyses indicate enhanced color accuracy and the rectification of subtle chromatic deviations. Furthermore, additional experiments reveal that our method, without any modifications, achieves SOTA-comparable performance in the auto white balance (AWB) task.

Related papers

• Leveraging Content and Context Cues for Low-Light Image Enhancement [25.97198463881292]
  Low-light conditions have an adverse impact on machine cognition, limiting the performance of computer vision systems in real life. We propose to improve the existing zero-reference low-light enhancement by leveraging the CLIP model to capture image prior and for semantic guidance. We experimentally show, that the proposed prior and semantic guidance help to improve the overall image contrast and hue, as well as improve background-foreground discrimination.
  arXiv  Detail & Related papers  (2024-12-10T17:32:09Z)
• CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement [97.95330185793358]
  Low-light image enhancement (LLIE) aims to improve low-illumination images. Existing methods face two challenges: uncertainty in restoration from diverse brightness degradations and loss of texture and color information. We propose a novel enhancement approach, CodeEnhance, by leveraging quantized priors and image refinement.
  arXiv  Detail & Related papers  (2024-04-08T07:34:39Z)
• Revealing Shadows: Low-Light Image Enhancement Using Self-Calibrated Illumination [4.913568097686369]
  Self-Calibrated Illumination (SCI) is a strategy initially developed for RGB images. We employ the SCI method to intensify and clarify details that are typically lost in low-light conditions. This method of selective illumination enhancement leaves the color information intact, thus preserving the color integrity of the image.
  arXiv  Detail & Related papers  (2023-12-23T08:49:19Z)
• Dimma: Semi-supervised Low Light Image Enhancement with Adaptive Dimming [0.728258471592763]
  Enhancing low-light images while maintaining natural colors is a challenging problem due to camera processing variations. We propose Dimma, a semi-supervised approach that aligns with any camera by utilizing a small set of image pairs. We achieve that by introducing a convolutional mixture density network that generates distorted colors of the scene based on the illumination differences.
  arXiv  Detail & Related papers  (2023-10-14T17:59:46Z)
• Joint Correcting and Refinement for Balanced Low-Light Image Enhancement [26.399356992450763]
  A novel structure is proposed which can balance brightness, color, and illumination more effectively. Joint Correcting and Refinement Network (JCRNet) mainly consists of three stages to balance brightness, color, and illumination of enhancement.
  arXiv  Detail & Related papers  (2023-09-28T03:16:45Z)
• LUT-GCE: Lookup Table Global Curve Estimation for Fast Low-light Image Enhancement [62.17015413594777]
  We present an effective and efficient approach for low-light image enhancement, named LUT-GCE. We estimate a global curve for the entire image that allows corrections for both under- and over-exposure. Our approach outperforms the state of the art in terms of inference speed, especially on high-definition images (e.g., 1080p and 4k)
  arXiv  Detail & Related papers  (2023-06-12T12:53:06Z)
• Diffusion in the Dark: A Diffusion Model for Low-Light Text Recognition [78.50328335703914]
  Diffusion in the Dark (DiD) is a diffusion model for low-light image reconstruction for text recognition. We demonstrate that DiD, without any task-specific optimization, can outperform SOTA low-light methods in low-light text recognition on real images.
  arXiv  Detail & Related papers  (2023-03-07T23:52:51Z)
• Designing An Illumination-Aware Network for Deep Image Relighting [69.750906769976]
  We present an Illumination-Aware Network (IAN) which follows the guidance from hierarchical sampling to progressively relight a scene from a single image. In addition, an Illumination-Aware Residual Block (IARB) is designed to approximate the physical rendering process. Experimental results show that our proposed method produces better quantitative and qualitative relighting results than previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-07-21T16:21:24Z)
• Semi-supervised atmospheric component learning in low-light image problem [0.0]
  Ambient lighting conditions play a crucial role in determining the perceptual quality of images from photographic devices. This study presents a semi-supervised training method using no-reference image quality metrics for low-light image restoration.
  arXiv  Detail & Related papers  (2022-04-15T17:06:33Z)
• Invertible Network for Unpaired Low-light Image Enhancement [78.33382003460903]
  We propose to leverage the invertible network to enhance low-light image in forward process and degrade the normal-light one inversely with unpaired learning. In addition to the adversarial loss, we design various loss functions to ensure the stability of training and preserve more image details. We present a progressive self-guided enhancement process for low-light images and achieve favorable performance against the SOTAs.
  arXiv  Detail & Related papers  (2021-12-24T17:00:54Z)
• 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)
• Low-light Image Enhancement Using the Cell Vibration Model [12.400040803969501]
  Low light very likely leads to the degradation of an image's quality and even causes visual task failures. We propose a new single low-light image lightness enhancement method. Experimental results show that the proposed algorithm is superior to nine state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-06-03T13:39:10Z)
• Unsupervised Low-light Image Enhancement with Decoupled Networks [103.74355338972123]
  We learn a two-stage GAN-based framework to enhance the real-world low-light images in a fully unsupervised fashion. Our proposed method outperforms the state-of-the-art unsupervised image enhancement methods in terms of both illumination enhancement and noise reduction.
  arXiv  Detail & Related papers  (2020-05-06T13:37:08Z)

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.