Recognition-Oriented Low-Light Image Enhancement based on Global and Pixelwise Optimization

• URL: http://arxiv.org/abs/2501.04210v1
• Date: Wed, 08 Jan 2025 01:09:49 GMT
• Title: Recognition-Oriented Low-Light Image Enhancement based on Global and Pixelwise Optimization
• Authors: Seitaro Ono, Yuka Ogino, Takahiro Toizumi, Atsushi Ito, Masato Tsukada,
• Abstract summary: We propose a novel low-light image enhancement method aimed at improving the performance of recognition models. The proposed method can be applied as a filter to improve low-light recognition performance without requiring retraining downstream recognition models.
• Score: 0.4951599300340954
• License:
• Abstract: In this paper, we propose a novel low-light image enhancement method aimed at improving the performance of recognition models. Despite recent advances in deep learning, the recognition of images under low-light conditions remains a challenge. Although existing low-light image enhancement methods have been developed to improve image visibility for human vision, they do not specifically focus on enhancing recognition model performance. Our proposed low-light image enhancement method consists of two key modules: the Global Enhance Module, which adjusts the overall brightness and color balance of the input image, and the Pixelwise Adjustment Module, which refines image features at the pixel level. These modules are trained to enhance input images to improve downstream recognition model performance effectively. Notably, the proposed method can be applied as a frontend filter to improve low-light recognition performance without requiring retraining of downstream recognition models. Experimental results demonstrate that our method improves the performance of pretrained recognition models under low-light conditions and its effectiveness.

Related papers

• Robust Low-Light Human Pose Estimation through Illumination-Texture Modulation [45.37915061527004]
  Current methods fail to provide high-quality representations due to reliance on pixel-level enhancements. We propose a frequency-based framework for low-light human pose estimation, rooted in the "divide-and-conquer" principle.
  arXiv  Detail & Related papers  (2025-01-14T11:42:54Z)
• HUPE: Heuristic Underwater Perceptual Enhancement with Semantic Collaborative Learning [62.264673293638175]
  Existing underwater image enhancement methods primarily focus on improving visual quality while overlooking practical implications. We propose a invertible network for underwater perception enhancement, dubbed H, which enhances visual quality and demonstrates flexibility in handling other downstream tasks.
  arXiv  Detail & Related papers  (2024-11-27T12:37:03Z)
• 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)
• Seed Optimization with Frozen Generator for Superior Zero-shot Low-light Enhancement [49.97304897798384]
  We embed a pre-trained generator to Retinex model to produce reflectance maps with enhanced detail and vividness. We introduce a novel optimization strategy, which backpropagates the gradients to the input seeds rather than the parameters of the low-light enhancement model. Benefiting from the pre-trained knowledge and seed-optimization strategy, the low-light enhancement model can significantly regularize the realness and fidelity of the enhanced result.
  arXiv  Detail & Related papers  (2024-02-15T04:06:18Z)
• Improving Low-Light Image Recognition Performance Based on Image-adaptive Learnable Module [0.4951599300340954]
  This study addresses the enhancement of recognition model performance in low-light conditions. We propose an image-adaptive learnable module which apply appropriate image processing on input images. Our proposed approach allows for the enhancement of recognition performance under low-light conditions by easily integrating as a front-end filter.
  arXiv  Detail & Related papers  (2024-01-12T08:18:42Z)
• LLDiffusion: Learning Degradation Representations in Diffusion Models for Low-Light Image Enhancement [118.83316133601319]
  Current deep learning methods for low-light image enhancement (LLIE) typically rely on pixel-wise mapping learned from paired data. We propose a degradation-aware learning scheme for LLIE using diffusion models, which effectively integrates degradation and image priors into the diffusion process.
  arXiv  Detail & Related papers  (2023-07-27T07:22:51Z)
• Learning a Single Convolutional Layer Model for Low Light Image Enhancement [43.411846299085575]
  Low-light image enhancement (LLIE) aims to improve the illuminance of images due to insufficient light exposure. A single convolutional layer model (SCLM) is proposed that provides global low-light enhancement as the coarsely enhanced results. Experimental results demonstrate that the proposed method performs favorably against the state-of-the-art LLIE methods in both objective metrics and subjective visual effects.
  arXiv  Detail & Related papers  (2023-05-23T13:12:00Z)
• The Loop Game: Quality Assessment and Optimization for Low-Light Image Enhancement [50.29722732653095]
  There is an increasing consensus that the design and optimization of low light image enhancement methods need to be fully driven by perceptual quality. We propose a loop enhancement framework that produces a clear picture of how the enhancement of low-light images could be optimized towards better visual quality.
  arXiv  Detail & Related papers  (2022-02-20T06:20:06Z)
• Improving Aerial Instance Segmentation in the Dark with Self-Supervised Low Light Enhancement [6.500738558466833]
  Low light conditions in aerial images adversely affect the performance of vision based applications. We propose a new method that is capable of enhancing the low light image in a self-supervised fashion. We also propose the generation of a new low light aerial dataset using GANs.
  arXiv  Detail & Related papers  (2021-02-10T12:24:40Z)
• 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.