Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement

• URL: http://arxiv.org/abs/2110.00970v1
• Date: Sun, 3 Oct 2021 10:07:36 GMT
• Title: Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement
• Authors: Shen Zheng, Gaurav Gupta
• Abstract summary: Low-light images challenge both human perceptions and computer vision algorithms. It is crucial to make algorithms robust to enlighten low-light images for computational photography and computer vision applications. This paper proposes a semantic-guided zero-shot low-light enhancement network which is trained in the absence of paired images.
• Score: 3.4722706398428493
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Low-light images challenge both human perceptions and computer vision algorithms. It is crucial to make algorithms robust to enlighten low-light images for computational photography and computer vision applications such as real-time detection and segmentation tasks. This paper proposes a semantic-guided zero-shot low-light enhancement network which is trained in the absence of paired images, unpaired datasets, and segmentation annotation. Firstly, we design an efficient enhancement factor extraction network using depthwise separable convolution. Secondly, we propose a recurrent image enhancement network for progressively enhancing the low-light image. Finally, we introduce an unsupervised semantic segmentation network for preserving the semantic information. Extensive experiments on various benchmark datasets and a low-light video demonstrate that our model outperforms the previous state-of-the-art qualitatively and quantitatively. We further discuss the benefits of the proposed method for low-light detection and segmentation.

Related papers

• Semi-LLIE: Semi-supervised Contrastive Learning with Mamba-based Low-light Image Enhancement [59.17372460692809]
  This work proposes a mean-teacher-based semi-supervised low-light enhancement (Semi-LLIE) framework that integrates the unpaired data into model training. We introduce a semantic-aware contrastive loss to faithfully transfer the illumination distribution, contributing to enhancing images with natural colors. We also propose novel perceptive loss based on the large-scale vision-language Recognize Anything Model (RAM) to help generate enhanced images with richer textual details.
  arXiv  Detail & Related papers  (2024-09-25T04:05:32Z)
• Unsupervised Image Prior via Prompt Learning and CLIP Semantic Guidance for Low-Light Image Enhancement [25.97198463881292]
  We propose to improve the zero-reference low-light enhancement method by leveraging the rich visual-linguistic CLIP prior. We show that the proposed method leads to consistent improvements across various datasets regarding task-based performance.
  arXiv  Detail & Related papers  (2024-05-19T08:06:14Z)
• 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)
• Zero-Shot Enhancement of Low-Light Image Based on Retinex Decomposition [4.175396687130961]
  We propose a new learning-based Retinex decomposition of zero-shot low-light enhancement method, called ZERRINNet. Our method is a zero-reference enhancement method that is not affected by the training data of paired and unpaired datasets.
  arXiv  Detail & Related papers  (2023-11-06T09:57:48Z)
• Learning Semantic Segmentation with Query Points Supervision on Aerial Images [57.09251327650334]
  We present a weakly supervised learning algorithm to train semantic segmentation algorithms. Our proposed approach performs accurate semantic segmentation and improves efficiency by significantly reducing the cost and time required for manual annotation.
  arXiv  Detail & Related papers  (2023-09-11T14:32:04Z)
• Deep Semantic Statistics Matching (D2SM) Denoising Network [70.01091467628068]
  We introduce the Deep Semantic Statistics Matching (D2SM) Denoising Network. It exploits semantic features of pretrained classification networks, then it implicitly matches the probabilistic distribution of clear images at the semantic feature space. By learning to preserve the semantic distribution of denoised images, we empirically find our method significantly improves the denoising capabilities of networks.
  arXiv  Detail & Related papers  (2022-07-19T14:35:42Z)
• Enhancing Low-Light Images in Real World via Cross-Image Disentanglement [58.754943762945864]
  We propose a new low-light image enhancement dataset consisting of misaligned training images with real-world corruptions. Our model achieves state-of-the-art performances on both the newly proposed dataset and other popular low-light datasets.
  arXiv  Detail & Related papers  (2022-01-10T03:12:52Z)
• 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)
• LEUGAN:Low-Light Image Enhancement by Unsupervised Generative Attentional Networks [4.584570928928926]
  We propose an unsupervised generation network with attention-guidance to handle the low-light image enhancement task. Specifically, our network contains two parts: an edge auxiliary module that restores sharper edges and an attention guidance module that recovers more realistic colors. Experiments validate that our proposed algorithm performs favorably against state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-12-24T16:49:19Z)
• Two-shot Spatially-varying BRDF and Shape Estimation [89.29020624201708]
  We propose a novel deep learning architecture with a stage-wise estimation of shape and SVBRDF. We create a large-scale synthetic training dataset with domain-randomized geometry and realistic materials. Experiments on both synthetic and real-world datasets show that our network trained on a synthetic dataset can generalize well to real-world images.
  arXiv  Detail & Related papers  (2020-04-01T12:56:13Z)

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.