From Enhancement to Understanding: Build a Generalized Bridge for Low-light Vision via Semantically Consistent Unsupervised Fine-tuning

• URL: http://arxiv.org/abs/2507.08380v1
• Date: Fri, 11 Jul 2025 07:51:26 GMT
• Title: From Enhancement to Understanding: Build a Generalized Bridge for Low-light Vision via Semantically Consistent Unsupervised Fine-tuning
• Authors: Sen Wang, Shao Zeng, Tianjun Gu, Zhizhong Zhang, Ruixin Zhang, Shouhong Ding, Jingyun Zhang, Jun Wang, Xin Tan, Yuan Xie, Lizhuang Ma,
• Abstract summary: Low-light enhancement improves image quality for downstream tasks, but existing methods rely on physical or geometric priors.<n>We build a generalized bridge between low-light enhancement and low-light understanding, which we term Generalized Enhancement For Understanding (GEFU)<n>To address the diverse causes of low-light degradation, we leverage pretrained generative diffusion models to optimize images, achieving zero-shot generalization performance.
• Score: 65.94580484237737
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Low-level enhancement and high-level visual understanding in low-light vision have traditionally been treated separately. Low-light enhancement improves image quality for downstream tasks, but existing methods rely on physical or geometric priors, limiting generalization. Evaluation mainly focuses on visual quality rather than downstream performance. Low-light visual understanding, constrained by scarce labeled data, primarily uses task-specific domain adaptation, which lacks scalability. To address these challenges, we build a generalized bridge between low-light enhancement and low-light understanding, which we term Generalized Enhancement For Understanding (GEFU). This paradigm improves both generalization and scalability. To address the diverse causes of low-light degradation, we leverage pretrained generative diffusion models to optimize images, achieving zero-shot generalization performance. Building on this, we propose Semantically Consistent Unsupervised Fine-tuning (SCUF). Specifically, to overcome text prompt limitations, we introduce an illumination-aware image prompt to explicitly guide image generation and propose a cycle-attention adapter to maximize its semantic potential. To mitigate semantic degradation in unsupervised training, we propose caption and reflectance consistency to learn high-level semantics and image-level spatial semantics. Extensive experiments demonstrate that our proposed method outperforms current state-of-the-art methods in traditional image quality and GEFU tasks including classification, detection, and semantic segmentation.

Related papers

• SAIGFormer: A Spatially-Adaptive Illumination-Guided Network for Low-Light Image Enhancement [58.79901582809091]
  Recent Transformer-based low-light enhancement methods have made promising progress in recovering global illumination.<n>Recent Transformer-based low-light enhancement methods have made promising progress in recovering global illumination.<n>We present a Spatially-Adaptive Illumination-Guided Transformer framework that enables accurate illumination restoration.
  arXiv  Detail & Related papers  (2025-07-21T11:38:56Z)
• A Multi-Scale Spatial Attention-Based Zero-Shot Learning Framework for Low-Light Image Enhancement [3.55026004901472]
  LucentVisionNet is a novel zero-shot learning framework for low-light image enhancement.<n>Our framework achieves high visual quality, structural consistency, and computational efficiency.<n>It is well-suited for deployment in real-world applications such as mobile photography, surveillance, and autonomous navigation.
  arXiv  Detail & Related papers  (2025-06-23T06:11:55Z)
• 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.<n>We propose to improve the existing zero-reference low-light enhancement by leveraging the CLIP model to capture image prior and for semantic guidance.<n>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)
• 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)
• ALEN: A Dual-Approach for Uniform and Non-Uniform Low-Light Image Enhancement [10.957431540794836]
  Inadequate illumination can lead to significant information loss and poor image quality, impacting various applications such as surveillance.<n>Current enhancement techniques often use specific datasets to enhance low-light images, but still present challenges when adapting to diverse real-world conditions.<n>The Adaptive Light Enhancement Network (ALEN) is introduced, whose main approach is the use of a classification mechanism to determine whether local or global illumination enhancement is required.
  arXiv  Detail & Related papers  (2024-07-29T05:19:23Z)
• 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)
• Zero-Reference Lighting Estimation Diffusion Model for Low-Light Image Enhancement [2.9873893715462185]
  We propose a novel zero-reference lighting estimation diffusion model for low-light image enhancement called Zero-LED.<n>It utilizes the stable convergence ability of diffusion models to bridge the gap between low-light domains and real normal-light domains.<n>It successfully alleviates the dependence on pairwise training data via zero-reference learning.
  arXiv  Detail & Related papers  (2024-03-05T11:39:17Z)
• Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement [69.47143451986067]
  Low-light image enhancement (LLIE) investigates how to improve illumination and produce normal-light images. The majority of existing methods improve low-light images via a global and uniform manner, without taking into account the semantic information of different regions. We propose a novel semantic-aware knowledge-guided framework that can assist a low-light enhancement model in learning rich and diverse priors encapsulated in a semantic segmentation model.
  arXiv  Detail & Related papers  (2023-04-14T10:22:28Z)
• Self-Aligned Concave Curve: Illumination Enhancement for Unsupervised Adaptation [36.050270650417325]
  We propose a learnable illumination enhancement model for high-level vision. Inspired by real camera response functions, we assume that the illumination enhancement function should be a concave curve. Our model architecture and training designs mutually benefit each other, forming a powerful unsupervised normal-to-low light adaptation framework.
  arXiv  Detail & Related papers  (2022-10-07T19:32:55Z)
• 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.