Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design

• URL: http://arxiv.org/abs/2504.14075v1
• Date: Fri, 18 Apr 2025 20:57:16 GMT
• Title: Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design
• Authors: Wei Dong, Yan Min, Han Zhou, Jun Chen,
• Abstract summary: Current Low-light Image Enhancement (LLIE) techniques rely on either direct Low-Light (LL) to Normal-Light (NL) mappings or guidance from semantic features or illumination maps.<n>We present SG-LLIE, a new multi-scale CNN-Transformer hybrid framework guided by structure priors.<n>Our solution ranks second in the NTIRE 2025 Low-Light Enhancement Challenge.
• Score: 13.587511215001115
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current Low-light Image Enhancement (LLIE) techniques predominantly rely on either direct Low-Light (LL) to Normal-Light (NL) mappings or guidance from semantic features or illumination maps. Nonetheless, the intrinsic ill-posedness of LLIE and the difficulty in retrieving robust semantics from heavily corrupted images hinder their effectiveness in extremely low-light environments. To tackle this challenge, we present SG-LLIE, a new multi-scale CNN-Transformer hybrid framework guided by structure priors. Different from employing pre-trained models for the extraction of semantics or illumination maps, we choose to extract robust structure priors based on illumination-invariant edge detectors. Moreover, we develop a CNN-Transformer Hybrid Structure-Guided Feature Extractor (HSGFE) module at each scale with in the UNet encoder-decoder architecture. Besides the CNN blocks which excels in multi-scale feature extraction and fusion, we introduce a Structure-Guided Transformer Block (SGTB) in each HSGFE that incorporates structural priors to modulate the enhancement process. Extensive experiments show that our method achieves state-of-the-art performance on several LLIE benchmarks in both quantitative metrics and visual quality. Our solution ranks second in the NTIRE 2025 Low-Light Enhancement Challenge. Code is released at https://github.com/minyan8/imagine.

Related papers

• DLEN: Dual Branch of Transformer for Low-Light Image Enhancement in Dual Domains [0.0]
  Low-light image enhancement (LLE) aims to improve the visual quality of images captured in poorly lit conditions.<n>These issues hinder the performance of computer vision tasks such as object detection, facial recognition, and autonomous driving.<n>We propose the Dual Light Enhance Network (DLEN), a novel architecture that incorporates two distinct attention mechanisms.
  arXiv  Detail & Related papers  (2025-01-21T15:58:16Z)
• GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval [80.96706764868898]
  We present a new Low-light Image Enhancement (LLIE) network via Generative LAtent feature based codebook REtrieval (GLARE) We develop a generative Invertible Latent Normalizing Flow (I-LNF) module to align the LL feature distribution to NL latent representations, guaranteeing the correct code retrieval in the codebook. Experiments confirm the superior performance of GLARE on various benchmark datasets and real-world data.
  arXiv  Detail & Related papers  (2024-07-17T09:40:15Z)
• Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT [120.39362661689333]
  We present an improved version of Lumina-T2X, showcasing stronger generation performance with increased training and inference efficiency. Thanks to these improvements, Lumina-Next not only improves the quality and efficiency of basic text-to-image generation but also demonstrates superior resolution extrapolation capabilities.
  arXiv  Detail & Related papers  (2024-06-05T17:53:26Z)
• 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)
• VQCNIR: Clearer Night Image Restoration with Vector-Quantized Codebook [16.20461368096512]
  Night photography often struggles with challenges like low light and blurring, stemming from dark environments and prolonged exposures. We believe in the strength of data-driven high-quality priors and strive to offer a reliable and consistent prior, circumventing the restrictions of manual priors. We propose Clearer Night Image Restoration with Vector-Quantized Codebook (VQCNIR) to achieve remarkable and consistent restoration outcomes on real-world and synthetic benchmarks.
  arXiv  Detail & Related papers  (2023-12-14T02:16:27Z)
• Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement [96.09255345336639]
  We formulate a principled One-stage Retinex-based Framework (ORF) to enhance low-light images. ORF first estimates the illumination information to light up the low-light image and then restores the corruption to produce the enhanced image. Our algorithm, Retinexformer, significantly outperforms state-of-the-art methods on thirteen benchmarks.
  arXiv  Detail & Related papers  (2023-03-12T16:54:08Z)
• Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method [51.30748775681917]
  We consider the task of low-light image enhancement (LLIE) and introduce a large-scale database consisting of images at 4K and 8K resolution. We conduct systematic benchmarking studies and provide a comparison of current LLIE algorithms. As a second contribution, we introduce LLFormer, a transformer-based low-light enhancement method.
  arXiv  Detail & Related papers  (2022-12-22T09:05:07Z)
• Toward Fast, Flexible, and Robust Low-Light Image Enhancement [87.27326390675155]
  We develop a new Self-Calibrated Illumination (SCI) learning framework for fast, flexible, and robust brightening images in real-world low-light scenarios. Considering the computational burden of the cascaded pattern, we construct the self-calibrated module which realizes the convergence between results of each stage. We make comprehensive explorations to SCI's inherent properties including operation-insensitive adaptability and model-irrelevant generality.
  arXiv  Detail & Related papers  (2022-04-21T14:40:32Z)
• Learning Deep Context-Sensitive Decomposition for Low-Light Image Enhancement [58.72667941107544]
  A typical framework is to simultaneously estimate the illumination and reflectance, but they disregard the scene-level contextual information encapsulated in feature spaces. We develop a new context-sensitive decomposition network architecture to exploit the scene-level contextual dependencies on spatial scales. We develop a lightweight CSDNet (named LiteCSDNet) by reducing the number of channels.
  arXiv  Detail & Related papers  (2021-12-09T06:25:30Z)

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.