Thresholded Cross-Attention for Reliable Intensity-Chromaticity Fusion in Low-Light Image Enhancement

• URL: http://arxiv.org/abs/2607.13925v1
• Date: Wed, 15 Jul 2026 15:06:16 GMT
• Title: Thresholded Cross-Attention for Reliable Intensity-Chromaticity Fusion in Low-Light Image Enhancement
• Abstract summary: Low-Light Image Enhancement (LLIE) requires a careful balance among noise suppression, color fidelity, and efficiency.<n>Recent HVI-based methods alleviate color entanglement by decoupling intensity and chromaticity, yet how reliably the two streams are fused again is an overlooked factor that largely determines the final quality.<n>We propose TCA-Net, a network built around Thresholded Cross-Attention that targets reliable intensity-chromaticity fusion in the HVI space.
• Score: 18.972830666871005
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Low-Light Image Enhancement (LLIE) requires a careful balance among noise suppression, color fidelity, and efficiency. Recent HVI-based methods alleviate color entanglement by decoupling intensity and chromaticity, yet how reliably the two streams are fused again is an overlooked factor that largely determines the final quality. We observe that the confidence of cross-stream attention is strongly layer-dependent, so the fixed-quota selection of Top-K sparse attention is mismatched to it, discarding informative dependencies in some layers while retaining noisy ones in others. Motivated by this observation, we propose TCA-Net, a network built around Thresholded Cross-Attention that targets reliable intensity-chromaticity fusion in the HVI space rather than introducing yet another color representation. At its core, TCA replaces the rigid Top-K quota with a fixed confidence threshold whose retained cardinality is input- and layer-adaptive, retaining only high-confidence cross-stream interactions while suppressing unreliable ones. Around this core, two complementary designs clean up the fusion before and after it: a Phase-guided Fourier Interaction Module provides a structure-aware brightness initialization for the intensity stream prior to fusion, and a Decoupled Dual-Stream Guidance Module constructs residual intensity features to suppress chromaticity leakage during reconstruction. A Scale-Aware Consistency Regularization further improves structural robustness under scale perturbations during training. Extensive experiments on LOL-v1, LOL-v2, Sony-Total-Dark, and LSRW-Huawei demonstrate that TCA-Net delivers competitive restoration accuracy, improved color fidelity, and a compact parameter size.

Related papers

• RA-SOD: Reliability-Aware RGB-T Salient Object Detection under Modality Degradation [23.43264234749439]
  We propose RA-SOD, a reliability-aware RGB-T salient object detection framework.<n> RA-SOD integrates modality reliability into feature learning and cross-modal fusion.<n>Experiments show RA-SOD achieves state-of-the-art performance and exhibits strong robustness under severe modality degradation.
  arXiv  Detail & Related papers  (2026-09-11T09:22:20Z)
• BC-IHV: Conditioning the Color Space for Stable Rectified-Flow Low-Light Enhancement [51.79298431282401]
  Low-light image enhancement must correct ambiguous exposure without overwriting structure already supported by the input.<n>We propose Structure-Anchored Rectified Flow (SA-RF), which maintains correspondence through separate chromaticity/intensity stems.<n>We also introduce BC-IHV, a learnable Box--Cox polar color space whose analytically invertible intensity mapping controls the inverse-gradient dynamic range through a single exponent.
  arXiv  Detail & Related papers  (2026-08-22T08:43:00Z)
• Overcoming Attention Drift: Homogeneity-Heterogeneity Guided Feature Aggregation for Low-Light Remote Sensing Image Enhancement [10.412281080988647]
  Under severe noise and illumination corruption, existing methods suffer from attention drift and severe structural blurring and color distortion.<n>We propose HALO, a dual-prior-driven enhancement framework that formulates enhancement as a guided feature aggregation problem driven by foundation model priors.<n>H2CAM achieves state-of-the-art performance across 8 challenging synthetic and real-world remote sensing benchmarks.
  arXiv  Detail & Related papers  (2026-08-06T10:11:36Z)
• DRPFNet: Dual-domain Residual Progressive Fusion Network for RGB-Thermal Object Detection [13.47934602159213]
  RGB-thermal (RGB-T) object detection aims to fuse complementary information from visible and thermal modalities to achieve robust detection under varying illumination and weather conditions.<n>Current methods typically employ attention mechanisms or transformers to perform cross-modal fusion independently at each feature scale.<n>We propose DRPFNet, a Dual-domain Residual Progressive Fusion Network that constructs a unified information flow optimization system from three synergistic levels:structure, feature, and enhancement.
  arXiv  Detail & Related papers  (2026-08-04T09:20:31Z)
• Beyond Illumination: A Conditional Mutual Information-Guided Network for Low-Light Image Enhancement [48.364582443938296]
  Low-light image enhancement (LLIE) seeks to restore structural fidelity, natural color rendition, and proper exposure from images captured under inadequate lighting conditions.<n>Recent state-of-the-art approaches, such as CIDNet, adopt a dual-branch architecture comprising a chrominance (HV) branch and an intensity (I) branch to separately model decoupled and luminance information within the HVI color space.<n>These methods overlook the mutual interaction between intensity and chrominance components, which inherently limits their representational capacity and leads to suboptimal enhancement performance.
  arXiv  Detail & Related papers  (2026-08-03T08:27:38Z)
• V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising [65.5867130156805]
  We present V-Co, a systematic study of visual co-denoising in a unified JiT-based framework.<n>Our study reveals four key ingredients for effective visual co-denoising.<n>V-Co outperforms the underlying pixel-space diffusion baseline and strong prior pixel-diffusion methods.
  arXiv  Detail & Related papers  (2026-03-17T17:01:54Z)
• Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark [58.61079960074608]
  Existing infrared image enhancement methods focus on tackling individual degradations.<n>All-in-one enhancement methods, commonly applied to RGB sensors, often demonstrate limited effectiveness.
  arXiv  Detail & Related papers  (2025-10-10T12:55:54Z)
• Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement [89.99237142387655]
  We introduce LH-VAE, which enhances semantic robustness through visual semantic constraints and progressive degradations.<n>Latent Harmony is a two-stage framework that redefines VAEs for UHD restoration by jointly regularizing the latent space and enforcing high-frequency-aware reconstruction.<n>Experiments show Latent Harmony achieves state-of-the-art performance across UHD and standard-resolution tasks, effectively balancing efficiency, perceptual quality, and reconstruction accuracy.
  arXiv  Detail & Related papers  (2025-10-09T08:54:26Z)
• Uncertainty-Aware Spatial Color Correlation for Low-Light Image Enhancement [5.6629926700493325]
  U2CLLIE is a novel framework that integrates uncertainty-aware enhancement and spatial-color causal correlation modeling.<n>It achieves state-of-the-art performance across multiple benchmark datasets, exhibiting robust performance and strong generalization across various scenes.
  arXiv  Detail & Related papers  (2025-08-06T08:02:21Z)
• Enhancing Diffusion Model Stability for Image Restoration via Gradient Management [25.215396311196713]
  We analyze the underlying gradient dynamics of these components and identify significant instabilities.<n>We show that these instabilities disrupt the generative process and compromise restoration performance.<n>We propose Stabilized Progressive Gradient Diffusion, a novel gradient management technique.
  arXiv  Detail & Related papers  (2025-07-09T08:40:46Z)
• EvRWKV: A Continuous Interactive RWKV Framework for Effective Event-Guided Low-Light Image Enhancement [10.556338127441167]
  Event cameras offer high dynamic range and microsecond temporal resolution by asynchronously capturing brightness changes.<n>We propose EvRWKV, a novel framework that enables continuous cross-modal interaction through dual-domain processing.<n>We show that EvRWKV achieves state-of-the-art performance, effectively enhancing image quality by suppressing noise, restoring structural details, and improving visual clarity in challenging low-light conditions.
  arXiv  Detail & Related papers  (2025-07-01T19:05:04Z)
• FUSE: Label-Free Image-Event Joint Monocular Depth Estimation via Frequency-Decoupled Alignment and Degradation-Robust Fusion [92.4205087439928]
  Image-event joint depth estimation methods leverage complementary modalities for robust perception, yet face challenges in generalizability.<n>We propose the Self-supervised Transfer (PST) and the FrequencyDe-coupled Fusion module (FreDF)<n>PST establishes cross-modal knowledge transfer through latent space alignment with image foundation models, effectively mitigating data scarcity.<n>FreDF explicitly decouples high-frequency edge features from low-frequency structural components, resolving modality-specific frequency mismatches.<n>This combined approach enables FUSE to construct a universal image-event that only requires lightweight decoder adaptation for target datasets.
  arXiv  Detail & Related papers  (2025-03-25T15:04:53Z)
• 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)

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.