用于低光图像增强中可靠强度-色度融合的阈值交叉注意力
Thresholded Cross-Attention for Reliable Intensity-Chromaticity Fusion in Low-Light Image Enhancement
另 2 家 · 查看机构详情
- School of Information Engineering, Guangdong University of Technology（广东工业大学信息工程学院）
- School of Computer Science, Wuhan University（武汉大学计算机科学学院）
- Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
- Department of Computer Science, University of Macau（澳门大学计算机科学系）
- Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
研究低光图像增强中强度与色度融合问题，提出TCA-Net网络，核心为阈值交叉注意力，通过固定置信度阈值自适应保留高置信度跨流交互，还有互补设计及正则化，实验证明该网络在恢复精度、颜色保真度和参数大小方面表现出色。
中文摘要 AI 辅助
低光图像增强需要在噪声抑制、颜色保真度和效率之间谨慎平衡。基于HVI的方法通过解耦强度和色度来减轻颜色纠缠，但两流再次融合的可靠性是一个被忽视的因素，很大程度上决定了最终质量。我们发现跨流注意力的置信度强烈依赖层，因此Top-K稀疏注意力的固定配额选择与之不匹配。基于此，我们提出TCA-Net，围绕阈值交叉注意力构建，以在HVI空间中实现可靠的强度-色度融合。其核心是用固定置信度阈值取代刚性Top-K配额，保留高置信度跨流交互。此外还有两个互补设计以及尺度感知一致性正则化。实验表明TCA-Net具有竞争力的恢复精度、更高的颜色保真度和紧凑的参数大小。
英文摘要
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.
