Abstract
Images captured in nighttime scenes suffer from severely reduced visibility, hindering effective content perception. Current low-light image enhancement (LLIE) methods face significant challenges: data-driven end-to-end mapping networks lack interpretability or rely on unreliable prior guidance, struggling under extremely dark conditions, while physics-based methods depend on simplified assumptions that often fail in complex real-world scenarios. To address these limitations, we propose CIVQLLIE, a novel framework that leverages the power of discrete representation learning through causal reasoning. We achieve this through Vector Quantization (VQ), which maps continuous image features to a discrete codebook of visual tokens learned from large-scale high-quality images. This codebook serves as a reliable prior, encoding standardized brightness and color patterns that are independent of degradation. However, direct application of VQ to low-light images fails due to distribution shifts between degraded inputs and the learned codebook. Therefore, we propose a multi-level causal intervention approach to systematically correct these shifts. First, during encoding, our Pixel-level Causal Intervention (PCI) module intervenes to align low-level features with the brightness and color distributions expected by the codebook. Second, a Feature-aware Causal Intervention (FCI) mechanism with Low-frequency Selective Attention Gating (LSAG) identifies and enhances channels most affected by illumination degradation, facilitating accurate codebook token matching while enhancing the encoder's generalization performance through flexible feature-level intervention. Finally, during decoding, the High-frequency Detail Reconstruction Module (HDRM) leverages structural information preserved in the matched codebook representations to reconstruct fine details using deformable convolution techniques.
Abstract (translated)
夜间拍摄的图像由于能见度严重降低，影响了有效的内容感知。目前的低光图像增强（LLIE）方法面临重大挑战：数据驱动的端到端映射网络缺乏可解释性或依赖于不可靠的先验指导，在极其黑暗的情况下表现不佳；而基于物理的方法则依赖过于简化的假设，往往在复杂的现实世界场景中失效。为了解决这些局限性，我们提出了CIVQLLIE这一新框架，它通过因果推理利用离散表示学习的力量。我们通过向量量化（VQ）实现这一点，该技术将连续的图像特征映射到从大规模高质量图片中学得的视觉标记代码本中。这个代码本作为可靠的先验知识存在，编码了标准化的亮度和颜色模式，并且不受降质影响。 然而，直接将VQ应用于低光图像会导致受损输入与学习到的代码本之间的分布偏移问题。因此，我们提出了一种多层次因果干预的方法来系统地纠正这些偏差。首先，在编码阶段，我们的像素级因果干预（PCI）模块介入以对齐低级别特征和代码本期望的亮度及颜色分布。其次，具有低频选择性注意力门控（LSAG）的功能感知因果干预（FCI）机制识别并增强受照明降质影响最大的通道，从而促进准确的代码标记匹配，并通过灵活的功能级干预提升编码器的一般化性能。 最后，在解码阶段，高频细节重建模块（HDRM）利用在匹配代码本表示中保留的结构信息，使用可变形卷积技术来恢复精细细节。这种方法结合了数据驱动和物理模型的优势，同时避免了它们各自的缺点，为低光图像增强提供了一种新的有效途径。
URL
https://arxiv.org/abs/2508.03338
