Abstract
Deep learning-based image enhancement methods face a fundamental trade-off between computational efficiency and representational capacity. For example, although a conventional three-dimensional Look-Up Table (3D LUT) can process a degraded image in real time, it lacks representational flexibility and depends solely on a fixed prior. To address this problem, we introduce FlowLUT, a novel end-to-end model that integrates the efficiency of LUTs, multiple priors, and the parameter-independent characteristic of flow-matched reconstructed images. Specifically, firstly, the input image is transformed in color space by a collection of differentiable 3D LUTs (containing a large number of 3D LUTs with different priors). Subsequently, a lightweight content-aware dynamically predicts fusion weights, enabling scene-adaptive color correction with $\mathcal{O}(1)$ complexity. Next, a lightweight fusion prediction network runs on multiple 3D LUTs, with $\mathcal{O}(1)$ complexity for scene-adaptive color this http URL, to address the inherent representation limitations of LUTs, we design an innovative iterative flow matching method to restore local structural details and eliminate artifacts. Finally, the entire model is jointly optimized under a composite loss function enforcing perceptual and structural fidelity. Extensive experimental results demonstrate the effectiveness of our method on three benchmarks.
Abstract (translated)
基于深度学习的图像增强方法面临着计算效率和表示能力之间的基本权衡。例如，传统的三维查找表（3D LUT）可以在实时处理降质图像的同时缺乏灵活性，并且仅依赖于固定的先验条件。为了应对这一问题，我们引入了FlowLUT，这是一种新颖的端到端模型，它集成了LUTs的效率、多种先验以及流匹配重建图像的参数独立特性。 具体来说，首先输入图像通过一系列可微分的3D LUT（包含具有不同先验条件的大量3D LUT）在颜色空间中进行转换。随后，一个轻量级的内容感知模块动态地预测融合权重，以实现场景适应性的色彩校正，并且其复杂度为$\mathcal{O}(1)$。接下来，轻量级的融合预测网络运行于多个3D LUT之上，同样具有$\mathcal{O}(1)$复杂度进行场景适应性颜色处理。 此外，为了克服LUT固有的表示限制，我们设计了一种创新性的迭代流匹配方法，用于恢复局部结构细节并消除伪影。最后，整个模型在复合损失函数下共同优化该函数强制执行感知和结构保真度。广泛的实验结果证明了我们的方法在三个基准测试中的有效性。
URL
https://arxiv.org/abs/2509.23608
