发表机构
Khulna University of Engineering & Technology (KUET)（库尔纳工程技术大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
AutoLumNet是首个结合结构单调性、最优传输最优性与有界局部适应性的单帧曝光校正框架，在五个基准上实现最优PSNR、SSIM，每帧处理11.2毫秒且可零样本泛化至低光场景。
AI 中文摘要
单帧曝光校正旨在将任意退化图像（无论是曝光不足、曝光过度，还是两者的空间混合）从单次采集映射到曝光良好的输出。我们提出AutoLumNet，该框架将此任务分解为全局单调色调曲线和有界局部残差，使全局组件成为形式保证的轨迹。色调曲线被参数化为严格正密度的归一化累积积分，通过构造而非惩罚确保严格单调性。我们证明，该参数化（i）无条件保留所有像素的成对亮度排序和所有空间极值，（ii）在有效色调校正空间中是稠密的，包含从输入到任何目标亮度分布的一维最优传输（OT）映射。可微的排序样本Wasserstein-2目标在训练期间驱动学习曲线向OT最优方向发展。全局映射可证明无法处理的空间变化效应——局部阴影、色度偏移和裁剪区域恢复——由具有双分支凸融合的有界残差解码器处理，我们为此提供了局部排序保留的显式充分条件。在五个基准（MSEC、SICE、LCDP、LOL-v1、LOL-v2-real）上的实验表明，AutoLumNet在曝光不足和曝光过度场景下均达到了最先进的PSNR和SSIM，每帧处理时间为11.2毫秒，且无需重新训练即可零样本泛化到纯低光基准。据我们所知，AutoLumNet是首个在单个可训练架构中结合结构单调性、最优传输最优性和有界局部适应性的曝光校正方法。代码可在该https URL获取。
英文摘要
Single-shot exposure correction aims to map an arbitrarily degraded image---whether under-exposed, over-exposed, or a spatial mixture of both---to a well-exposed output from a single capture. We present AutoLumNet, a framework that decomposes this task into a global monotone tone curve and a bounded local residual, making the global component the locus of formal guarantees. The tone curve is parameterized as the normalized cumulative integral of a strictly positive density, ensuring strict monotonicity by construction rather than by penalty. We prove that this parameterization (i)~preserves the pairwise luminance ordering of all pixels and all spatial extrema unconditionally, and (ii)~is dense in the space of valid tone corrections, containing the one-dimensional optimal-transport map from the input to any target luminance distribution. A differentiable sorted-sample Wasserstein-2 objective drives the learned curve toward the OT optimum during training. Spatially varying effects that the global map provably cannot address---local shading, chrominance shifts, and clipped-region restoration---are handled by a bounded residual decoder with dual-branch convex fusion, for which we provide an explicit sufficient condition for local order preservation. Experiments on five benchmarks (MSEC, SICE, LCDP, LOL-v1, LOL-v2-real) show that AutoLumNet achieves state-of-the-art PSNR and SSIM across both under- and over-exposure regimes at 11.2\,ms per frame, and generalizes zero-shot to pure low-light benchmarks without retraining. To our knowledge, AutoLumNet is the first exposure-correction method to unite structural monotonicity, optimal-transport optimality, and bounded local adaptivity within a single trainable architecture. Code is available at https://github.com/kraihan/Autolumnet.
