ExpandDiff：用于单图像HDR重建的动态范围扩展扩散模型
ExpandDiff: Dynamic Range Expanding Diffusion for Single-Image HDR Reconstruction
浏览论文内容
中文总结 AI 辅助
ExpandDiff提出条件扩散流程，联合重建裁剪的阴影和高光，通过动态裁剪合成和空间自适应归一化，在SI-HDR基准上显著提升HDR重建精度。
中文摘要 AI 辅助
单图像HDR重建需要在保留LDR图像可见内容的同时推断缺失的细节。传感器动态范围和曝光差异导致LDR图像在阴影和高光区域丢失不同数量的信息。我们提出了ExpandDiff，一种条件扩散流程，可联合重建被裁剪的阴影和高光。为应对这种变化，我们引入了动态裁剪合成（DCS），在从HDR目标构建训练输入时随机采样阴影和高光裁剪百分位数。由空间自适应归一化引导的像素空间扩散模型通过有界输出头预测感知编码的HDR，在一次采样轨迹中同时重建两个裁剪方向。在SI-HDR基准上，ExpandDiff变体在PU21-PSNR上比最强评估竞争方法将HDR重建精度提高了3.43 dB，在双侧裁剪下提高了7.34 dB。代码和补充材料可在该https URL获取。
英文摘要
Single-image HDR reconstruction requires inferring missing detail while preserving the visible content of an LDR image. Differences in sensor dynamic range and exposure cause LDR images to lose varying amounts of information in shadows and highlights. We present ExpandDiff, a conditional diffusion pipeline that jointly reconstructs clipped shadows and highlights. To account for this variation, we introduce Dynamic Clipping Synthesis (DCS), which randomly samples shadow and highlight clipping percentiles when constructing training inputs from HDR targets. A pixel-space diffusion model guided by spatially-adaptive normalization then predicts perceptually encoded HDR through a bounded output head, reconstructing both clipping directions in one sampling trajectory. On the SI-HDR benchmark, ExpandDiff variants improve HDR reconstruction accuracy by 3.43 dB in PU21-PSNR over the strongest evaluated competing method, and by 7.34 dB under two-sided clipping. The code and supplementary material are available at https://memreandiran.github.io/expanddiff/.
发表机构
- EPFL（洛桑联邦理工学院）
机构由 AI 辅助整理，请以论文原文为准。
