通过SDR融合与增益图逆色调映射实现双输出多曝光HDR重建
Dual-Output Multi-Exposure HDR Reconstruction via SDR Fusion and Gain Map Inverse Tone Mapping
浏览论文内容
中文总结 AI 辅助
该研究提出DOME-HDR框架，通过LoRA适配的潜在扩散模型与双交叉注意力融合模块生成SDR，结合HPGM网络预测增益图实现多曝光HDR重建，在多个数据集上达到最优性能。
中文摘要 AI 辅助
我们提出了DOME-HDR，一种双输出多曝光HDR重建框架，可通过增益图逆色调映射同时生成感知平衡的SDR图像和一致的HDR图像。给定三张 bracketed LDR输入图像，DOME-HDR首先使用LoRA适配的潜在扩散模型合成基础SDR。双交叉注意力融合模块从欠曝光和过曝光图像中注入互补的结构与颜色线索，同时以中曝光图像为锚定以保证稳定性。合成的SDR随后指导HPGM（我们的HDR先验引导增益图网络）预测空间变化的增益图，以实现可靠的动态范围扩展。我们在Kalantari、Tel和Challenge123数据集上使用全参考和无参考指标进行评估，DOME-HDR实现了最先进的HDR重建质量； ablation研究进一步证实了双交叉注意力和SDR引导增益图估计的有效性。
英文摘要
We propose DOME-HDR, a dual-output multi-exposure HDR reconstruction framework that jointly produces a perceptually balanced SDR image and a consistent HDR image via gain map inverse tone mapping. Given three bracketed LDR inputs, DOME-HDR first synthesizes a base SDR using a LoRA-adapted latent diffusion model. A dual cross-attention fusion module injects complementary structural and color cues from the under- and over-exposed images while anchoring on the mid exposure for stability. The synthesized SDR then guides HPGM, our HDR Prior-guided Gain Map network, to predict a spatially varying gain map for reliable dynamic-range expansion. We evaluate on Kalantari, Tel, and Challenge123 using both full-reference and no-reference metrics, where DOME-HDR achieves state-of-the-art HDR reconstruction quality; ablations further confirm the effectiveness of dual cross-attention and SDR-guided gain map estimation.
发表机构
- Yonsei University（延世大学）
机构由 AI 辅助整理，请以论文原文为准。
