用多曝光图像联合优化，提升低动态范围融合画质。
Unsupervised Learning Based Multi-Scale Exposure Fusion
- 引入新损失函数，利用同一场景的多张曝光图协同训练
- 融合图像在对比度和景深上显著优于现有方法
- 支持曝光插值与外推，适合真实场景图像增强
无监督多尺度曝光融合（ULMEF）能高效将不同曝光的低动态范围（LDR）图像融合为高质量的LDR图像以还原高动态范围（HDR）场景。与有监督学习不同，损失函数在ULMEF中起关键作用。本文提出新型损失函数，基于待融合图像及同一HDR场景中其他不同曝光图像构建，使模型能从更丰富的场景信息中学习，从而提升融合质量。所提方法还采用多尺度策略，包含多尺度注意力模块，有效保留场景深度与局部对比度。此外，该方法可实现曝光插值与外推。大量实验表明，该算法优于当前最先进的曝光融合方法。
原文摘要 · Abstract (English)
Unsupervised learning based multi-scale exposure fusion (ULMEF) is efficient for fusing differently exposed low dynamic range (LDR) images into a higher quality LDR image for a high dynamic range (HDR) scene. Unlike supervised learning, loss functions play a crucial role in the ULMEF. In this paper, novel loss functions are proposed for the ULMEF and they are defined by using all the images to be fused and other differently exposed images from the same HDR scene. The proposed loss functions can guide the proposed ULMEF to learn more reliable information from the HDR scene than existing loss functions which are defined by only using the set of images to be fused. As such, the quality of the fused image is significantly improved. The proposed ULMEF also adopts a multi-scale strategy that includes a multi-scale attention module to effectively preserve the scene depth and local contrast in the fused image. Meanwhile, the proposed ULMEF can be adopted to achieve exposure interpolation and exposure extrapolation. Extensive experiments show that the proposed ULMEF algorithm outperforms state-of-the-art exposure fusion algorithms.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。