用神经增强融合多曝光全景图，解决高动态范围拼接中的亮度失真问题。
Neural Augmentation Based Panoramic High Dynamic Range Stitching
- 结合物理模型与数据驱动方法，利用重叠视域生成多曝光图像
- 通过多尺度曝光融合算法合成无伪影的全景高动态图像
- 适合需要高质量全景图像的VR/摄影应用
由于输入的低动态范围（LDR）图像存在过曝区域，且不同曝光间存在显著亮度差异，仅靠几何对齐的多曝光LDR图像拼接难以生成信息丰富且无视觉伪影的全景式高动态范围（HDR）场景图像。得益于各图像之间存在重叠视域（OFOVs），该问题恰好为物理驱动与数据驱动方法的融合提供了理想场景。本文提出一种基于神经增强的全景HDR拼接算法：首先利用重叠视域构建物理驱动方法生成各视角下的多曝光图像，再通过数据驱动方法进行优化，最终生成多组不同曝光的全景LDR图像；所有图像经多尺度曝光融合算法合并，得到最终全景LDR图像。实验结果表明，该方法优于现有全景拼接算法。
原文摘要 · Abstract (English)
Due to saturated regions of inputting low dynamic range (LDR) images and large intensity changes among the LDR images caused by different exposures, it is challenging to produce an information enriched panoramic LDR image without visual artifacts for a high dynamic range (HDR) scene through stitching multiple geometrically synchronized LDR images with different exposures and pairwise overlapping fields of views (OFOVs). Fortunately, the stitching of such images is innately a perfect scenario for the fusion of a physics-driven approach and a data-driven approach due to their OFOVs. Based on this new insight, a novel neural augmentation based panoramic HDR stitching algorithm is proposed in this paper. The physics-driven approach is built up using the OFOVs. Different exposed images of each view are initially generated by using the physics-driven approach, are then refined by a data-driven approach, and are finally used to produce panoramic LDR images with different exposures. All the panoramic LDR images with different exposures are combined together via a multi-scale exposure fusion algorithm to produce the final panoramic LDR image. Experimental results demonstrate the proposed algorithm outperforms existing panoramic stitching 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。