Pano360：从透视到全景视觉的几何一致性方法
Pano360: Perspective to Panoramic Vision with Geometric Consistency
把2D成对特征匹配的对齐任务搬到3D摄影测量空间，用相机位姿直接引导图像warping做全局对齐，并用多特征联合优化求接缝；对做全景/宽基线拼接、多视图对齐的人，这是一个可复用的「位姿引导+全局优化」范式。
原文依据 It directly utilizes camera poses to guide image warping for global alignment in 3D space and employs a multi-feature joint optimization strategy to compute the seams.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有的全景拼接方法严重依赖成对特征对应关系，无法利用多视图之间的几何一致性，这在弱纹理、大视差和重复纹理等困难场景中会导致严重的畸变与错位。鉴于多视图几何对应关系可以直接在三维空间中构建，从而更加准确且全局一致，我们将二维对齐任务扩展到三维摄影测量空间。我们采用一种新颖的基于 Transformer 的架构来实现三维感知，并聚合所有视图的全局信息。该方法直接利用相机位姿引导图像变换，以在三维空间中实现全局对齐，并采用多特征联合优化策略计算接缝。此外，为建立评测基准并训练我们的网络，我们构建了一个真实场景的大规模数据集。大量实验表明，我们的方法在对齐精度和感知质量上显著优于现有替代方案。
英文原文摘要 1066 字符
Prior panorama stitching approaches heavily rely on pairwise feature correspondences and are unable to leverage geometric consistency across multiple views. This leads to severe distortion and misalignment, especially in challenging scenes with weak textures, large parallax, and repetitive patterns. Given that multi-view geometric correspondences can be directly constructed in 3D space, making them more accurate and globally consistent, we extend the 2D alignment task to the 3D photogrammetric space. We adopt a novel transformer-based architecture to achieve 3D awareness and aggregate global information across all views. It directly utilizes camera poses to guide image warping for global alignment in 3D space and employs a multi-feature joint optimization strategy to compute the seams. Additionally, to establish an evaluation benchmark and train our network, we constructed a large-scale dataset of real-world scenes. Extensive experiments show that our method significantly outperforms existing alternatives in alignment accuracy and perceptual quality.