PanoVGGT：基于全景图像的前馈三维重建
PanoVGGT: Feed-Forward 3D Reconstruction from Panoramic Imagery
将前馈式三维重建模型（如VGGT）扩展到全景图像，通过球面感知位置编码和三轴SO(3)旋转增强处理非针孔畸变，并引入随机锚定策略解决全局坐标系歧义，为全景相机下的联合位姿估计与稠密重建提供可复用方案。
原文依据 We propose PanoVGGT, a permutation-equivariant Transformer framework that jointly predicts camera poses, depth maps, and 3D point clouds from one or multiple panoramas in a single forward pass.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论全景图像提供完整的360度视野，在消费设备中日益普及。然而，它引入了非针孔畸变，对联合位姿估计和三维重建构成挑战。现有的前馈模型为透视相机设计，在此场景下泛化能力较差。我们提出PanoVGGT，一个置换等变的Transformer框架，单次前向传播即可从单张或多张全景图像中联合预测相机位姿、深度图和三维点云。该模型结合了球面感知位置嵌入和全景特定的三轴SO(3)旋转增强，从而在球面域中实现有效的几何推理。为解决固有的全局坐标系歧义，我们进一步在训练中引入随机锚定策略。此外，我们贡献了PanoCity，一个带有稠密深度和6自由度位姿标注的大规模室外全景数据集。在PanoCity和标准基准上的大量实验表明，PanoVGGT取得了有竞争力的精度、强鲁棒性和改进的跨域泛化能力。代码和数据集将公开。
英文原文摘要 1136 字符
Panoramic imagery offers a full 360^\circ field of view and is increasingly common in consumer devices. However, it introduces non-pinhole distortions that challenge joint pose estimation and 3D reconstruction. Existing feed-forward models, built for perspective cameras, generalize poorly to this setting. We propose PanoVGGT, a permutation-equivariant Transformer framework that jointly predicts camera poses, depth maps, and 3D point clouds from one or multiple panoramas in a single forward pass. The model incorporates spherical-aware positional embeddings and a panorama-specific three-axis SO(3) rotation augmentation, enabling effective geometric reasoning in the spherical domain. To resolve inherent global-frame ambiguity, we further introduce a stochastic anchoring strategy during training. In addition, we contribute PanoCity, a large-scale outdoor panoramic dataset with dense depth and 6-DoF pose annotations. Extensive experiments on PanoCity and standard benchmarks demonstrate that PanoVGGT achieves competitive accuracy, strong robustness, and improved cross-domain generalization. Code and dataset will be released.