PanoVGGT: Feed-Forward 3D Reconstruction from Panoramic Imagery
Panoramic imagery offers a full 360° 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 i...
| Authors | Yijing Guo, Mengjun Chao, Luo Wang et al. |
|---|---|
| Primary category | cs.CV |
| Published | 18 March 2026 |
| Last updated at source | 18 March 2026 |
Connected in the knowledge graph
- YijingGuo/PanoCityDataset · cited by
Models and datasets referencing this paper
- YijingGuo/PanoCityDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.