Pano360: Perspective to Panoramic Vision with Geometric Consistency
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910050630500352 |
|---|---|
| author | Zhu, Zhengdong Xue, Weiyi Yang, Zuyuan Zhou, Wenlve Zhou, Zhiheng |
| author_facet | Zhu, Zhengdong Xue, Weiyi Yang, Zuyuan Zhou, Wenlve Zhou, Zhiheng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_12013 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Pano360: Perspective to Panoramic Vision with Geometric Consistency Zhu, Zhengdong Xue, Weiyi Yang, Zuyuan Zhou, Wenlve Zhou, Zhiheng Computer Vision and Pattern Recognition 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. |
| title | Pano360: Perspective to Panoramic Vision with Geometric Consistency |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.12013 |