SphereUFormer: A U-Shaped Transformer for Spherical 360 Perception
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913604094132224 |
|---|---|
| author | Benny, Yaniv Wolf, Lior |
| author_facet | Benny, Yaniv Wolf, Lior |
| contents | This paper proposes a novel method for omnidirectional 360$\degree$ perception. Most common previous methods relied on equirectangular projection. This representation is easily applicable to 2D operation layers but introduces distortions into the image. Other methods attempted to remove the distortions by maintaining a sphere representation but relied on complicated convolution kernels that failed to show competitive results. In this work, we introduce a transformer-based architecture that, by incorporating a novel ``Spherical Local Self-Attention'' and other spherically-oriented modules, successfully operates in the spherical domain and outperforms the state-of-the-art in 360$\degree$ perception benchmarks for depth estimation and semantic segmentation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_06968 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SphereUFormer: A U-Shaped Transformer for Spherical 360 Perception Benny, Yaniv Wolf, Lior Computer Vision and Pattern Recognition This paper proposes a novel method for omnidirectional 360$\degree$ perception. Most common previous methods relied on equirectangular projection. This representation is easily applicable to 2D operation layers but introduces distortions into the image. Other methods attempted to remove the distortions by maintaining a sphere representation but relied on complicated convolution kernels that failed to show competitive results. In this work, we introduce a transformer-based architecture that, by incorporating a novel ``Spherical Local Self-Attention'' and other spherically-oriented modules, successfully operates in the spherical domain and outperforms the state-of-the-art in 360$\degree$ perception benchmarks for depth estimation and semantic segmentation. |
| title | SphereUFormer: A U-Shaped Transformer for Spherical 360 Perception |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.06968 |