Multi-Class Segmentation from Aerial Views using Recursive Noise Diffusion
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2022
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916255880970240 |
|---|---|
| author | Kolbeinsson, Benedikt Mikolajczyk, Krystian |
| author_facet | Kolbeinsson, Benedikt Mikolajczyk, Krystian |
| contents | Semantic segmentation from aerial views is a crucial task for autonomous drones, as they rely on precise and accurate segmentation to navigate safely and efficiently. However, aerial images present unique challenges such as diverse viewpoints, extreme scale variations, and high scene complexity. In this paper, we propose an end-to-end multi-class semantic segmentation diffusion model that addresses these challenges. We introduce recursive denoising to allow information to propagate through the denoising process, as well as a hierarchical multi-scale approach that complements the diffusion process. Our method achieves promising results on the UAVid dataset and state-of-the-art performance on the Vaihingen Building segmentation benchmark. Being the first iteration of this method, it shows great promise for future improvements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2212_00787 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Multi-Class Segmentation from Aerial Views using Recursive Noise Diffusion Kolbeinsson, Benedikt Mikolajczyk, Krystian Computer Vision and Pattern Recognition Semantic segmentation from aerial views is a crucial task for autonomous drones, as they rely on precise and accurate segmentation to navigate safely and efficiently. However, aerial images present unique challenges such as diverse viewpoints, extreme scale variations, and high scene complexity. In this paper, we propose an end-to-end multi-class semantic segmentation diffusion model that addresses these challenges. We introduce recursive denoising to allow information to propagate through the denoising process, as well as a hierarchical multi-scale approach that complements the diffusion process. Our method achieves promising results on the UAVid dataset and state-of-the-art performance on the Vaihingen Building segmentation benchmark. Being the first iteration of this method, it shows great promise for future improvements. |
| title | Multi-Class Segmentation from Aerial Views using Recursive Noise Diffusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2212.00787 |