Domain Generalization for 6D Pose Estimation Through NeRF-based Image Synthesis
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913431435608064 |
|---|---|
| author | Legrand, Antoine Detry, Renaud De Vleeschouwer, Christophe |
| author_facet | Legrand, Antoine Detry, Renaud De Vleeschouwer, Christophe |
| contents | This work introduces a novel augmentation method that increases the diversity of a train set to improve the generalization abilities of a 6D pose estimation network. For this purpose, a Neural Radiance Field is trained from synthetic images and exploited to generate an augmented set. Our method enriches the initial set by enabling the synthesis of images with (i) unseen viewpoints, (ii) rich illumination conditions through appearance extrapolation, and (iii) randomized textures. We validate our augmentation method on the challenging use-case of spacecraft pose estimation and show that it significantly improves the pose estimation generalization capabilities. On the SPEED+ dataset, our method reduces the error on the pose by 50% on both target domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_10762 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Domain Generalization for 6D Pose Estimation Through NeRF-based Image Synthesis Legrand, Antoine Detry, Renaud De Vleeschouwer, Christophe Computer Vision and Pattern Recognition Image and Video Processing This work introduces a novel augmentation method that increases the diversity of a train set to improve the generalization abilities of a 6D pose estimation network. For this purpose, a Neural Radiance Field is trained from synthetic images and exploited to generate an augmented set. Our method enriches the initial set by enabling the synthesis of images with (i) unseen viewpoints, (ii) rich illumination conditions through appearance extrapolation, and (iii) randomized textures. We validate our augmentation method on the challenging use-case of spacecraft pose estimation and show that it significantly improves the pose estimation generalization capabilities. On the SPEED+ dataset, our method reduces the error on the pose by 50% on both target domains. |
| title | Domain Generalization for 6D Pose Estimation Through NeRF-based Image Synthesis |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2407.10762 |