Reprojection Errors as Prompts for Efficient Scene Coordinate Regression
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_ | 1866910592899481600 |
|---|---|
| author | Liu, Ting-Ru Yang, Hsuan-Kung Liu, Jou-Min Huang, Chun-Wei Chiang, Tsung-Chih Kong, Quan Kobori, Norimasa Lee, Chun-Yi |
| author_facet | Liu, Ting-Ru Yang, Hsuan-Kung Liu, Jou-Min Huang, Chun-Wei Chiang, Tsung-Chih Kong, Quan Kobori, Norimasa Lee, Chun-Yi |
| contents | Scene coordinate regression (SCR) methods have emerged as a promising area of research due to their potential for accurate visual localization. However, many existing SCR approaches train on samples from all image regions, including dynamic objects and texture-less areas. Utilizing these areas for optimization during training can potentially hamper the overall performance and efficiency of the model. In this study, we first perform an in-depth analysis to validate the adverse impacts of these areas. Drawing inspiration from our analysis, we then introduce an error-guided feature selection (EGFS) mechanism, in tandem with the use of the Segment Anything Model (SAM). This mechanism seeds low reprojection areas as prompts and expands them into error-guided masks, and then utilizes these masks to sample points and filter out problematic areas in an iterative manner. The experiments demonstrate that our method outperforms existing SCR approaches that do not rely on 3D information on the Cambridge Landmarks and Indoor6 datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_04178 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Reprojection Errors as Prompts for Efficient Scene Coordinate Regression Liu, Ting-Ru Yang, Hsuan-Kung Liu, Jou-Min Huang, Chun-Wei Chiang, Tsung-Chih Kong, Quan Kobori, Norimasa Lee, Chun-Yi Computer Vision and Pattern Recognition Scene coordinate regression (SCR) methods have emerged as a promising area of research due to their potential for accurate visual localization. However, many existing SCR approaches train on samples from all image regions, including dynamic objects and texture-less areas. Utilizing these areas for optimization during training can potentially hamper the overall performance and efficiency of the model. In this study, we first perform an in-depth analysis to validate the adverse impacts of these areas. Drawing inspiration from our analysis, we then introduce an error-guided feature selection (EGFS) mechanism, in tandem with the use of the Segment Anything Model (SAM). This mechanism seeds low reprojection areas as prompts and expands them into error-guided masks, and then utilizes these masks to sample points and filter out problematic areas in an iterative manner. The experiments demonstrate that our method outperforms existing SCR approaches that do not rely on 3D information on the Cambridge Landmarks and Indoor6 datasets. |
| title | Reprojection Errors as Prompts for Efficient Scene Coordinate Regression |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.04178 |