Joint prototype and coefficient prediction for 3D instance segmentation
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_ | 1866909249427210240 |
|---|---|
| author | Royen, Remco Denis, Leon Munteanu, Adrian |
| author_facet | Royen, Remco Denis, Leon Munteanu, Adrian |
| contents | 3D instance segmentation is crucial for applications demanding comprehensive 3D scene understanding. In this paper, we introduce a novel method that simultaneously learns coefficients and prototypes. Employing an overcomplete sampling strategy, our method produces an overcomplete set of instance predictions, from which the optimal ones are selected through a Non-Maximum Suppression (NMS) algorithm during inference. The obtained prototypes are visualizable and interpretable. Our method demonstrates superior performance on S3DIS-blocks, consistently outperforming existing methods in mRec and mPrec. Moreover, it operates 32.9% faster than the state-of-the-art. Notably, with only 0.8% of the total inference time, our method exhibits an over 20-fold reduction in the variance of inference time compared to existing methods. These attributes render our method well-suited for practical applications requiring both rapid inference and high reliability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_06958 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Joint prototype and coefficient prediction for 3D instance segmentation Royen, Remco Denis, Leon Munteanu, Adrian Computer Vision and Pattern Recognition 3D instance segmentation is crucial for applications demanding comprehensive 3D scene understanding. In this paper, we introduce a novel method that simultaneously learns coefficients and prototypes. Employing an overcomplete sampling strategy, our method produces an overcomplete set of instance predictions, from which the optimal ones are selected through a Non-Maximum Suppression (NMS) algorithm during inference. The obtained prototypes are visualizable and interpretable. Our method demonstrates superior performance on S3DIS-blocks, consistently outperforming existing methods in mRec and mPrec. Moreover, it operates 32.9% faster than the state-of-the-art. Notably, with only 0.8% of the total inference time, our method exhibits an over 20-fold reduction in the variance of inference time compared to existing methods. These attributes render our method well-suited for practical applications requiring both rapid inference and high reliability. |
| title | Joint prototype and coefficient prediction for 3D instance segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.06958 |