Metraipolis › archive › dc_1ed607f8eb41

Predicting Signed Distance Functions for Visual Instance Segmentation — arXiv:2608.13135

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13135
License (as archived)
CC0-1.0
Archived
2026-10-19T04:55:47.844Z
SHA-256 of the archived text
86ce865cd0121bfd8832cd58dcc696dbe7d270933cdf9347b6f4148e06e93f95
Stable URL of this page
https://metraipolis.com/documento/dc_1ed607f8eb41

How to cite

Predicting Signed Distance Functions for Visual Instance Segmentation — arXiv:2608.13135 — arXiv (en), https://arxiv.org/abs/2608.13135 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1ed607f8eb41 (Metraipolis archive dc_1ed607f8eb41, sha256 86ce865cd0121bfd8832cd58dcc696dbe7d270933cdf9347b6f4148e06e93f95)
BibTeX
@misc{dc1ed607f8eb41,
  title = {Predicting Signed Distance Functions for Visual Instance Segmentation — arXiv:2608.13135},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13135},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1ed607f8eb41; sha256 86ce865cd0121bfd8832cd58dcc696dbe7d270933cdf9347b6f4148e06e93f95},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13135. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Visual instance segmentation is a challenging problem and becomes even more difficult if objects of interest varies unconstrained in shape. Some objects are well described by a rectangle, however, this is hardly always the case. Consider for instance long, slender objects such as ropes. Anchor-based approaches classify predefined bounding boxes as either negative or positive and thus provide a limited set of shapes that can be handled. Defining anchor-boxes that fit well to all possible shapes leads to an infeasible number of prior boxes. We explore a different approach and propose to train a neural network to compute distance maps along different directions. The network is trained at each pixel to predict the distance to the closest object contour in a given direction. By pooling the distance maps we obtain an approximation to the signed distance function (SDF). The SDF may then be thresholded in order to obtain a foreground-background segmentation. We compare this segmentation to foreground segmentations obtained from the state-of-the-art instance segmentation method YOLACT. On the COCO dataset, our segmentation yields a higher performance in terms of foreground intersection over union (IoU). However, while the distance maps contain information on the individual instances, it is not straightforward to map them to the full instance segmentation. We still believe that this idea is a promising research direction for instance segmentation, as it better captures the different shapes found in the real world.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-14 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.13135 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T04:46:30.157Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).