Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.10343 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908448980992000 |
|---|---|
| author | Norrby, Hugo Färm, Gabriel Hernandez-Diaz, Kevin Alonso-Fernandez, Fernando |
| author_facet | Norrby, Hugo Färm, Gabriel Hernandez-Diaz, Kevin Alonso-Fernandez, Fernando |
| contents | We introduce FGSSNet, a novel multi-headed feature-guided semantic segmentation (FGSS) architecture designed to improve the generalization ability of wall segmentation on floorplans. FGSSNet features a U-Net segmentation backbone with a multi-headed dedicated feature extractor used to extract domain-specific feature maps which are injected into the latent space of U-Net to guide the segmentation process. This dedicated feature extractor is trained as an encoder-decoder with selected wall patches, representative of the walls present in the input floorplan, to produce a compressed latent representation of wall patches while jointly trained to predict the wall width. In doing so, we expect that the feature extractor encodes texture and width features of wall patches that are useful to guide the wall segmentation process. Our experiments show increased performance by the use of such injected features in comparison to the vanilla U-Net, highlighting the validity of the proposed approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_10343 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FGSSNet: Feature-Guided Semantic Segmentation of Real World Floorplans Norrby, Hugo Färm, Gabriel Hernandez-Diaz, Kevin Alonso-Fernandez, Fernando Computer Vision and Pattern Recognition We introduce FGSSNet, a novel multi-headed feature-guided semantic segmentation (FGSS) architecture designed to improve the generalization ability of wall segmentation on floorplans. FGSSNet features a U-Net segmentation backbone with a multi-headed dedicated feature extractor used to extract domain-specific feature maps which are injected into the latent space of U-Net to guide the segmentation process. This dedicated feature extractor is trained as an encoder-decoder with selected wall patches, representative of the walls present in the input floorplan, to produce a compressed latent representation of wall patches while jointly trained to predict the wall width. In doing so, we expect that the feature extractor encodes texture and width features of wall patches that are useful to guide the wall segmentation process. Our experiments show increased performance by the use of such injected features in comparison to the vanilla U-Net, highlighting the validity of the proposed approach. |
| title | FGSSNet: Feature-Guided Semantic Segmentation of Real World Floorplans |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.10343 |