GSN: Generalisable Segmentation in Neural Radiance Field
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_ | 1866910321083416576 |
|---|---|
| author | Gupta, Vinayak Goel, Rahul Dhawal, Sirikonda Narayanan, P. J. |
| author_facet | Gupta, Vinayak Goel, Rahul Dhawal, Sirikonda Narayanan, P. J. |
| contents | Traditional Radiance Field (RF) representations capture details of a specific scene and must be trained afresh on each scene. Semantic feature fields have been added to RFs to facilitate several segmentation tasks. Generalised RF representations learn the principles of view interpolation. A generalised RF can render new views of an unknown and untrained scene, given a few views. We present a way to distil feature fields into the generalised GNT representation. Our GSN representation generates new views of unseen scenes on the fly along with consistent, per-pixel semantic features. This enables multi-view segmentation of arbitrary new scenes. We show different semantic features being distilled into generalised RFs. Our multi-view segmentation results are on par with methods that use traditional RFs. GSN closes the gap between standard and generalisable RF methods significantly. Project Page: https://vinayak-vg.github.io/GSN/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_04632 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GSN: Generalisable Segmentation in Neural Radiance Field Gupta, Vinayak Goel, Rahul Dhawal, Sirikonda Narayanan, P. J. Computer Vision and Pattern Recognition Graphics Traditional Radiance Field (RF) representations capture details of a specific scene and must be trained afresh on each scene. Semantic feature fields have been added to RFs to facilitate several segmentation tasks. Generalised RF representations learn the principles of view interpolation. A generalised RF can render new views of an unknown and untrained scene, given a few views. We present a way to distil feature fields into the generalised GNT representation. Our GSN representation generates new views of unseen scenes on the fly along with consistent, per-pixel semantic features. This enables multi-view segmentation of arbitrary new scenes. We show different semantic features being distilled into generalised RFs. Our multi-view segmentation results are on par with methods that use traditional RFs. GSN closes the gap between standard and generalisable RF methods significantly. Project Page: https://vinayak-vg.github.io/GSN/ |
| title | GSN: Generalisable Segmentation in Neural Radiance Field |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2402.04632 |