{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/gsn-generalisable-segmentation-in-neural","title":"GSN: Generalisable Segmentation in Neural Radiance Field","arxiv_id":"2402.04632","date":"2024-02-07","proceeding":null,"authors":["Vinayak Gupta","Rahul Goel","Sirikonda Dhawal","P. J. Narayanan"],"abstract":"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/","url_abs":"https://arxiv.org/abs/2402.04632v1","url_pdf":"https://arxiv.org/pdf/2402.04632v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"gsn-generalisable-segmentation-in-neural","repo_url":"https://github.com/Vinayak-VG/GSN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"gsn-generalisable-segmentation-in-neural","repo_url":"https://github.com/Vinayak-VG/GAURA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2402.04632","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}