{"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/neo-360-neural-fields-for-sparse-view","title":"NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes","arxiv_id":"2308.12967","date":"2023-08-24","proceeding":"ICCV 2023 1","authors":["Muhammad Zubair Irshad","Sergey Zakharov","Katherine Liu","Vitor Guizilini","Thomas Kollar","Adrien Gaidon","Zsolt Kira","Rares Ambrus"],"abstract":"Recent implicit neural representations have shown great results for novel view synthesis. However, existing methods require expensive per-scene optimization from many views hence limiting their application to real-world unbounded urban settings where the objects of interest or backgrounds are observed from very few views. To mitigate this challenge, we introduce a new approach called NeO 360, Neural fields for sparse view synthesis of outdoor scenes. NeO 360 is a generalizable method that reconstructs 360{\\deg} scenes from a single or a few posed RGB images. The essence of our approach is in capturing the distribution of complex real-world outdoor 3D scenes and using a hybrid image-conditional triplanar representation that can be queried from any world point. Our representation combines the best of both voxel-based and bird's-eye-view (BEV) representations and is more effective and expressive than each. NeO 360's representation allows us to learn from a large collection of unbounded 3D scenes while offering generalizability to new views and novel scenes from as few as a single image during inference. We demonstrate our approach on the proposed challenging 360{\\deg} unbounded dataset, called NeRDS 360, and show that NeO 360 outperforms state-of-the-art generalizable methods for novel view synthesis while also offering editing and composition capabilities. Project page: https://zubair-irshad.github.io/projects/neo360.html","url_abs":"https://arxiv.org/abs/2308.12967v1","url_pdf":"https://arxiv.org/pdf/2308.12967v1.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":"neo-360-neural-fields-for-sparse-view","repo_url":"https://github.com/zubair-irshad/NeO-360","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neo-360-neural-fields-for-sparse-view","repo_url":"https://github.com/zubair-irshad/NeRF-MAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"generalizable-novel-view-synthesis","task_name":"Generalizable Novel View Synthesis"},{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"}],"methods":[],"datasets_introduced":[{"slug":"nerds-360","name":"NERDS 360","full_name":"NeRF for Reconstruction, Decomposition and Scene Synthesis of 360° outdoor scenes"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.12967","atlas_url":"https://app.syntology.ai/?focus=2308.12967","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}