-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Irshad_2023_ICCV, author = {Irshad, Muhammad Zubair and Zakharov, Sergey and Liu, Katherine and Guizilini, Vitor and Kollar, Thomas and Gaidon, Adrien and Kira, Zsolt and Ambrus, Rares}, title = {NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9187-9198} }
NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes
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 360deg 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 360deg 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: zubair-irshad.github.io/projects/neo360.html
Related Material