NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes

TL;DR

NeO 360 is a novel neural field approach that enables 360-degree outdoor scene reconstruction and novel view synthesis from very few images, combining voxel and BEV representations for improved generalization and expressiveness.

Contribution

The paper introduces NeO 360, a generalizable neural field method that reconstructs outdoor scenes from minimal views using a hybrid representation, outperforming existing methods.

Findings

Outperforms state-of-the-art generalizable view synthesis methods

Works effectively with only a single input image

Provides editing and composition capabilities

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