Learning Spherical Radiance Field for Efficient 360° Unbounded Novel View Synthesis
IEEE Transactions on Image Processing · 2024 · 33 · 3722-3734
DOI: 10.1109/tip.2024.3409052 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2024. Verfasst von Minglin Chen und 4 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 75 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Basic and Applied Basic Research Foundation of Guangdong Province, Shenzhen Science and Technology Program.
Abstract (Originalsprache)
Novel view synthesis aims at rendering any posed images from sparse observations of the scene. Recently, neural radiance fields (NeRF) have demonstrated their effectiveness in synthesizing novel views of a bounded scene. However, most existing methods cannot be directly extended to 360° unbounded scenes where the camera orientations and scene depths are unconstrained with large variations. In this paper, we present a spherical radiance field (SRF) for efficient novel view synthesis in 360° unbounded scenes. Specifically, we represent a 3D scene as multiple concentric spheres with different radii. In particular, each sphere encodes its corresponding layered scene into implicit representations and is parameterized with an equirectangular projection image. A shallow multi-layer perceptron (MLP) is then used to infer the density and color from these sphere representations for volume rendering. Moreover, an occupancy grid is introduced to cache the density field and guide the ray sampling, which accelerates the training and rendering procedures by reducing the number of samples along the ray. Experiments show that our method can well fit 360° unbounded scenes and produces state-of-the-art results on three benchmark datasets with less than 30 minutes of training time on a 3090 GPU, surpassing Mip-NeRF 360 with a 400× speedup. In addition, our method achieves competitive performance in terms of both accuracy and efficiency on a bounded dataset. Project page: https://minglin-chen.github.io/SphericalRF.
Förderung
- National Natural Science Foundation of China
- Basic and Applied Basic Research Foundation of Guangdong Province
- Shenzhen Science and Technology Program
Zitieren
APA
Chen, M., Wang, L., Lei, Y., Dong, Z., & Guo, Y. (2024). Learning Spherical Radiance Field for Efficient 360° Unbounded Novel View Synthesis. IEEE Transactions on Image Processing, 33, 3722-3734. https://doi.org/10.1109/tip.2024.3409052
Vancouver
Chen M, Wang L, Lei Y, Dong Z, Guo Y. Learning Spherical Radiance Field for Efficient 360° Unbounded Novel View Synthesis. IEEE Transactions on Image Processing. 2024;33:3722-3734. doi:10.1109/tip.2024.3409052
BibTeX
@article{Chen2024,
author = {Chen, Minglin and Wang, Longguang and Lei, Yinjie and Dong, Zilong and Guo, Yulan},
title = {Learning Spherical Radiance Field for Efficient 360° Unbounded Novel View Synthesis},
journal = {IEEE Transactions on Image Processing},
year = {2024},
volume = {33},
pages = {3722--3734},
doi = {10.1109/tip.2024.3409052}
}
EUVIMED