-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Peng and Liu, Yuan and Chen, Zhaoxi and Liu, Lingjie and Liu, Ziwei and Komura, Taku and Theobalt, Christian and Wang, Wenping}, title = {F2-NeRF: Fast Neural Radiance Field Training With Free Camera Trajectories}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4150-4159} }
F2-NeRF: Fast Neural Radiance Field Training With Free Camera Trajectories
Abstract
This paper presents a novel grid-based NeRF called F^2-NeRF (Fast-Free-NeRF) for novel view synthesis, which enables arbitrary input camera trajectories and only costs a few minutes for training. Existing fast grid-based NeRF training frameworks, like Instant-NGP, Plenoxels, DVGO, or TensoRF, are mainly designed for bounded scenes and rely on space warping to handle unbounded scenes. Existing two widely-used space-warping methods are only designed for the forward-facing trajectory or the 360deg object-centric trajectory but cannot process arbitrary trajectories. In this paper, we delve deep into the mechanism of space warping to handle unbounded scenes. Based on our analysis, we further propose a novel space-warping method called perspective warping, which allows us to handle arbitrary trajectories in the grid-based NeRF framework. Extensive experiments demonstrate that F^2-NeRF is able to use the same perspective warping to render high-quality images on two standard datasets and a new free trajectory dataset collected by us.
Related Material