Misc,
NeRF--: Neural Radiance Fields Without Known Camera Parameters
(2021)cite arxiv:2102.07064Comment: project page see nerfmm.active.vision.
Abstract
This paper tackles the problem of novel view synthesis (NVS) from 2D images
without known camera poses and intrinsics. Among various NVS techniques, Neural
Radiance Field (NeRF) has recently gained popularity due to its remarkable
synthesis quality. Existing NeRF-based approaches assume that the camera
parameters associated with each input image are either directly accessible at
training, or can be accurately estimated with conventional techniques based on
correspondences, such as Structure-from-Motion. In this work, we propose an
end-to-end framework, termed NeRF--, for training NeRF models given only RGB
images, without pre-computed camera parameters. Specifically, we show that the
camera parameters, including both intrinsics and extrinsics, can be
automatically discovered via joint optimisation during the training of the NeRF
model. On the standard LLFF benchmark, our model achieves comparable novel view
synthesis results compared to the baseline trained with COLMAP pre-computed
camera parameters. We also conduct extensive analyses to understand the model
behaviour under different camera trajectories, and show that in scenarios where
COLMAP fails, our model still produces robust results.
