A Construct-Optimize Approach to Sparse View Synthesis without Camera Pose

arXiv:2405.03659v1 Announce Type: new
Abstract: Novel view synthesis from a sparse set of input images is a challenging problem of great practical interest, especially when camera poses are absent or inaccurate. Direct optimization of camera poses and usage of estimated depths in neural radiance field algorithms usually do not produce good results because of the coupling between poses and depths, and inaccuracies in monocular depth estimation. In this paper, we leverage the recent 3D Gaussian splatting method to develop a …

abstract algorithms arxiv construct cs.cv cs.gr images neural radiance field novel optimization practical set synthesis type usage view