CT-NeRF: Incremental Optimizing Neural Radiance Field and Poses with Complex Trajectory

arXiv:2404.13896v1 Announce Type: new
Abstract: Neural radiance field (NeRF) has achieved impressive results in high-quality 3D scene reconstruction. However, NeRF heavily relies on precise camera poses. While recent works like BARF have introduced camera pose optimization within NeRF, their applicability is limited to simple trajectory scenes. Existing methods struggle while tackling complex trajectories involving large rotations. To address this limitation, we propose CT-NeRF, an incremental reconstruction optimization pipeline using only RGB images without pose and depth input. In this pipeline, …

abstract arxiv cs.cv however incremental nerf neural radiance field optimization quality results simple struggle trajectory type