AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization

arXiv:2308.10001v2 Announce Type: replace
Abstract: Neural Radiance Fields (NeRF) have shown promise in generating realistic novel views from sparse scene images. However, existing NeRF approaches often encounter challenges due to the lack of explicit 3D supervision and imprecise camera poses, resulting in suboptimal outcomes. To tackle these issues, we propose AltNeRF -- a novel framework designed to create resilient NeRF representations using self-supervised monocular depth estimation (SMDE) from monocular videos, without relying on known camera poses. SMDE in AltNeRF masterfully …

abstract arxiv challenges cs.cv fields images nerf neural radiance field neural radiance fields novel optimization robust supervision type via