AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization
This work improves NeRF for 3D scene reconstruction and novel view synthesis, particularly in scenarios with unknown camera poses, though it appears incremental by combining existing techniques.
The paper tackles the problem of generating realistic novel views from sparse images in Neural Radiance Fields (NeRF) by addressing challenges from lack of 3D supervision and imprecise camera poses, resulting in high-fidelity and robust view synthesis as demonstrated in experiments.
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 learns depth and pose priors to regulate NeRF training. The depth prior enriches NeRF's capacity for precise scene geometry depiction, while the pose prior provides a robust starting point for subsequent pose refinement. Moreover, we introduce an alternating algorithm that harmoniously melds NeRF outputs into SMDE through a consistence-driven mechanism, thus enhancing the integrity of depth priors. This alternation empowers AltNeRF to progressively refine NeRF representations, yielding the synthesis of realistic novel views. Extensive experiments showcase the compelling capabilities of AltNeRF in generating high-fidelity and robust novel views that closely resemble reality.