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

TL;DR

AltNeRF introduces a self-supervised framework that enhances neural radiance fields by jointly optimizing depth and pose from monocular videos, improving robustness and scene reconstruction quality without known camera poses.

Contribution

It proposes an alternating optimization method that integrates self-supervised monocular depth estimation with NeRF training, enabling robust scene modeling without explicit pose supervision.

Findings

Produces high-fidelity novel views

Demonstrates robustness to pose and depth estimation errors

Outperforms existing NeRF methods in sparse data scenarios

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 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.