Self-supervised Video Depth Adaptation for Efficient Sparse-view NeRF

Depth priors are critical for maintaining accurate geometry in novel view synthesis, especially when input views are sparse and scenes are complex and room-scale. However, obtaining reliable depth under such conditions remains a significant challenge. In this work, we present a novel method that self-supervisedly adapts a pretrained video depth estimation network to each specific scene. This scene-specific adaptation enables high-fidelity depth estimation even under extreme view sparsity. Leveraging these accurate depth priors, we propose an efficient two-stage NeRF training pipeline with a density self-correction mechanism that mitigates the effects of depth errors without relying on explicit uncertainty modeling. Our approach not only enhances synthesis quality in sparse-view settings but also significantly accelerates neural radiance field (NeRF) training, outperforming existing methods in both fidelity and efficiency.