Stable Surface Regularization for Fast Few-Shot NeRF

arXiv:2403.19985v1 Announce Type: new
Abstract: This paper proposes an algorithm for synthesizing novel views under few-shot setup. The main concept is to develop a stable surface regularization technique called Annealing Signed Distance Function (ASDF), which anneals the surface in a coarse-to-fine manner to accelerate convergence speed. We observe that the Eikonal loss - which is a widely known geometric regularization - requires dense training signal to shape different level-sets of SDF, leading to low-fidelity results under few-shot training. In contrast, …

abstract algorithm arxiv concept convergence cs.cv few-shot function loss nerf novel observe paper regularization setup speed surface type