Stable Surface Regularization for Fast Few-Shot NeRF
This work addresses the challenge of efficient few-shot novel view synthesis for 3D reconstruction, representing an incremental improvement with specific speed gains.
The paper tackles the problem of synthesizing novel views with few training images by introducing a stable surface regularization technique called Annealing Signed Distance Function (ASDF), which accelerates convergence and achieves up to 45 times faster performance than existing methods while producing comparable results on datasets like ScanNet and NeRF-Real.
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, the proposed surface regularization successfully reconstructs scenes and produce high-fidelity geometry with stable training. Our method is further accelerated by utilizing grid representation and monocular geometric priors. Finally, the proposed approach is up to 45 times faster than existing few-shot novel view synthesis methods, and it produces comparable results in the ScanNet dataset and NeRF-Real dataset.