NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction. In ICCV, 2023.

Paper Abstract:
Recent methods for neural surface representation and rendering, for example NeuS, have demonstrated remarkably high-quality reconstruction of static scenes. However, the training of NeuS takes an extremely long time (8~hours), which makes it almost impossible to apply them to dynamic scenes with thousands of frames. We propose a fast neural surface reconstruction approach, called NeuS2, which achieves two orders of magnitude improvement in terms of acceleration without compromising reconstruction quality. To accelerate the training process, we integrate multi-resolution hash encodings into a neural surface representation and implement our whole algorithm in CUDA. We also present a lightweight calculation of second-order derivatives tailored to our networks (i.e., ReLU-based MLPs), which achieves a factor two speed up. To further stabilize training, a progressive learning strategy is proposed to optimize multi-resolution hash encodings from coarse to fine. In addition, we extend our method for reconstructing dynamic scenes with an incremental training strategy. Our experiments on various datasets demonstrate that NeuS2 significantly outperforms the state-of-the-arts in both surface reconstruction accuracy and training speed.
Reference Publication:
Yiming Wang, Qin Han, Marc Habermann, Kostas Daniilidis, Christian Theobalt, Lingjie Liu : NeuS2: Fast Learning of Neural Implicit Surfaces
for Multi-view Reconstruction. In ICCV, 2023.
Project Page:
vcai.mpi-inf.m...

[@well5423]

Amazing reconstruction quality! Bravo.

[@crestz1]

whats the diff between this and neuralangelo? both appears to use first and second order derivatives