Can I read GenS: Generalizable Neural Surface Reconstruction from Multi-View Images on EtoBox?

GenS: Generalizable Neural Surface Reconstruction from Multi-View Images by Peng, Rui; Gu, Xiaodong; Tang, Luyang; Shen, Shihe; Yu, Fanqi; Wang, Ronggang is a scholarly article available to read on EtoBox.

What is GenS: Generalizable Neural Surface Reconstruction from Multi-View Images about?

Combining the signed distance function (SDF) and differentiable volume rendering has emerged as a powerful paradigm for surface reconstruction from multi-view images without 3D supervision. However, current methods are impeded by requiring long-time per-scene optimizations and cannot generalize to new scenes. In this paper, we present GenS, an end-to-end generalizable neural surface reconstruction model. Unlike coordinate-based methods that train a separate network for each scene, we construct a generalized multi-scale volume to directly encode all scenes. Compared with existing solutions, our representation is more powerful, which can recover high-frequency details while maintaining global smoothness. Meanwhile, we introduce a multi-scale feature-metric consistency to impose the multi-view consistency in a more discriminative multi-scale feature space, which is robust to the failures of the photometric consistency. And the learnable feature can be self-enhanced to continuously improve the matching accuracy and mitigate aggregation ambiguity. Furthermore, we design a view contrast loss to force the model to be robust to those regions covered by few viewpoints through distilling the

Author

Peng, Rui; Gu, Xiaodong; Tang, Luyang; Shen, Shihe; Yu, Fanqi; Wang, Ronggang

Published

2024

Language

EN