MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction

06/01/2022
by   Zehao Yu, et al.
2

In recent years, neural implicit surface reconstruction methods have become popular for multi-view 3D reconstruction. In contrast to traditional multi-view stereo methods, these approaches tend to produce smoother and more complete reconstructions due to the inductive smoothness bias of neural networks. State-of-the-art neural implicit methods allow for high-quality reconstructions of simple scenes from many input views. Yet, their performance drops significantly for larger and more complex scenes and scenes captured from sparse viewpoints. This is caused primarily by the inherent ambiguity in the RGB reconstruction loss that does not provide enough constraints, in particular in less-observed and textureless areas. Motivated by recent advances in the area of monocular geometry prediction, we systematically explore the utility these cues provide for improving neural implicit surface reconstruction. We demonstrate that depth and normal cues, predicted by general-purpose monocular estimators, significantly improve reconstruction quality and optimization time. Further, we analyse and investigate multiple design choices for representing neural implicit surfaces, ranging from monolithic MLP models over single-grid to multi-resolution grid representations. We observe that geometric monocular priors improve performance both for small-scale single-object as well as large-scale multi-object scenes, independent of the choice of representation.

READ FULL TEXT

page 20

page 21

page 22

page 23

page 24

page 25

page 26

page 27

research
08/29/2023

DebSDF: Delving into the Details and Bias of Neural Indoor Scene Reconstruction

In recent years, the neural implicit surface has emerged as a powerful r...
research
10/14/2021

NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild

Recent history has seen a tremendous growth of work exploring implicit r...
research
06/08/2023

StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Views

We present a novel multi-view implicit surface reconstruction technique,...
research
09/19/2023

360^∘ Reconstruction From a Single Image Using Space Carved Outpainting

We introduce POP3D, a novel framework that creates a full 360^∘-view 3D ...
research
03/25/2023

VisCo Grids: Surface Reconstruction with Viscosity and Coarea Grids

Surface reconstruction has been seeing a lot of progress lately by utili...
research
03/10/2020

Convolutional Occupancy Networks

Recently, implicit neural representations have gained popularity for lea...
research
05/25/2017

Plan3D: Viewpoint and Trajectory Optimization for Aerial Multi-View Stereo Reconstruction

We introduce a new method that efficiently computes a set of rich viewpo...

Please sign up or login with your details

Forgot password? Click here to reset