Log In Sign Up

Sign-Agnostic CONet: Learning Implicit Surface Reconstructions by Sign-Agnostic Optimization of Convolutional Occupancy Networks

by   Jiapeng Tang, et al.

Surface reconstruction from point clouds is a fundamental problem in the computer vision and graphics community. Recent state-of-the-arts solve this problem by individually optimizing each local implicit field during inference. Without considering the geometric relationships between local fields, they typically require accurate normals to avoid the sign conflict problem in overlapping regions of local fields, which severely limits their applicability to raw scans where surface normals could be unavailable. Although SAL breaks this limitation via sign-agnostic learning, it is still unexplored that how to extend this pipeline to local shape modeling. To this end, we propose to learn implicit surface reconstruction by sign-agnostic optimization of convolutional occupancy networks, to simultaneously achieve advanced scalability, generality, and applicability in a unified framework. In the paper, we also show this goal can be effectively achieved by a simple yet effective design, which optimizes the occupancy fields that are conditioned on convolutional features from an hourglass network architecture with an unsigned binary cross-entropy loss. Extensive experimental comparison with previous state-of-the-arts on both object-level and scene-level datasets demonstrate the superior accuracy of our approach for surface reconstruction from un-orientated point clouds.


page 6

page 8

page 10

page 11

page 13

page 14

page 15

page 16


LightSAL: Lightweight Sign Agnostic Learning for Implicit Surface Representation

Recently, several works have addressed modeling of 3D shapes using deep ...

Learning Modified Indicator Functions for Surface Reconstruction

Surface reconstruction is a fundamental problem in 3D graphics. In this ...

Dynamic Plane Convolutional Occupancy Networks

Learning-based 3D reconstruction using implicit neural representations h...

Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstruction

This paper focuses on the task of 4D shape reconstruction from a sequenc...

ImpDet: Exploring Implicit Fields for 3D Object Detection

Conventional 3D object detection approaches concentrate on bounding boxe...

Semi-signed neural fitting for surface reconstruction from unoriented point clouds

Reconstructing 3D geometry from unoriented point clouds can benefit many...