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

05/08/2021
by   Jiapeng Tang, et al.
3

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.

READ FULL TEXT

page 6

page 8

page 10

page 11

page 13

page 14

page 15

page 16

research
12/14/2020

Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point Clouds

Shape modeling and reconstruction from raw point clouds of objects stand...
research
03/26/2021

LightSAL: Lightweight Sign Agnostic Learning for Implicit Surface Representation

Recently, several works have addressed modeling of 3D shapes using deep ...
research
08/18/2023

Reach For the Spheres: Tangency-Aware Surface Reconstruction of SDFs

Signed distance fields (SDFs) are a widely used implicit surface represe...
research
11/11/2020

Dynamic Plane Convolutional Occupancy Networks

Learning-based 3D reconstruction using implicit neural representations h...
research
03/30/2021

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...
research
06/18/2021

Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching

Reconstruction of object or scene surfaces has tremendous applications i...
research
03/31/2022

ImpDet: Exploring Implicit Fields for 3D Object Detection

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

Please sign up or login with your details

Forgot password? Click here to reset