Dynamic Plane Convolutional Occupancy Networks

11/11/2020
by   Stefan Lionar, et al.
11

Learning-based 3D reconstruction using implicit neural representations has shown promising progress not only at the object level but also in more complicated scenes. In this paper, we propose Dynamic Plane Convolutional Occupancy Networks, a novel implicit representation pushing further the quality of 3D surface reconstruction. The input noisy point clouds are encoded into per-point features that are projected onto multiple 2D dynamic planes. A fully-connected network learns to predict plane parameters that best describe the shapes of objects or scenes. To further exploit translational equivariance, convolutional neural networks are applied to process the plane features. Our method shows superior performance in surface reconstruction from unoriented point clouds in ShapeNet as well as an indoor scene dataset. Moreover, we also provide interesting observations on the distribution of learned dynamic planes.

READ FULL TEXT
research
03/10/2020

Convolutional Occupancy Networks

Recently, implicit neural representations have gained popularity for lea...
research
11/18/2019

TSRNet: Scalable 3D Surface Reconstruction Network for Point Clouds using Tangent Convolution

Existing learning-based surface reconstruction methods from point clouds...
research
03/01/2023

P^2SDF for Neural Indoor Scene Reconstruction

Given only a set of images, neural implicit surface representation has s...
research
10/02/2022

Neural Implicit Surface Reconstruction from Noisy Camera Observations

Representing 3D objects and scenes with neural radiance fields has becom...
research
05/08/2021

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

Surface reconstruction from point clouds is a fundamental problem in the...
research
04/05/2023

Dynamic Point Fields

Recent years have witnessed significant progress in the field of neural ...
research
03/31/2021

RetrievalFuse: Neural 3D Scene Reconstruction with a Database

3D reconstruction of large scenes is a challenging problem due to the hi...

Please sign up or login with your details

Forgot password? Click here to reset