Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks

07/23/2018
by   Kripasindhu Sarkar, et al.
2

We present a novel global representation of 3D shapes, suitable for the application of 2D CNNs. We represent 3D shapes as multi-layered height-maps (MLH) where at each grid location, we store multiple instances of height maps, thereby representing 3D shape detail that is hidden behind several layers of occlusion. We provide a novel view merging method for combining view dependent information (Eg. MLH descriptors) from multiple views. Because of the ability of using 2D CNNs, our method is highly memory efficient in terms of input resolution compared to the voxel based input. Together with MLH descriptors and our multi view merging we achieve the state-of-the-art result in classification on ModelNet dataset.

READ FULL TEXT

page 4

page 18

page 19

page 23

research
05/05/2015

Multi-view Convolutional Neural Networks for 3D Shape Recognition

A longstanding question in computer vision concerns the representation o...
research
07/20/2017

3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks

We propose a method for reconstructing 3D shapes from 2D sketches in the...
research
10/17/2020

MeshMVS: Multi-View Stereo Guided Mesh Reconstruction

Deep learning based 3D shape generation methods generally utilize latent...
research
09/07/2020

Improved Modeling of 3D Shapes with Multi-view Depth Maps

We present a simple yet effective general-purpose framework for modeling...
research
03/29/2023

CN-DHF: Compact Neural Double Height-Field Representations of 3D Shapes

We introduce CN-DHF (Compact Neural Double-Height-Field), a novel hybrid...
research
03/25/2019

Structured 2D Representation of 3D Data for Shape Processing

We represent 3D shape by structured 2D representations of fixed length m...
research
11/21/2020

Height Prediction and Refinement from Aerial Images with Semantic and Geometric Guidance

Deep learning provides a powerful new approach to many computer vision t...

Please sign up or login with your details

Forgot password? Click here to reset