Topology-Aware Single-Image 3D Shape Reconstruction

We make an attempt to address topology-awareness for 3D shape reconstruction. Two types of high-level shape typologies are being studied here, namely genus (number of cuttings/holes) and connectivity (number of connected components), which are of great importance in 3D object reconstruction/understa...

Full description

Saved in:
Bibliographic Details
Main Authors: Chen, Qimin, Nguyen, Vincent, Han, Feng, Kiveris, Raimondas, Tu, Zhuowen
Format: Conference Proceeding
Language:English
Subjects:
Decoding
Image reconstruction
Shape
Three-dimensional displays
Topology
Training
Two dimensional displays
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We make an attempt to address topology-awareness for 3D shape reconstruction. Two types of high-level shape typologies are being studied here, namely genus (number of cuttings/holes) and connectivity (number of connected components), which are of great importance in 3D object reconstruction/understanding but have been thus far disjoint from the existing dense voxel-wise prediction literature. We propose a topology-aware shape autoencoder component (TPWCoder) by approximating topology property functions such as genus and connectivity with neural networks from the latent variables. TPWCoder can be directly combined with the existing 3D shape reconstruction pipelines for end-to-end training and prediction. On the challenging A Big CAD Model Dataset (ABC), TPWCoder demonstrates a noticeable quantitative and qualitative improvement over the competing methods, and it also shows improved quantitative result on the ShapeNet dataset.
ISSN:2160-7516
DOI:10.1109/CVPRW50498.2020.00143