Label transfer between images and 3D shapes via local correspondence encoding

DOI10.1016/J.CAGD.2019.04.009MaRDI QIDQ2010304zbMATH OpenOpenAlexWikidataFDO

Authors Jie Zhu, Yunfeng Zhang, Jie Guo, Huikun Liu, Mingming Liu, Yang Liu, Yanwen Guo

Publication date 27 November 2019

Published in Computer Aided Geometric Design (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.cagd.2019.04.009

zbMATH Keywords

segmentationbi-directionallabel transferlocal correspondence encoding

Mathematics Subject Classification ID

Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Computing methodologies for image processing (68U10) Computer science aspects of computer-aided design (68U07)

Recommendations

• Knowledge-based part correspondence
• Shape part transfer via semantic latent space factorization
• Learning part-based templates from large collections of 3D shapes
• Partial shape matching without point-wise correspondence
• EdgeNet: deep metric learning for 3D shapes

Cites work

• A survey on Mesh Segmentation Techniques
• Texture aware image segmentation using graph cuts and active contours
• Unsupervised 3D shape segmentation and co-segmentation via deep learning

Cited in

(2)

• 3D grasp saliency analysis via deep shape correspondence
• Shape part transfer via semantic latent space factorization

Describes a project that uses

Uses Software

• GrabCut
• ShapeNet
• DeconvNet

This page was built for publication: Label transfer between images and 3D shapes via local correspondence encoding

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2010304)