3D grasp saliency analysis via deep shape correspondence

DOI10.1016/J.CAGD.2020.101901MaRDI QIDQ2197929zbMATH OpenOpenAlexFDO

Authors Yanyan Li

Publication date 1 September 2020

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

Full work available at URL https://doi.org/10.1016/j.cagd.2020.101901

zbMATH Keywords

3D shapeglobal featureneural networksaliencyshape corresponding

Mathematics Subject Classification ID

Computer-aided design (modeling of curves and surfaces) (65D17) Computational issues in computer and robotic vision (65D19) Artificial neural networks and deep learning (68T07) Computer science aspects of computer-aided design (68U07)

Recommendations

• Learning continuous grasp affordances by sensorimotor exploration
• Learning 3D shape completion under weak supervision
• Multimodal features deep learning for robotic potential grasp recognition
• Multi-scale mesh saliency based on low-rank and sparse analysis in shape feature space
• Label transfer between images and 3D shapes via local correspondence encoding

Cites work

• Mesh saliency via spectral processing
• Multi-scale mesh saliency based on low-rank and sparse analysis in shape feature space

Cited in

(1)

• Physics-aware iterative learning and prediction of saliency map for bimanual grasp planning

Describes a project that uses

Uses Software

• PCPNet
• PointNet
• PointCNN

This page was built for publication: 3D grasp saliency analysis via deep shape correspondence

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2197929)