i2c-net: Using Instance-Level Neural Networks for Monocular Category-Level 6D Pose Estimation
Open Access
- 27 January 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (3) , 1515-1522
Abstract
Object detection and pose estimation are strict requirements for many robotic grasping and manipulation applications to endow robots with the ability to grasp objects with different properties in cluttered scenes and with various lighting conditions. This work proposes the framework i2c-net to extract the 6D pose of multiple objects belonging to different categories, starting from an instance-level pose estimation network and relying only on RGB images. The network is trained on a custom-made synthetic photo-realistic dataset, generated from some base CAD models, opportunely deformed, and enriched with real textures for domain randomization purposes. At inference time, the instance-level network is employed in combination with a 3D mesh reconstruction module, achieving category-level capabilities. Depth information is used for post-processing as a correction. Tests conducted on real objects of the YCB-V and NOCS-REAL datasets outline the high accuracy of the proposed approach.Keywords
Funding Information
- Leonardo Company S.p.A. (LDO/CTI/P/0026995/21)
This publication has 26 references indexed in Scilit:
- A study on picking objects in cluttered environments: Exploiting depth features for a custom low-cost universal jamming gripperRobotics and Computer-Integrated Manufacturing, 2020
- Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation2019
- DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation2019
- Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images2018
- PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes2018
- Real-Time Seamless Single Shot 6D Object Pose Prediction2018
- Progress and prospects of the human–robot collaborationAutonomous Robots, 2017
- Deep Residual Learning for Image Recognition2016
- Weak Perspective Projection2014
- A method for registration of 3-D shapesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992