DeepAI AI Chat
Log In Sign Up

Object Shell Reconstruction: Camera-centric Object Representation for Robotic Grasping

by   Nikhil Chavan Dafle, et al.

Robots can effectively grasp and manipulate objects using their 3D models. In this paper, we propose a simple shape representation and a reconstruction method that outperforms state-of-the-art methods in terms of geometric metrics and enables grasp generation with high precision and success. Our reconstruction method models the object geometry as a pair of depth images, composing the "shell" of the object. This representation allows using image-to-image residual ConvNet architectures for 3D reconstruction, generates object reconstruction directly in the camera frame, and generalizes well to novel object types. Moreover, an object shell can be converted into an object mesh in a fraction of a second, providing time and memory efficient alternative to voxel or implicit representations. We explore the application of shell representation for grasp planning. With rigorous experimental validation, both in simulation and on a real setup, we show that shell reconstruction encapsulates sufficient geometric information to generate precise grasps and the associated grasp quality with over 90 shell reconstructions allow the robot to select and execute grasps in cluttered scenes with more than 93


page 8

page 9

page 12

page 14

page 15

page 16

page 17

page 18


Robotic Grasping through Combined image-Based Grasp Proposal and 3D Reconstruction

We present a novel approach to robotic grasp planning using both a learn...

Learning Continuous 3D Reconstructions for Geometrically Aware Grasping

Deep learning has enabled remarkable improvements in grasp synthesis for...

UV-Based 3D Hand-Object Reconstruction with Grasp Optimization

We propose a novel framework for 3D hand shape reconstruction and hand-o...

Active Visuo-Haptic Object Shape Completion

Recent advancements in object shape completion have enabled impressive o...

6-DoF Grasp Planning using Fast 3D Reconstruction and Grasp Quality CNN

Recent consumer demand for home robots has accelerated performance of ro...

Improving Grasp Planning Efficiency with Human Grasp Tendencies*

After a grasp has been planned, if the object orientation changes, the i...

Gradient-SDF: A Semi-Implicit Surface Representation for 3D Reconstruction

We present Gradient-SDF, a novel representation for 3D geometry that com...