Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation

07/16/2020
by   Meng Tian, et al.
0

We present a novel learning approach to recover the 6D poses and sizes of unseen object instances from an RGB-D image. To handle the intra-class shape variation, we propose a deep network to reconstruct the 3D object model by explicitly modeling the deformation from a pre-learned categorical shape prior. Additionally, our network infers the dense correspondences between the depth observation of the object instance and the reconstructed 3D model to jointly estimate the 6D object pose and size. We design an autoencoder that trains on a collection of object models and compute the mean latent embedding for each category to learn the categorical shape priors. Extensive experiments on both synthetic and real-world datasets demonstrate that our approach significantly outperforms the state of the art. Our code is available at https://github.com/mentian/object-deformnet.

READ FULL TEXT

page 14

page 19

research
03/03/2022

CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation

This paper studies the complex task of simultaneous multi-object 3D reco...
research
07/12/2022

Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networks

It is difficult to precisely annotate object instances and their semanti...
research
09/17/2023

Uncertainty-aware 3D Object-Level Mapping with Deep Shape Priors

3D object-level mapping is a fundamental problem in robotics, which is e...
research
10/10/2021

6D-ViT: Category-Level 6D Object Pose Estimation via Transformer-based Instance Representation Learning

This paper presents 6D-ViT, a transformer-based instance representation ...
research
08/21/2023

CHORD: Category-level Hand-held Object Reconstruction via Shape Deformation

In daily life, humans utilize hands to manipulate objects. Modeling the ...
research
09/14/2022

Landmark-free Statistical Shape Modeling via Neural Flow Deformations

Statistical shape modeling aims at capturing shape variations of an anat...
research
01/19/2023

RGB-D-Based Categorical Object Pose and Shape Estimation: Methods, Datasets, and Evaluation

Recently, various methods for 6D pose and shape estimation of objects at...

Please sign up or login with your details

Forgot password? Click here to reset