A Unified Framework for Multi-View Multi-Class Object Pose Estimation
Preprint
Abstract
One core challenge in object pose estimation is to ensure accurate and robust performance for large numbers of diverse foreground objects amidst complex background clutter. In this work, we present a scalable framework for accurately inferring six Degree-of-Freedom (6-DoF) pose for a large number of object classes from single or multiple views. To learn discriminative pose features, we integrate three new capabilities into a deep Convolutional Neural Network (CNN): an inference scheme that combines both classification and pose regression based on a uniform tessellation of the Special Euclidean group in three dimensions (SE(3)), the fusion of class priors into the training process via a tiled class map, and an additional regularization using deep supervision with an object mask. Further, an efficient multi-view framework is formulated to address single-view ambiguity. We show that this framework consistently improves the performance of the single-view network. We evaluate our method on three large-scale benchmarks: YCB-Video, JHUScene-50 and ObjectNet-3D. Our approach achieves competitive or superior performance over the current state-of-the-art methods.Keywords
All Related Versions
This publication has 35 references indexed in Scilit:
- Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimation2016
- ObjectNet3D: A Large Scale Database for 3D Object Recognition2016
- Integration of Probabilistic Pose Estimates from Multiple Views2016
- Learning descriptors for object recognition and 3D pose estimation2015
- Learning 6D Object Pose Estimation Using 3D Object Coordinates2014
- Latent-Class Hough Forests for 3D Object Detection and Pose Estimation2014
- SLAM++: Simultaneous Localisation and Mapping at the Level of Objects2013
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012
- Articulated pose estimation with flexible mixtures-of-parts2011
- Semantic 3D Object Maps for Everyday Manipulation in Human Living EnvironmentsKI - Künstliche Intelligenz, 2010