FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation
Authors:
Top Cited Papers
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3002-3012
Abstract
In this work, we present FFB6D, a Full Flow Bidirectional fusion network designed for 6D pose estimation from a single RGBD image. Our key insight is that appearance information in the RGB image and geometry information from the depth image are two complementary data sources, and it still remains unknown how to fully leverage them. Towards this end, we propose FFB6D, which learns to combine appearance and geometry information for representation learning as well as output representation selection. Specifically, at the representation learning stage, we build bidirectional fusion modules in the full flow of the two networks, where fusion is applied to each encoding and decoding layer. In this way, the two networks can leverage local and global complementary in-formation from the other one to obtain better representations. Moreover, at the output representation stage, we designed a simple but effective 3D keypoints selection algorithm considering the texture and geometry information of objects, which simplifies keypoint localization for precise pose estimation. Experimental results show that our method outperforms the state-of-the-art by large margins on several benchmarks. Code and video are available at https://github.com/ethnhe/FFB6D.git.Keywords
All Related Versions
This publication has 55 references indexed in Scilit:
- Pose Estimation for Augmented Reality: A Hands-On SurveyIEEE Transactions on Visualization and Computer Graphics, 2015
- The YCB object and Model set: Towards common benchmarks for manipulation research2015
- Learning descriptors for object recognition and 3D pose estimation2015
- Discriminatively Trained Templates for 3D Object Detection: A Real Time Scalable Approach2013
- The MOPED framework: Object recognition and pose estimation for manipulationThe International Journal of Robotics Research, 2011
- Depth-Encoded Hough Voting for Joint Object Detection and Shape Recovery2010
- 3D Object Modeling and Recognition Using Local Affine-Invariant Image Descriptors and Multi-View Spatial ConstraintsInternational Journal of Computer Vision, 2006
- Mean shift: a robust approach toward feature space analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Object recognition from local scale-invariant features1999
- Comparing images using the Hausdorff distanceIEEE Transactions on Pattern Analysis and Machine Intelligence, 1993