Siamese Regression Networks with Efficient mid-level Feature Extraction for 3D Object Pose Estimation
arXiv:1607.02257
Abstract
In this paper we tackle the problem of estimating the 3D pose of object instances, using convolutional neural networks. State of the art methods usually solve the challenging problem of regression in angle space indirectly, focusing on learning discriminative features that are later fed into a separate architecture for 3D pose estimation. In contrast, we propose an end-to-end learning framework for directly regressing object poses by exploiting Siamese Networks. For a given image pair, we enforce a similarity measure between the representation of the sample images in the feature and pose space respectively, that is shown to boost regression performance. Furthermore, we argue that our pose-guided feature learning using our Siamese Regression Network generates more discriminative features that outperform the state of the art. Last, our feature learning formulation provides the ability of learning features that can perform under severe occlusions, demonstrating high performance on our novel hand-object dataset.
9 pages, paper submitted to NIPS 2016, project page: http://www.iis.ee.ic.ac.uk/rkouskou/research/SRN.html
References in corpus (1)
Cited by in corpus (12)
- PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
- Indoor Scene Understanding in 2.5/3D for Autonomous Agents: A Survey
- Deep 6-DOF Tracking
- Improving Cytoarchitectonic Segmentation of Human Brain Areas with Self-supervised Siamese Networks
- Towards Real-World Category-level Articulation Pose Estimation
- Deep Learning a Grasp Function for Grasping under Gripper Pose Uncertainty
- Twin Neural Network Regression
- Probabilistic orientation estimation with matrix Fisher distributions
- 6D Object Pose Estimation without PnP
- Sports Camera Calibration via Synthetic Data
- 3D Human Pose Estimation with Siamese Equivariant Embedding
- LyRN (Lyapunov Reaching Network): A Real-Time Closed Loop approach from Monocular Vision