PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learning

State-of-the-art computer vision algorithms often achieve efficiency by making discrete choices about which hypotheses to explore next. This allows allocation of computational resources to promising candidates, however, such decisions are non-differentiable. As a result, these algorithms are hard to train in an end-to-end fashion. In this work we propose to learn an efficient algorithm for the task of 6D object pose estimation. Our system optimizes the parameters of an existing state-of-the art pose estimation system using reinforcement learning, where the pose estimation system now becomes the stochastic policy, parametrized by a CNN. Additionally, we present an efficient training algorithm that dramatically reduces computation time. We show empirically that our learned pose estimation procedure makes better use of limited resources and improves upon the state-of-the-art on a challenging dataset. Our approach enables differentiable end-to-end training of complex algorithmic pipelines and learns to make optimal use of a given computational budget.

[1]  W. Kabsch.  A solution for the best rotation to relate two sets of vectors , 1976 .

[2]  Eric Brachmann,et al.  6-DOF Model Based Tracking via Object Coordinate Regression , 2014, ACCV.

[3]  Svetlana Lazebnik,et al.  Active Object Localization with Deep Reinforcement Learning , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[4]  Vincent Lepetit,et al.  Going Further with Point Pair Features , 2016, ECCV.

[5]  Andrew W. Fitzgibbon,et al.  Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Eric Brachmann,et al.  Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Alex Graves,et al.  Recurrent Models of Visual Attention , 2014, NIPS.

[8]  Andrew W. Fitzgibbon,et al.  The Vitruvian manifold: Inferring dense correspondences for one-shot human pose estimation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Pieter Abbeel,et al.  An Application of Reinforcement Learning to Aerobatic Helicopter Flight , 2006, NIPS.

[10]  Nassir Navab,et al.  Model globally, match locally: Efficient and robust 3D object recognition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Leslie Pack Kaelbling,et al.  Effective reinforcement learning for mobile robots , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[12]  Vincent Lepetit,et al.  Model Based Training, Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes , 2012, ACCV.

[13]  Eric Brachmann,et al.  Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Images , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[14]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[15]  Tinne Tuytelaars,et al.  Discriminatively Trained Templates for 3D Object Detection: A Real Time Scalable Approach , 2013, 2013 IEEE International Conference on Computer Vision.

[16]  Eric Brachmann,et al.  Learning 6D Object Pose Estimation Using 3D Object Coordinates , 2014, ECCV.

[17]  Peter L. Bartlett,et al.  Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning , 2001, J. Mach. Learn. Res..

[18]  David G. Lowe,et al.  Local feature view clustering for 3D object recognition , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[19]  Siddhartha S. Srinivasa,et al.  MOPED: A scalable and low latency object recognition and pose estimation system , 2010, 2010 IEEE International Conference on Robotics and Automation.

[20]  Eric Brachmann,et al.  Pose Estimation of Kinematic Chain Instances via Object Coordinate Regression , 2015, BMVC.

[21]  Jitendra Malik,et al.  Inferring 3D Object Pose in RGB-D Images , 2015, ArXiv.

[22]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[23]  Cristian Sminchisescu,et al.  Reinforcement Learning for Visual Object Detection , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Koray Kavukcuoglu,et al.  Multiple Object Recognition with Visual Attention , 2014, ICLR.

[25]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[26]  Yishay Mansour,et al.  Policy Gradient Methods for Reinforcement Learning with Function Approximation , 1999, NIPS.