Is 2D Information Enough For Viewpoint Estimation?

Recent top performing methods for viewpoint estimation make use of 3D information like 3D CAD models or 3D landmarks to build a 3D representation of the class. These 3D annotations are expensive and not really available for many classes. In this paper we investigate whether and how comparable performance can be obtained without any 3D information. We consider viewpoint estimation as a 1-vs-all classification problem on the previously detected object bounding box. In this framework we compare several features and parameter configurations and show that the modern representations based on Fisher encoding and convolutional neural network based features together with a neighbor viewpoints suppression strategy on the training data lead to comparable or even better performance than 3D methods.

[1]  David Haussler,et al.  Exploiting Generative Models in Discriminative Classifiers , 1998, NIPS.

[2]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[3]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[4]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[5]  Silvio Savarese,et al.  3D generic object categorization, localization and pose estimation , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[6]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[7]  Silvio Savarese,et al.  A multi-view probabilistic model for 3D object classes , 2009, CVPR.

[8]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Silvio Savarese,et al.  Learning a dense multi-view representation for detection, viewpoint classification and synthesis of object categories , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[10]  Ronen Basri,et al.  Constructing implicit 3D shape models for pose estimation , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[11]  A multi-view probabilistic model for 3D object classes , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  P. Fua,et al.  Pose estimation for category specific multiview object localization , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Cordelia Schmid,et al.  Multi-view object class detection with a 3D geometric model , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[14]  Thomas Mensink,et al.  Improving the Fisher Kernel for Large-Scale Image Classification , 2010, ECCV.

[15]  Michael Goesele,et al.  Back to the Future: Learning Shape Models from 3D CAD Data , 2010, BMVC.

[16]  Xiaofeng Ren,et al.  Discriminative Mixture-of-Templates for Viewpoint Classification , 2010, ECCV.

[17]  Takeo Kanade,et al.  Multi-PIE , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[18]  Silvio Savarese,et al.  Deformable part models revisited: A performance evaluation for object category pose estimation , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[19]  Luc Van Gool,et al.  Real time head pose estimation with random regression forests , 2011, CVPR 2011.

[20]  Ronen Basri,et al.  Viewpoint-aware object detection and pose estimation , 2011, 2011 International Conference on Computer Vision.

[21]  Sinisa Todorovic,et al.  From contours to 3D object detection and pose estimation , 2011, 2011 International Conference on Computer Vision.

[22]  Cristian Sminchisescu,et al.  Semantic Segmentation with Second-Order Pooling , 2012, ECCV.

[23]  Peter V. Gehler,et al.  3D2PM - 3D Deformable Part Models , 2012, ECCV.

[24]  Deva Ramanan,et al.  Analyzing 3D Objects in Cluttered Images , 2012, NIPS.

[25]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[26]  Peter V. Gehler,et al.  Teaching 3D geometry to deformable part models , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[27]  Deva Ramanan,et al.  Face detection, pose estimation, and landmark localization in the wild , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Bernt Schiele,et al.  Detailed 3D Representations for Object Recognition and Modeling , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Andrew Zisserman,et al.  Fisher Vector Faces in the Wild , 2013, BMVC.

[30]  Christian Szegedy,et al.  DeepPose: Human Pose Estimation via Deep Neural Networks , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[31]  Luc Van Gool,et al.  Face Detection without Bells and Whistles , 2014, ECCV.

[32]  Jonathan Tompson,et al.  Learning Human Pose Estimation Features with Convolutional Networks , 2013, ICLR.

[33]  Silvio Savarese,et al.  Beyond PASCAL: A benchmark for 3D object detection in the wild , 2014, IEEE Winter Conference on Applications of Computer Vision.

[34]  Stefan Carlsson,et al.  CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[35]  Tinne Tuytelaars,et al.  All together now: Simultaneous Detection and Continuous Pose Estimation using a Hough Forest with Probabilistic Locally Enhanced Voting , 2014, BMVC.

[36]  Carolina Redondo-Cabrera.  REDONDO-CABRERA ET AL.: CONTINUOUS POSE ESTIMATION WITH HOUGH FOREST 1 All together now: Simultaneous Object Detection and Continuous Pose Estimation using a Hough Forest with Probabilistic Locally Enhanced Voting , 2014 .

[37]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

[38]  Seung Woo Lee,et al.  Birdsnap: Large-Scale Fine-Grained Visual Categorization of Birds , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[39]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.