Crafting a multi-task CNN for viewpoint estimation

Abstract

Convolutional Neural Networks (CNNs) were recently shown to provide state-of-the-art results for object category viewpoint estimation. However different ways of formulating this problem have been proposed and the competing approaches have been explored with very different design choices. This paper presents a comparison of these approaches in a unified setting as well as a detailed analysis of the key factors that impact performance. Followingly, we present a new joint training method with the detection task and demonstrate its benefit. We also highlight the superiority of classification approaches over regression approaches, quantify the benefits of deeper architectures and extended training data, and demonstrate that synthetic data is beneficial even when using ImageNet training data. By combining all these elements, we demonstrate an improvement of approximately 5% mAVP over previous state-of-the-art results on the Pascal3D+ dataset. In particular for their most challenging 24 view classification task we improve the results from 31.1% to 36.1% mAVP.

To appear in BMVC 2016

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
• Viewpoints and Keypoints
• Convolutional Neural Networks for joint object detection and pose estimation: A comparative study

Cited by in corpus (8)

• Rethinking Reprojection: Closing the Loop for Pose-aware ShapeReconstruction from a Single Image
• The challenge of simultaneous object detection and pose estimation: a comparative study
• PointNetLK: Robust & Efficient Point Cloud Registration using PointNet
• ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving
• SampleAhead: Online Classifier-Sampler Communication for Learning from Synthesized Data
• A Mixed Classification-Regression Framework for 3D Pose Estimation from 2D Images
• Convolutional Networks for Object Category and 3D Pose Estimation from 2D Images
• Car Pose in Context: Accurate Pose Estimation with Ground Plane Constraints