Fast Single Shot Detection and Pose Estimation

TL;DR

This paper introduces a fast, single-shot deep learning system that simultaneously detects objects and estimates their rough 3D pose in real-time, suitable for robotics and navigation tasks.

Contribution

It presents the first unified deep learning approach combining detection and pose estimation at the same level without intermediate steps.

Findings

Achieves 42.4% 8 View mAVP on Pascal 3D+

Operates at 46 FPS on a TITAN X GPU

Comparable accuracy to recent pose estimation methods

Abstract

For applications in navigation and robotics, estimating the 3D pose of objects is as important as detection. Many approaches to pose estimation rely on detecting or tracking parts or keypoints [11, 21]. In this paper we build on a recent state-of-the-art convolutional network for slidingwindow detection [10] to provide detection and rough pose estimation in a single shot, without intermediate stages of detecting parts or initial bounding boxes. While not the first system to treat pose estimation as a categorization problem, this is the first attempt to combine detection and pose estimation at the same level using a deep learning approach. The key to the architecture is a deep convolutional network where scores for the presence of an object category, the offset for its location, and the approximate pose are all estimated on a regular grid of locations in the image. The resulting system is as accurate as recent work on pose estimation (42.4% 8 View mAVP on Pascal 3D+ [21] ) and significantly faster (46 frames per second (FPS) on a TITAN X GPU). This approach to detection and rough pose estimation is fast and accurate enough to be widely applied as a pre-processing step for tasks including high-accuracy pose estimation, object tracking and localization, and vSLAM.