# Fast Single Shot Detection and Pose Estimation

arXiv: https://arxiv.org/abs/1609.05590 · HTML: https://mlsanity.com/paper/1609.05590/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2016.

## Built on by (most cited first, 11 of 11)

- [M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation](https://mlsanity.com/paper/2204.05088/) (2022)
- [Translating Images into Maps](https://mlsanity.com/paper/2110.00966/) (2021)
- [Voxel-based 3D Detection and Reconstruction of Multiple Objects from a Single Image](https://mlsanity.com/paper/2111.03098/) (2021)
- [HFT: Lifting Perspective Representations via Hybrid Feature Transformation](https://mlsanity.com/paper/2204.05068/) (2022)
- [Parametric Depth Based Feature Representation Learning for Object Detection and Segmentation in Bird's Eye View](https://mlsanity.com/paper/2307.04106/) (2023)
- [Occlusion-Robust Object Pose Estimation with Holistic Representation](https://mlsanity.com/paper/2110.11636/) (2021)
- ["The Pedestrian next to the Lamppost" Adaptive Object Graphs for Better Instantaneous Mapping](https://mlsanity.com/paper/2204.02944/) (2022)
- [Spatial Feature Mapping for 6DoF Object Pose Estimation](https://mlsanity.com/paper/2206.01831/) (2022)
- [Object Pose Estimation using Mid-level Visual Representations](https://mlsanity.com/paper/2203.01449/) (2022)
- [Semantic Image Cropping](https://mlsanity.com/paper/2107.07153/) (2021)
- [Review on 6D Object Pose Estimation with the focus on Indoor Scene Understanding](https://mlsanity.com/paper/2212.01920/) (2022)

## Abstract (arXiv)

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.