SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again

@article{Kehl2017SSD6DMR,
  title={SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again},
  author={Wadim Kehl and Fabian Manhardt and Federico Tombari and Slobodan Ilic and Nassir Navab},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={1530-1538}
}
We present a novel method for detecting 3D model instances and estimating their 6D poses from RGB data in a single shot. To this end, we extend the popular SSD paradigm to cover the full 6D pose space and train on synthetic model data only. Our approach competes or surpasses current state-of-the-art methods that leverage RGBD data on multiple challenging datasets. Furthermore, our method produces these results at around 10Hz, which is many times faster than the related methods. For the sake of… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 83 CITATIONS, ESTIMATED 43% COVERAGE

Instance- and Category-level 6D Object Pose Estimation

VIEW 11 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

DPOD: 6D Pose Object Detector and Refiner.

VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion

  • ArXiv
  • 2019
VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Deep Model-Based 6D Pose Refinement in RGB

VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Deep-6DPose: Recovering 6D Object Pose from a Single RGB Image

VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

DeepIM: Deep Iterative Matching for 6D Pose Estimation

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Feature Mapping for Learning Fast and Accurate 3D Pose Inference from Synthetic Images

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
VIEW 9 EXCERPTS
CITES RESULTS, METHODS & BACKGROUND
HIGHLY INFLUENCED

Intelligent Multimodal Framework for Human Assistive Robotics Based on Computer Vision Algorithms

VIEW 8 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2017
2019

CITATION STATISTICS

  • 30 Highly Influenced Citations

  • Averaged 29 Citations per year over the last 3 years

  • 96% Increase in citations per year in 2018 over 2017

References

Publications referenced by this paper.
SHOWING 1-10 OF 37 REFERENCES

Model Based Training

S. Hinterstoisser, V. Lepetit, +4 authors N. Navab
  • Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes. In ACCV
  • 2012
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

S

W. Liu, D. Anguelov, D. Erhan, C. Szegedy
  • Reed, C.-y. Fu, and A. C. Berg. SSD : Single Shot MultiBox Detector. In ECCV
  • 2016
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

R

A. Tejani, D. Tang
  • Kouskouridas, and T.-k. Kim. Latentclass hough forests for 3D object detection and pose estimation. In ECCV
  • 2014
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

3D Bounding Box Estimation Using Deep Learning and Geometry

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
VIEW 2 EXCERPTS

Feature Pyramid Networks for Object Detection

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
VIEW 1 EXCERPT

Fast Single Shot Detection and Pose Estimation

  • 2016 Fourth International Conference on 3D Vision (3DV)
  • 2016
VIEW 2 EXCERPTS

Inception-v4

C. Szegedy, S. Ioffe, V. Vanhoucke
  • Inception-ResNet and the Impact of Residual Connections on Learning. arxiv:1602.07261
  • 2016
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…