Real-Time Seamless Single Shot 6D Object Pose Prediction

CVPR 2018  ·  Bugra Tekin, Sudipta N. Sinha, Pascal Fua ·

We propose a single-shot approach for simultaneously detecting an object in an RGB image and predicting its 6D pose without requiring multiple stages or having to examine multiple hypotheses. Unlike a recently proposed single-shot technique for this task (Kehl et al., ICCV'17) that only predicts an approximate 6D pose that must then be refined, ours is accurate enough not to require additional post-processing. As a result, it is much faster - 50 fps on a Titan X (Pascal) GPU - and more suitable for real-time processing. The key component of our method is a new CNN architecture inspired by the YOLO network design that directly predicts the 2D image locations of the projected vertices of the object's 3D bounding box. The object's 6D pose is then estimated using a PnP algorithm. For single object and multiple object pose estimation on the LINEMOD and OCCLUSION datasets, our approach substantially outperforms other recent CNN-based approaches when they are all used without post-processing. During post-processing, a pose refinement step can be used to boost the accuracy of the existing methods, but at 10 fps or less, they are much slower than our method.

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
6D Pose Estimation using RGB LineMOD Single-shot Deep CNN Accuracy 90.37% # 7
Mean ADD 55.95 # 16
Mean IoU 99.92 # 1
6D Pose Estimation using RGB OCCLUSION Single-shot deep CNN MAP 0.48 # 1
Drone Pose Estimation UAVA SingleShotPose Normalized Position Error 0.025 # 2
Orientation Error 0.07 # 2
Combined Pose Error 0.095 # 2

Methods


No methods listed for this paper. Add relevant methods here