6-DoF Object Pose from Semantic Keypoints

14 Mar 2017Georgios PavlakosXiaowei ZhouAaron ChanKonstantinos G. DerpanisKostas Daniilidis

This paper presents a novel approach to estimating the continuous six degree of freedom (6-DoF) pose (3D translation and rotation) of an object from a single RGB image. The approach combines semantic keypoints predicted by a convolutional network (convnet) with a deformable shape model... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Keypoint Detection Pascal3D+ ConvNet + deformable shape model Mean PCK 82.5 # 1