The paper introduces Pix2Pose, a network that predicts per-pixel 3D coordinates from RGB images and uses them to compute 6D poses, with a new transformer loss for symmetric objects.
Deep learning of local rgb-d patches for 3d object detection and 6d pose estimation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation
The paper introduces Pix2Pose, a network that predicts per-pixel 3D coordinates from RGB images and uses them to compute 6D poses, with a new transformer loss for symmetric objects.