Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimation

by   Markus Oberweger, et al.

We introduce a novel method for robust and accurate 3D object pose estimation from single color images under large occlusions. Following recent approaches, we first predict the 2D reprojections of 3D points related to the target object and then compute the 3D pose from these correspondences using a geometric method. Unfortunately, as our experiments show, predicting these 2D reprojections using a regular CNN or a Convolutional Pose Machine is very sensitive to partial occlusions, even when these methods are trained with partially occluded examples. Our solution is to predict heatmaps from multiple small patches independently and to accumulate the results to obtain accurate and robust predictions. Training then becomes challenging because patches with similar appearances but different positions on the object correspond to different heatmaps. However, we provide a simple yet effective solution to deal with such ambiguities. We show that our approach outperforms existing methods on two challenging datasets: The Occluded LineMOD dataset, and the YCB-Video dataset, both exhibiting cluttered scenes with highly occluded objects. Project website:


page 2

page 3

page 10

page 13

page 19

page 20

page 23

page 24


BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth

We introduce a novel method for 3D object detection and pose estimation ...

Segmentation-driven 6D Object Pose Estimation

The most recent trend in estimating the 6D pose of rigid objects has bee...

Now You See Me: Robust approach to Partial Occlusions

Occlusions of objects is one of the indispensable problems in Computer v...

Iterative Hough Forest with Histogram of Control Points for 6 DoF Object Registration from Depth Images

State-of-the-art techniques proposed for 6D object pose recovery depend ...

Occlusion-Robust Object Pose Estimation with Holistic Representation

Practical object pose estimation demands robustness against occlusions t...

HandsFormer: Keypoint Transformer for Monocular 3D Pose Estimation ofHands and Object in Interaction

We propose a robust and accurate method for estimating the 3D poses of t...

Latent-Class Hough Forests for 6 DoF Object Pose Estimation

In this paper we present Latent-Class Hough Forests, a method for object...

Please sign up or login with your details

Forgot password? Click here to reset