Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting

About

While 6D object pose estimation has recently made a huge leap forward, most methods can still only handle a single or a handful of different objects, which limits their applications. To circumvent this problem, category-level object pose estimation has recently been revamped, which aims at predicting the 6D pose as well as the 3D metric size for previously unseen instances from a given set of object classes. This is, however, a much more challenging task due to severe intra-class shape variations. To address this issue, we propose GPV-Pose, a novel framework for robust category-level pose estimation, harnessing geometric insights to enhance the learning of category-level pose-sensitive features. First, we introduce a decoupled confidence-driven rotation representation, which allows geometry-aware recovery of the associated rotation matrix. Second, we propose a novel geometry-guided point-wise voting paradigm for robust retrieval of the 3D object bounding box. Finally, leveraging these different output streams, we can enforce several geometric consistency terms, further increasing performance, especially for non-symmetric categories. GPV-Pose produces superior results to state-of-the-art competitors on common public benchmarks, whilst almost achieving real-time inference speed at 20 FPS.

Yan Di, Ruida Zhang, Zhiqiang Lou, Fabian Manhardt, Xiangyang Ji, Nassir Navab, Federico Tombari• 2022

Related benchmarks

TaskDatasetResultRank
Category-level 6D Pose EstimationREAL275 (test)
Pose Acc (5°/5cm)44.2
53
6D Pose and Size EstimationREAL275
5°5cm0.429
50
Category-level 6D Object Pose EstimationREAL275
mAP (5°5cm)42.9
16
6D Pose EstimationLineMOD
ADD (S)98.2
16
Category-level 6D Object Pose EstimationCamera
mAP (5°2cm)72.1
13
Category-level Object Pose EstimationCamera
Success Rate (5° 2cm)72.1
12
6D Object Pose EstimationCAMERA25
IoU@7588.3
9
Category-level Object Pose and Size EstimationREAL275
IoU@2584.2
8
Category-level 6D Object Pose EstimationShapeNet-C (test)
Rotation Mean Error (°)50.95
7
Category-level Object Pose EstimationCAMERA25
IoU@5093.4
5
Showing 10 of 12 rows

Other info

Code

Follow for update