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

StarMap for Category-Agnostic Keypoint and Viewpoint Estimation

About

Semantic keypoints provide concise abstractions for a variety of visual understanding tasks. Existing methods define semantic keypoints separately for each category with a fixed number of semantic labels in fixed indices. As a result, this keypoint representation is in-feasible when objects have a varying number of parts, e.g. chairs with varying number of legs. We propose a category-agnostic keypoint representation, which combines a multi-peak heatmap (StarMap) for all the keypoints and their corresponding features as 3D locations in the canonical viewpoint (CanViewFeature) defined for each instance. Our intuition is that the 3D locations of the keypoints in canonical object views contain rich semantic and compositional information. Using our flexible representation, we demonstrate competitive performance in keypoint detection and localization compared to category-specific state-of-the-art methods. Moreover, we show that when augmented with an additional depth channel (DepthMap) to lift the 2D keypoints to 3D, our representation can achieve state-of-the-art results in viewpoint estimation. Finally, we show that our category-agnostic keypoint representation can be generalized to novel categories.

Xingyi Zhou, Arjun Karpur, Linjie Luo, Qixing Huang• 2018

Related benchmarks

TaskDatasetResultRank
2D Human Pose EstimationMPII (val)
Head92.12
61
2D Keypoint LocalizationPASCAL3D+ (test)
Aero Acc93.1
6
Joint Object Detection and Viewpoint EstimationObjectNet3D Intra-dataset
Bed Accuracy32
6
Joint Object Detection and Viewpoint EstimationPascal3D+ Inter-dataset
Aero Score0.03
6
3D Object Pose EstimationPASCAL3D+
Aeroplane Accuracy83.2
5
Viewpoint EstimationObjectNet3D 20 novel classes Intra-dataset 10-shot
Acc (30 deg)46
5
Viewpoint EstimationPascal3D+ 12 novel classes
Accuracy (30 deg)28
5
3D Pose EstimationPASCAL3D+
Bicycle 30° Acc83.2
4
Viewpoint EstimationPascal3D+ novel categories 44
Motorcycle Viewpoint Accuracy55
4
Keypoint ClassificationPascal3D+ 44 (test)
Accuracy (Aero)0.77
3
Showing 10 of 12 rows

Other info

Code

Follow for update