Conditional Link Prediction of Category-Implicit Keypoint Detection
This work provides a more efficient and effective method for keypoint detection and link prediction, which is crucial for computer vision tasks involving object understanding and pose estimation, particularly for multi-class objects and occluded scenarios.
The paper addresses the problem of simultaneous semantic keypoint detection and connection link prediction for multi-class instances, which existing methods struggle with due to computational intensity and inability to encode connection information. The proposed KLPNet, an end-to-end network, achieves state-of-the-art performance on three public benchmarks and demonstrates effectiveness in handling occlusion problems for connection link prediction.
Keypoints of objects reflect their concise abstractions, while the corresponding connection links (CL) build the skeleton by detecting the intrinsic relations between keypoints. Existing approaches are typically computationally-intensive, inapplicable for instances belonging to multiple classes, and/or infeasible to simultaneously encode connection information. To address the aforementioned issues, we propose an end-to-end category-implicit Keypoint and Link Prediction Network (KLPNet), which is the first approach for simultaneous semantic keypoint detection (for multi-class instances) and CL rejuvenation. In our KLPNet, a novel Conditional Link Prediction Graph is proposed for link prediction among keypoints that are contingent on a predefined category. Furthermore, a Cross-stage Keypoint Localization Module (CKLM) is introduced to explore feature aggregation for coarse-to-fine keypoint localization. Comprehensive experiments conducted on three publicly available benchmarks demonstrate that our KLPNet consistently outperforms all other state-of-the-art approaches. Furthermore, the experimental results of CL prediction also show the effectiveness of our KLPNet with respect to occlusion problems.