Multi-Scale Supervised Network for Human Pose Estimation
Human pose estimation is an important topic in computer vision with many applications including gesture and activity recognition. However, pose estimation from image is challenging due to appearance variations, occlusions, clutter background, and complex activities. To alleviate these problems, we develop a robust pose estimation method based on the recent deep conv-deconv modules with two improvements: (1) multi-scale supervision of body keypoints, and (2) a global regression to improve structural consistency of keypoints. We refine keypoint detection heatmaps using layer-wise multi-scale supervision to better capture local contexts. Pose inference via keypoint association is optimized globally using a regression network at the end. Our method can effectively disambiguate keypoint matches in close proximity including the mismatch of left-right body parts, and better infer occluded parts. Experimental results show that our method achieves competitive performance among state-of-the-art methods on the MPII and FLIC datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Activity RecognitionKeypoint DetectionPose EstimationregressionSimilar Papers 제목 키워드 기반
X as Supervision: Contending with Depth Ambiguity in Unsupervised Monocular 3D Pose Estimation
Recent unsupervised methods for monocular 3D pose estimation have endeavored to reduce dependence on limited annotated 3D data, but most are solely formulated in 2D space, overlooking the inherent depth ambiguity issue. …
3D Pose EstimationPose EstimationKinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimation
Estimation of 3D human pose from monocular image has gained considerable attention, as a key step to several human-centric applications. However, generalizability of human pose estimation models developed using supervisi…
3D Human Pose Estimation3D Pose EstimationDisentanglementPose Estimation+1Towards Alleviating the Modeling Ambiguity of Unsupervised Monocular 3D Human Pose Estimation
In this work, we study the ambiguity problem in the task of unsupervised 3D human pose estimation from 2D counterpart. On one hand, without explicit annotation, the scale of 3D pose is difficult to be accurately capt…
3D Human Pose EstimationMonocular 3D Human Pose EstimationPose EstimationUnsupervised 3D Human Pose EstimationUnsupervised Multi-Person 3D Human Pose Estimation From 2D Poses Alone
Current unsupervised 2D-3D human pose estimation (HPE) methods do not work in multi-person scenarios due to perspective ambiguity in monocular images. Therefore, we present one of the first studies investigating the feas…
3D Human Pose Estimation3D Pose Estimation3D ReconstructionPose EstimationSelf-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos
Video annotation is expensive and time consuming. Consequently, datasets for multi-person pose estimation and tracking are less diverse and have more sparse annotations compared to large scale image datasets for human po…
Multi-Person Pose EstimationMulti-Person Pose Estimation and TrackingPose EstimationPose Tracking