Exploiting temporal context for 3D human pose estimation in the wild
We present a bundle-adjustment-based algorithm for recovering accurate 3D human pose and meshes from monocular videos. Unlike previous algorithms which operate on single frames, we show that reconstructing a person over an entire sequence gives extra constraints that can resolve ambiguities. This is because videos often give multiple views of a person, yet the overall body shape does not change and 3D positions vary slowly. Our method improves not only on standard mocap-based datasets like Human 3.6M -- where we show quantitative improvements -- but also on challenging in-the-wild datasets such as Kinetics. Building upon our algorithm, we present a new dataset of more than 3 million frames of YouTube videos from Kinetics with automatically generated 3D poses and meshes. We show that retraining a single-frame 3D pose estimator on this data improves accuracy on both real-world and mocap data by evaluating on the 3DPW and HumanEVA datasets.
Code (1)
Tasks
3D Human Pose Estimation3D Pose EstimationMonocular 3D Human Pose EstimationPose EstimationSimilar Papers 제목 키워드 기반
Towards Accurate Human Pose Estimation in Videos of Crowded Scenes
Video-based human pose estimation in crowded scenes is a challenging problem due to occlusion, motion blur, scale variation and viewpoint change, etc. Prior approaches always fail to deal with this problem because of (1)…
DiversityOptical Flow EstimationPose EstimationExploiting Spatiotemporal Properties for Efficient Event-Driven Human Pose Estimation
Human pose estimation focuses on predicting body keypoints to analyze human motion. Currently, most pose estimation tasks rely on conventional RGB cameras. In contrast, event cameras provide high temporal resolution and …
Computational EfficiencyPose EstimationExploiting temporal information for 3D human pose estimation
In this work, we address the problem of 3D human pose estimation from a sequence of 2D human poses. Although the recent success of deep networks has led many state-of-the-art methods for 3D pose estimation to train deep …
3D Human Pose Estimation3D Pose EstimationPose EstimationExploiting temporal information for 3D pose estimation
In this work, we address the problem of 3D human pose estimation from a sequence of 2D human poses. Although the recent success of deep networks has led many state-of-the-art methods for 3D pose estimation to train deep …
3D Human Pose Estimation3D Pose EstimationDecoderPose EstimationExploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation
Despite the great progress in 3D human pose estimation from videos, it is still an open problem to take full advantage of a redundant 2D pose sequence to learn representative representations for generating one 3D pose. T…
3D Human Pose EstimationMonocular 3D Human Pose EstimationPose Estimation