PONet: Robust 3D Human Pose Estimation via Learning Orientations Only

by   Jue Wang, et al.

Conventional 3D human pose estimation relies on first detecting 2D body keypoints and then solving the 2D to 3D correspondence problem.Despite the promising results, this learning paradigm is highly dependent on the quality of the 2D keypoint detector, which is inevitably fragile to occlusions and out-of-image absences.In this paper,we propose a novel Pose Orientation Net (PONet) that is able to robustly estimate 3D pose by learning orientations only, hence bypassing the error-prone keypoint detector in the absence of image evidence. For images with partially invisible limbs, PONet estimates the 3D orientation of these limbs by taking advantage of the local image evidence to recover the 3D pose.Moreover, PONet is competent to infer full 3D poses even from images with completely invisible limbs, by exploiting the orientation correlation between visible limbs to complement the estimated poses,further improving the robustness of 3D pose estimation.We evaluate our method on multiple datasets, including Human3.6M, MPII, MPI-INF-3DHP, and 3DPW. Our method achieves results on par with state-of-the-art techniques in ideal settings, yet significantly eliminates the dependency on keypoint detectors and the corresponding computation burden. In highly challenging scenarios, such as truncation and erasing, our method performs very robustly and yields much superior results as compared to state of the art,demonstrating its potential for real-world applications.


page 1

page 5

page 8

page 9


DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model

Thanks to the development of 2D keypoint detectors, monocular 3D human p...

Bottom-Up Human Pose Estimation by Ranking Heatmap-Guided Adaptive Keypoint Estimates

The typical bottom-up human pose estimation framework includes two stage...

Multi-Scale Supervised Network for Human Pose Estimation

Human pose estimation is an important topic in computer vision with many...

Recurrent Human Pose Estimation

We propose a novel ConvNet model for predicting 2D human body poses in a...

Improving Robustness for Pose Estimation via Stable Heatmap Regression

Deep learning methods have achieved excellent performance in pose estima...

Combining 3D Model Contour Energy and Keypoints for Object Tracking

We present a new combined approach for monocular model-based 3D tracking...

Semi-supervised Human Pose Estimation in Art-historical Images

Gesture as language of non-verbal communication has been theoretically e...

Please sign up or login with your details

Forgot password? Click here to reset