DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model
This work addresses depth ambiguity in 3D human pose estimation for applications where temporal sequences are unavailable, representing an incremental improvement over existing multi-hypothesis methods.
The paper tackles the problem of monocular 3D human pose estimation from a single 2D keypoint detection by generating multiple 3D pose candidates to address depth ambiguities, using a diffusion-based framework with graph convolutional networks, and reports outperforming state-of-the-art multi-hypothesis methods on Human3.6M and HumanEva-I datasets.
Thanks to the development of 2D keypoint detectors, monocular 3D human pose estimation (HPE) via 2D-to-3D uplifting approaches have achieved remarkable improvements. Still, monocular 3D HPE is a challenging problem due to the inherent depth ambiguities and occlusions. To handle this problem, many previous works exploit temporal information to mitigate such difficulties. However, there are many real-world applications where frame sequences are not accessible. This paper focuses on reconstructing a 3D pose from a single 2D keypoint detection. Rather than exploiting temporal information, we alleviate the depth ambiguity by generating multiple 3D pose candidates which can be mapped to an identical 2D keypoint. We build a novel diffusion-based framework to effectively sample diverse 3D poses from an off-the-shelf 2D detector. By considering the correlation between human joints by replacing the conventional denoising U-Net with graph convolutional network, our approach accomplishes further performance improvements. We evaluate our method on the widely adopted Human3.6M and HumanEva-I datasets. Comprehensive experiments are conducted to prove the efficacy of the proposed method, and they confirm that our model outperforms state-of-the-art multi-hypothesis 3D HPE methods.