Two more papers have been accepted at the 11th International Workshop on Computer Vision in Sports (CVsports) at CVPR 2025:

• "Leveraging Anthropometric Measurements to Improve Human Mesh Estimation and Ensure Consistent Body Shapes" by Katja Ludwig, Julian Lorenz, Daniel Kienzle, Tuan Bui & Rainer Lienhart
• "Efficient 2D to Full 3D Human Pose Uplifting including Joint Rotations" by Katja Ludwig, Yuliia Oksymets, Robin Sch?n, Daniel Kienzle & Rainer Lienhart.

The first paper discusses inconsistencies in existing methods for estimating 3D meshes of people – when such a method is applied to a video of a person, the person’s body shape changes from frame to frame. To address this, the authors introduce the method A2B, which uses anthropometric measurements to determine and encode a person’s body shape in the SMPL-X body model. This fixed body shape can then be used for all videos of that individual. The paper also describes how combining a 3D pose estimator with inverse kinematics and A2B yields significantly better results on sports datasets than current mesh estimation methods.

The second paper builds on and improves this idea. Inverse kinematics is an iterative algorithm that needs to be executed separately for each frame, making it very time-consuming. The authors therefore explore an extension of the 3D pose estimator "Uplift and Upsample" (Einfalt et al.) to include the estimation of 3D joint rotations, which are not part of the base version. This allows the system to be made 150 times faster.

Leveraging Anthropometric Measurements to Improve Human Mesh Estimation and Ensure Consistent Body Shapes:

The basic body shape (i.e., the body shape in T-pose) of a person does not change within a single video. However, most SOTA human mesh estimation (HME) models output a slightly different, thus inconsistent basic body shape for each video frame. Furthermore, we find that SOTA 3D human pose estimation (HPE) models outperform HME models regarding the precision of the estimated 3D keypoint positions. We solve the problem of inconsistent body shapes by leveraging anthropometric measurements like taken by tailors from humans. We create a model called A2B that converts given anthropometric measurements to basic body shape parameters of human mesh models. We obtain superior and consistent human meshes by combining the A2B model results with the keypoints of 3D HPE models using inverse kinematics. We evaluate our approach on challenging datasets like ASPset or fit3D, where we can lower the MPJPE by over 30 mm compared to SOTA HME models. Further, replacing estimates of the body shape parameters from existing HME models with A2B results not only increases the performance of these HME models, but also guarantees consistent body shapes.

?

Efficient 2D to Full 3D Human Pose Uplifting including Joint Rotations:

In sports analytics, accurately capturing both the 3D locations and rotations of body joints is essential for understanding an athlete's biomechanics. While Human Mesh Recovery (HMR) models can estimate joint rotations, they often exhibit lower accuracy in joint localization compared to 3D Human Pose Estimation (HPE) models. Recent work addressed this limitation by combining a 3D HPE model with inverse kinematics (IK) to estimate both joint locations and rotations. However, IK is computationally expensive. To overcome this, we propose a novel 2D-to-3D uplifting model that directly estimates 3D human poses, including joint rotations, in a single forward pass. We investigate multiple rotation representations, loss functions, and training strategies — both with and without access to ground truth rotations. Our models achieve state-of-the-art accuracy in rotation estimation, are 150 times faster than the IK-based approach, and surpass HMR models in joint localization precision.