arXiv Computer Vision September 3, 2026 By R. James Cotton, Divya Joshi, Colleen Peyton

Cross-Model Distillation of a Human-Pose Foundation Model from Unannotated Infant Video for Markerless 3D Pose Estimation

Read the original on arXiv Computer Vision →

The paper presents a method for improving markerless 3D pose estimation in infants by cross‑model distillation. Using unannotated infant video, a frozen Sapiens 2 pose model provides dense pseudo‑labels that guide fine‑tuning of the SAM 3D Body model. On a held‑out dataset of eleven infants, the fine‑tuned model shows significant gains in 2D keypoint accuracy and 3D joint error compared to the original SAM 3D Body model.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Computer Vision

3d ago

Biomechanical 3D Body: Self-Supervised Distillation of Biomechanical Pose from a 3D Body Foundation Model

arXiv:2608.29928v1 Announce Type: new Abstract: State-of-the-art monocular body recovery methods predict mesh vertices and angles on the corresponding kinematic tree, but their outputs lack biomechan...

By R. James Cotton, J. D. Peiffer, Lucinda Williamson, John Leske, Georgios Pavlakos

efficiency benchmarks

arXiv AI

Jul 10

Pose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Prediction

arXiv:2607. 08725v1 Announce Type: cross Abstract: Recent progress in 3D human pose estimation has made markerless recovery of skeletal motion increasingly accurate and scalable.

By Ayda Eghbalian, Kevin Desai

llms computer-vision multimodal benchmarks

arXiv Machine Learning

Jun 29

Cross-view Multimodal Vision-Based Assessment Framework for Traditional Chinese Medicine Rehabilitation Training

arXiv:2606. 28104v1 Announce Type: cross Abstract: Vision-based assessment can provide convenient and cost-effective evaluation in Traditional Chinese Medicine (TCM) rehabilitation training, where action quality assessment (AQA) from computer vision offers a promising solution.

By Francis Xiatian Zhang, Hao Yao, Shengxuan Chen, Hong Zhu, Hongxiao Jia, Sisi Zheng, Hubert P. H. Shum

computer-vision robotics multimodal

Hugging Face Trending Papers

Jul 27

Multiview Multi-Person Human Mesh Recovery Under Large Scenes with Occlusions

Human mesh recovery (HMR) aims to recover 3D human meshes from images. Most existing HMR benchmarks and methods focus on either multi-person reconstruction from a single view or single-person reconstruction from multiple views, where the number of subjects and the scene scale are relatively limited.

computer-vision benchmarks

Hugging Face Trending Papers

Aug 4

Learning Biomechanically Plausible Human Motion from Sparse Radar Point Clouds

Radar-based human pose estimation has focused on improving learning algorithms while representing the body as unconstrained keypoint coordinates. We address the underexplored dimension of anatomical fidelity by integrating a full-body skeletal model into a differentiable, end-to-end trainable radar-based pose estimation framework, in which the pose network is supervised through forward kinematics while subject-specific geometry is fitted beforehand.

computer-vision

arXiv Computer Vision

2d ago

On the Role of Rotation Equivariance in Monocular 2D-to-3D Human Pose Lifting

arXiv:2601.13913v3 Announce Type: replace Abstract: We consider monocular 3D human pose estimation (HPE), where the goal is to predict 3D human skeletal joints from a single 2D image, typically via 2...

By Pavlo Melnyk, Cuong Le, Urs Waldmann, Per-Erik Forss\'en, Bastian Wandt

computer-vision benchmarks safety