Hugging Face Trending Papers August 13, 2026

Topology-Unified 2D Pose Estimation across Intact, Residual and Prosthetic Limbs

Read the original on Hugging Face Trending Papers →

Driven by the availability of large-scale datasets, Human Pose Estimation (HPE) plays a critical role in numerous downstream tasks. However, mainstream benchmarks exhibit severe representation bias, predominantly featuring able-bodied individuals.

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 Hugging Face Trending Papers.

arXiv AI

Aug 25

TransHands: Repurposing Human Pose Encoders as Hand Pose Encoders

arXiv:2608.22341v1 Announce Type: cross Abstract: Lifting 3D hand poses from 2D monocular representations remains challenging due to the limited availability of large-scale, diverse 3D-annotated hand...

By Milo Piccioli, Gianluca Amprimo, Claudia Ferraris, Gabriella Olmo

llms computer-vision fine-tuning benchmarks

Hugging Face Trending Papers

Jul 2

PWM-ArtGen: Part World Model for Articulated Object Generation

The key challenge in articulated 3D object generation from a single image is accurately predicting the underlying kinematic structure. Existing methods either infer kinematic parameters directly from a static image that lacks dynamic part-level kinematic relationships, or estimate parameters from visual dynamics generated from a single image, which is prone to accumulated errors of two steps.

diffusion

Hugging Face Trending Papers

Sep 16

Prosthesis-Aware 3D Human Pose Estimation: A Dataset and Benchmark for RSP Users

Recovering 3D human body motion from video is important for applications such as rehabilitation assessment and sports performance evaluation. For prosthesis users, this requires capturing both natural...

computer-vision benchmarks

arXiv Computer Vision

Sep 2

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

arXiv Computer Vision

Sep 17

Prosthesis-Aware 3D Human Pose Estimation: A Dataset and Benchmark for RSP Users

arXiv:2609.18406v1 Announce Type: new Abstract: Recovering 3D human body motion from video is important for applications such as rehabilitation assessment and sports performance evaluation. For prost...

By Yilin Wen, Kechuan Dong, Fumiya Suginaka, Ken Endo, Yusuke Sugano

computer-vision 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

One email a morning, machine-written

Related stories

TransHands: Repurposing Human Pose Encoders as Hand Pose Encoders

PWM-ArtGen: Part World Model for Articulated Object Generation

Prosthesis-Aware 3D Human Pose Estimation: A Dataset and Benchmark for RSP Users

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

Prosthesis-Aware 3D Human Pose Estimation: A Dataset and Benchmark for RSP Users

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