Hugging Face Trending Papers September 4, 2026

Sound-based Multi-Person 3D Pose Estimation

Read the original on Hugging Face Trending Papers →

The paper introduces SoundMHPE, the first system to estimate multi‑person 3D poses using only acoustic signals. It tackles challenges such as overlapping acoustic signatures and inter‑person reflections by employing an Acoustic Multi‑scale Encoder and a Temporal Pose Decoder with attention. The authors built a 6‑hour Acoustic Multi‑person Pose dataset and show that SoundMHPE outperforms baseline models.

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.

computer-vision

arXiv AI

Sep 7

Sound-based Multi-Person 3D Pose Estimation

The paper introduces SoundMHPE, an encoder‑decoder framework that estimates 3D poses of multiple people using only acoustic signals. It addresses challenges such as overlapping acoustic signatures and inter‑person reflections by employing a multi‑scale acoustic encoder and a temporal pose decoder with attention. The authors created the 6‑hour Acoustic Multi‑person Pose (AMP) dataset and show that SoundMHPE outperforms baseline models.

By Yusuke Oumi, Yuto Shibata, Go Irie, Akisato Kimura, Yoshimitsu Aoki, Mariko Isogawa

computer-vision

arXiv Computer Vision

Aug 28

Residual Flow Matching with Dynamic Cross-Interaction for 3D Multi-Person Motion Prediction

The paper introduces a Prior‑Guided Residual Flow Matching framework for 3D multi‑person motion prediction. It uses a Deterministic Coarse Prior to anchor kinematics and a Dynamic Cross‑Interaction mechanism to synchronize inter‑agent message passing during integration, thereby improving structural consistency and social context extraction. A decoupled joint‑motion architecture with bidirectional fusion further preserves fine‑grained kinematic coherence, achieving state‑of‑the‑art accuracy on several datasets.

By Wei Wei, Yinyuan Zhao, Ruixuan Yu

agents diffusion benchmarks

arXiv AI

Sep 15

BGM2Pose: Active 3D Human Pose Estimation with Non-Stationary Sounds

arXiv:2503.00389v2 Announce Type: replace-cross Abstract: We propose BGM2Pose, a non-invasive 3D human pose estimation method using arbitrary music (e.g., background music) as active sensing signals....

By Yuto Shibata, Yusuke Oumi, Go Irie, Akisato Kimura, Yoshimitsu Aoki, Mariko Isogawa

computer-vision

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 AI

Jun 4

MAEPose: Self-Supervised Spatiotemporal Learning for Human Pose Estimation on mmWave Video

arXiv:2605. 00242v2 Announce Type: replace-cross Abstract: Millimetre-wave (mmWave) radar offers a more privacy-preserving alternative to RGB-based human pose estimation.

By Xijia Wei, Yuan Fang, Kevin Chetty, Youngjun Cho, Nadia Bianchi-Berthouze

computer-vision benchmarks safety

arXiv Computer Vision

Sep 1

Everybody Tracking Every Body

arXiv:2608.29927v1 Announce Type: new Abstract: We address the problem of 3D body pose estimation of multiple interacting people from their egocentric views with centralized coordination. Each indivi...

By Daeyun Shin, Yunhan Zhao, Shu Kong, Alexander C. Berg, Charless Fowlkes

diffusion computer-vision

One email a morning, machine-written

Related stories

Sound-based Multi-Person 3D Pose Estimation

Residual Flow Matching with Dynamic Cross-Interaction for 3D Multi-Person Motion Prediction

BGM2Pose: Active 3D Human Pose Estimation with Non-Stationary Sounds

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

MAEPose: Self-Supervised Spatiotemporal Learning for Human Pose Estimation on mmWave Video

Everybody Tracking Every Body