The paper introduces a unified model for forecasting both global trajectories and 3D body poses of multiple agents in sports settings. It uses a socio‑temporal encoder that fuses trajectory and pose inputs, shared factorized attention, per‑joint loss reweighting, and a frequency‑domain smoothing term to improve predictions. The authors also correct evaluation biases by adopting a non‑overlapping protocol and demonstrate state‑of‑the‑art results on WorldPose and 3DPW datasets, especially in pose accuracy.
arXiv:2609.08636v1 Announce Type: cross Abstract: Egocentric 4D interaction forecasting aims to anticipate both where future interactions will occur in 3D and how the human body will move to realize...
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.
UT‑HMR is a one‑stage monocular 3D human mesh recovery framework that introduces uncertainty‑guided temporal modeling to address ambiguities caused by weak observations such as distance, occlusion, and motion blur. It predicts a Gaussian distribution over SMPL pose with a low‑rank-plus‑diagonal covariance, converting this into joint‑wise precision weights for heteroscedastic supervision while keeping inference deterministic. Temporal early fusion incorporates neighboring‑frame evidence before pose decoding, enabling the model to resolve pose ambiguities and achieve state‑of‑the‑art results on VIP‑HockeyPose‑v2, WorldPose, and competitive performance on 3DPW using a lightweight ViT‑B backbone.
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.
arXiv:2609.10498v1 Announce Type: new Abstract: Recovering 3D human pose from monocular sports broadcasts remains challenging when players must be localized in a shared metric world coordinate system...
arXiv:2401.05018v3 Announce Type: replace Abstract: Human motion prediction is a crucial capability for advanced robotic systems that interact with humans. In facilities with dynamic human-robot coll...
The paper introduces a new egocentric tennis dataset and evaluates how well foundation vision models can perform spatiotemporal tasks such as player and ball localization, trajectory forecasting, stroke type anticipation, and contact-time prediction. Seven models—image encoders, video encoders, and vision‑language models—are trained and tested on these tasks, achieving localization errors of 0.14 m for the player and 0.54 m for the ball, and forecasting errors of 0.34 m for the player and 0.91 m for the ball over 1.1 s. The study also shows that auxiliary depth data improves 3D ball localization, that longer image histories do not aid ball forecasting, and proposes a conditional diffusion model that generates real‑time whole‑body kinematic tennis motion from egocentric video predictions.
arXiv:2609.13778v1 Announce Type: cross Abstract: Human trajectory prediction requires modeling both individual motion patterns and social interactions among agents. Existing methods have made substa...
arXiv:2606. 09842v1 Announce Type: cross Abstract: Applying Human Pose Estimation (HPE) in real world environments remains a challenging task, this paper explores and surveys real time HPE approaches and their limitations in sports analysis for individuals, alongside developing a practical lightweight prototype for real world testing and usage.
arXiv:2608. 20284v1 Announce Type: new Abstract: Reliable surgical planning requires models to anticipate not only how instruments will move, but also how the operative visual state will evolve together with such motion.
Pose-Anchored Optical Flow for Low-Latency Human Action Anticipation in Human-Robot Teaming proposes PoseOFF, a representation that captures local motion around human joints by conditioning optical flow extraction on pose. This structured motion representation aligns with human kinematics and improves early action recognition accuracy across multiple datasets and backbones. PoseOFF achieves comparable or better performance while observing less of the action sequence, making it suitable for real‑time, resource‑constrained robotic systems.
The paper introduces Object-Conditioned Social Diffusion (OCSD), a conditional diffusion model that unifies motion history, multi‑person interactions, and object cues for human motion forecasting in complex scenes. OCSD employs an object‑conditioning mechanism that modulates denoising at each timestep, enabling fine‑grained human‑object reasoning, and a social encoder that captures interactions among all humans. Experiments on the Humans in Kitchens (HiK) and HOI‑M3 benchmarks show state‑of‑the‑art performance, reducing two‑second path error by 31.3% on HiK and 33.2% on HOI‑M3 compared to prior work, while producing more realistic long‑term forecasts.