#motion-capture News & Analysis

7 articles tagged with #motion-capture. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

7 articles

AIBullisharXiv – CS AI · Jun 237/10

🧠

XmoPipe: A Pipeline for Large-Scale In-the-Wild Human Motion Dataset Construction

XmoPipe is a scalable pipeline that constructs large-scale human motion datasets by extracting 3D body and facial motion from unconstrained online videos, combined with automated textual descriptions. The system demonstrates that motion models trained on this in-the-wild data achieve performance comparable to traditional marker-based motion capture datasets while offering superior scalability and diversity.

AIBullisharXiv – CS AI · Jun 107/10

🧠

UniDexTok: A Unified Dexterous Hand Tokenizer from Real Data

UniDexTok introduces a unified tokenization system that standardizes how different dexterous robotic hands represent their states, enabling cross-embodiment learning from real-world data. By mapping diverse hand kinematics to a shared 22-degree-of-freedom interface, the system achieves sub-millimeter reconstruction accuracy—a 99% improvement over previous approaches—while eliminating the need for simulation or manual retargeting.

AIBullisharXiv – CS AI · Jun 17/10

🧠

Joint angle based learning to refine kinematic human pose estimation

Researchers propose a joint angle-based learning method to refine human pose estimation (HPE) by leveraging kinematic constraints and Fourier series approximation, addressing keypoint recognition errors and trajectory fluctuations. The approach demonstrates superior performance in challenging motion scenarios like figure skating and breaking, offering potential applications across sports analysis, healthcare, and motion capture industries.

AIBullisharXiv – CS AI · Feb 277/105

🧠

VQ-Style: Disentangling Style and Content in Motion with Residual Quantized Representations

Researchers have developed VQ-Style, a new AI method that uses Residual Vector Quantized Variational Autoencoders to separate style from content in human motion data. The technique enables effective motion style transfer without requiring fine-tuning for new styles, with applications in animation, gaming, and digital content creation.

AINeutralarXiv – CS AI · May 126/10

🧠

PhysHanDI: Physics-Based Reconstruction of Hand-Deformable Object Interactions

PhysHanDI introduces a physics-based framework for reconstructing 3D hand-object interactions involving deformable materials like cloth and soft objects. By simulating physically plausible object deformations driven by hand movements and using inverse physics to refine hand reconstruction, the method achieves superior performance in reconstruction and prediction tasks compared to existing approaches.

AINeutralarXiv – CS AI · May 96/10

🧠

ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video Generation

ActCam is a zero-shot AI method that enables simultaneous control of character motion and camera movement in video generation without requiring model retraining. The technique uses a two-phase conditioning approach with pose and depth constraints to generate videos with improved geometric consistency and motion fidelity across diverse scenarios.

AINeutralarXiv – CS AI · Mar 37/106

🧠

Non-verbal Real-time Human-AI Interaction in Constrained Robotic Environments

Researchers developed the first real-time framework for natural non-verbal human-AI interaction using body language, achieving 100 FPS on NVIDIA hardware. The study found that while AI models can mimic human motion, measurable differences persist between human and AI-generated body language, with temporal coherence being more important than visual fidelity.