Skip to main content
GameDev.net gamedev.net

Motion Capture News

The latest Motion Capture coverage curated for game developers.

Tokyo Game Show 2026: Bill Skarsgård Cast as Lead Role in PHYSINT

XBox Wire says Hideo Kojima has cast Bill Skarsgård as the lead in PHYSINT, the studio’s action-espionage project. Kojima also shared a new poster and said recent costume fittings, scans, …

Official XBox Wire · 2 days, 14 hours ago
SeMoCo: A Semantic-First Motion Codec for Motion Language Modeling

SeMoCo reframes motion tokens around meaning first, splitting each token into a semantic core and residual kinematics. For animation and ML pipelines, that could make text-to-motion generation easier to steer …

Research arXiv cs.GR · 3 weeks, 3 days ago
Erratum: OmniHands: Robust Motion Capture of Interactive Hands via A Versatile Transformer

ACM Transactions on Graphics has published an erratum for OmniHands, the hand-motion capture paper aimed at interactive hand tracking. The correction lands in Volume 45, Issue 5, dated October 2026. …

Research ACM Graphics · 3 weeks, 4 days ago
EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation

A new motion-generation method uses speech cues to decide which gesture frames to mask, aiming to produce more natural co-speech animation. EchoMask builds a shared motion-audio space, then scores frame-level …

Research arXiv cs.GR · 1 month ago
Smooth Motion Stitching via Laplacian Optimization in Rodrigues Vector Space

A new motion-editing method uses Laplacian optimization in Rodrigues vector space to stitch animation clips with smoother transitions. By keeping joint rotations continuous, it avoids the brittle hand-tuning and learning-based …

Research arXiv cs.GR · 1 month, 1 week ago
Multi-View Face and Gesture Animation with Dynamic Gaussians

A new multi-view avatar pipeline combines separate face and hand modeling with a parametric upper-body mesh, then renders the result with dynamic 3D Gaussians. The goal is to preserve subtle …

Research arXiv cs.GR · 1 month, 1 week ago
Reproducing Human Individual Motor Signatures: A Data-Driven Approach for Repetitive Motion

A new data-driven motion model can reproduce an individual's repetitive movement signature from real human data. Built around LSTM networks, it captures both velocity distribution and amplitude envelopes, which could …

Research arXiv cs.GR · 1 month, 2 weeks ago
260 Hours of MoCap: Baldur's Gate 3's Karlach Actor on Game Performance | GDC Side Quest

260 hours of motion capture went into Karlach’s performance in Baldur’s Gate 3, and Samantha Béart says that level of collaboration is reshaping expectations for game acting. Béart also pointed …

Video GDC Festival of Gaming · 1 month, 2 weeks ago
EgoExoMoCap: Distributed Ego-Exo Human Motion Capture

A new motion-capture approach uses just two or more people wearing smart glasses to reconstruct human movement in 3D. EgoExoMoCap blends egocentric and exocentric signals, plus head and optional wrist …

Research arXiv cs.GR · 1 month, 4 weeks ago
A Generative Motion Rig for Artist-Driven Motion Authoring

Disney Research Studios has turned a generative motion model into a Blender plugin for artist-driven animation authoring. The rig lets animators shape motion with sparse poses, handles, window lengths, and …

Research Disney Research Studios · 2 months ago
Prior-First, Condition-Second: Scalable and Controllable Hand Motion Completion

A new hand-motion completion system uses a learned body-hand prior first, then adds control signals on top, aiming to make real-time animation both plausible and steerable. It targets the hard …

Research arXiv cs.GR · 2 months, 1 week ago
OmniHands: Robust Motion Capture of Interactive Hands via A Versatile Transformer

A 2026 TOG paper describes a transformer-based hand mocap system aimed at messy, interactive hand poses rather than clean lab captures. For teams building VR, AR, or first-person interaction, the …

Research ACM Graphics · 2 months, 3 weeks ago
MOCHI: Motion Enhancement of Collaborative Human-object Interactions

For teams building motion-capture or animation tools, this paper tackles a familiar problem: collaborative human-object captures are noisy, with hand-object misalignment, jitter, and missing finger detail. MOCHI uses a two-stage …

Research arXiv cs.GR · 3 months ago
TopoCap: Learning Topology-Agnostic Motion Priors for Monocular Video-to-Animation

TopoCap tackles a real production pain point: retargeting motion from monocular video onto rigs that don’t share a human template. The paper claims zero-shot animation transfer across arbitrary skeletal topologies, …

Research arXiv cs.GR · 3 months, 1 week ago
Ultra Diffusion Poser: Diffusion-Based Human Motion Tracking From Sparse Inertial Sensors and Ranging-Based Between-Sensor Distances

Sparse IMU tracking gets a meaningful accuracy bump when UWB ranging is treated as geometry, not just another feature. This paper says reconstructing the sensor layout and guiding diffusion sampling …

Research arXiv cs.GR · 3 months, 2 weeks ago
AnyAct: Towards Human Reenactment of Character Motion From Video

AnyAct turns monocular video of non-human characters into editable human motion, aiming to give animators a usable starting point instead of a full reconstruction. The method leans on sparse local …

Research arXiv cs.GR · 4 months ago
A Dataset and Evaluation for Complex 4D Markerless Human Motion Capture

A new dataset for complex 4D markerless human motion capture has been introduced, addressing the limitations of traditional marker-based systems. This dataset captures intricate human interactions, making it invaluable for …

Research arXiv cs.GR · 5 months ago
VQ-Style: Disentangling Style and Content in Motion with Residual Quantized Representations

Disney Research Studios has introduced a groundbreaking method for disentangling style and content in human motion data, which could significantly enhance style transfer in game development. This innovation is particularly …

Research Disney Research Studios · 5 months, 2 weeks ago
DancingBox: A Lightweight MoCap System for Character Animation from Physical Proxies

DancingBox introduces a novel approach to motion capture, making it accessible for novice animators. By utilizing everyday objects and a single webcam, it transforms coarse movements into refined character animations. …

Research arXiv cs.GR · 6 months ago
Step2Motion: Locomotion Reconstruction from Pressure Sensing Insoles

Step2Motion introduces a novel approach to reconstructing human locomotion using pressure sensing insoles, offering game developers a way to capture motion without the constraints of traditional methods. This technology could …

Research arXiv cs.GR · 6 months, 1 week ago
Page 1 of 2 Next