Motion Capture Dataset for Practical Use of AI-based Motion Editing and Stylization (2023-06-15T00:00:00.000000Z)

TL;DR

This work proposes a new style-diverse dataset that uses an industrial-standard human bone structure and thus is industry-ready to be plugged into 3D characters for many projects and claims the challenges in motion style transfer.

Abstract

In this work, we proposed a new style-diverse dataset for the domain of motion style transfer. The motion dataset uses an industrial-standard human bone structure and thus is industry-ready to be plugged into 3D characters for many projects. We claim the challenges in motion style transfer and encourage future work in this domain by releasing the proposed motion dataset both to the public and the market. We conduct a comprehensive study on motion style transfer in the experiment using the state-of-the-art method, and the results show the proposed dataset's validity for the motion style transfer task.

Authors

Makito Kobayashi

1 papers

Chen-Chieh Liao

1 papers

Keito Inoue

1 papers

TL;DR

Abstract

Authors

References40 items

AI Coach: A Motor Skill Training System using Motion Discrepancy Detection

MuscleRehab: Improving Unsupervised Physical Rehabilitation by Monitoring and Visualizing Muscle Engagement

Motion Puzzle: Arbitrary Motion Style Transfer by Body Part

Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases

Diverse Motion Stylization for Multiple Style Domains via Spatial-Temporal Graph-Based Generative Model

Autoregressive Stylized Motion Synthesis with Generative Flow

Real-Time Sign Language Detection using Human Pose Estimation

Robust motion in-betweening

Unpaired motion style transfer from video to animation

Deep High-Resolution Representation Learning for Visual Recognition

InterPoser: Visualizing Interpolated Movements for Bouldering Training

OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields

Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization

A Deep Learning Framework for Character Motion Synthesis and Editing

Spectral style transfer for human motion between independent actions

Design of a video game for rehabilitation using motion capture, EMG analysis and virtual reality

Learning motion manifolds with convolutional autoencoders

The KIT whole-body human motion database

Realtime style transfer for unlabeled heterogeneous human motion

Pose-conditioned joint angle limits for 3D human pose reconstruction

Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments

Sleight of hand: perception of finger motion from reduced marker sets

Emotion in Motion

A Virtual Reality Dance Training System Using Motion Capture Technology

Modeling style and variation in human motion

Efficient and robust annotation of motion capture data

Fourier principles for emotion-based human figure animation

Mirai Komachi Official Page

AI Golf: Golf Swing Analysis Tool for Self-Training

A Cyclic Consistency Motion Style Transfer Method Combined with Kinematic Constraints

Harvey , Mike Yurick , Derek Nowrouzezahrai , and Christopher Pal . 2020

Xsens MVN: Full 6DOF Human Motion Tracking Using Miniature Inertial Sensors

Optical Motion Capture: Theory and Implementation

A framework for analysis and synthesis of human gait patterns

CMU Graphics Lab Motion Capture Database

Samples of motion style transfer results using our dataset, applied to various characters

Vicon Motion Systems

Emote motion dataset is commercially available and is targeted for R&D, universities, and research institutes that are conducting or planning to conduct Motion AI research. More information

Inc. BandaiNamcoResearch

inquiry form

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names