Continuous intermediate token learning with implicit motion manifold for keyframe based motion interpolation

CA Mo, K Hu, C Long, Z Wang - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Deriving sophisticated 3D motions from sparse keyframes is a particularly challenging
problem, due to continuity and exceptionally skeletal precision. The action features are often …

DanceGen: Supporting Choreography Ideation and Prototy** with Generative AI

Y Liu, M Sra - Proceedings of the 2024 ACM Designing Interactive …, 2024 - dl.acm.org
Choreography creation requires high proficiency in artistic and technical skills.
Choreographers typically go through four stages to create a dance piece: preparation …

Controllable free viewpoint video reconstruction based on neural radiance fields and motion graphs

H Zhang, F Li, J Zhao, C Tan, D Shen… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
In this paper, we propose a controllable high-quality free viewpoint video generation method
based on the motion graph and neural radiance fields (NeRF). Different from existing pose …

Bridging actions: Generate 3D poses and shapes in-between photos

WL Wei, JC Lin - IEEE Transactions on Pattern Analysis and …, 2024 - ieeexplore.ieee.org
Generating realistic 3D human motion has been a fundamental goal of the game/animation
industry. This work presents a novel transition generation technique that can bridge the …

Optimizing Motion Completion with Unconstrained Human Skeleton Structure Learning

T He, T Yang, S Konomi - 2024 IEEE International Conference …, 2024 - ieeexplore.ieee.org
Completing a motion sequence based on sparse key-frames remains a challenging task.
The limited grasp of the human skeleton's spatial structure and the complexity of handling …

Develo** an Interactive Virtual Reality Dance Partner

A Slezas - 2024 - aaltodoc.aalto.fi
Virtual Reality (VR) offers enhanced immersion and potential for complex interactions with
the virtual space and characters, allowing to utilise the whole body of the user as an input …

Motor Learning based on Presentation of a Tentative Goal

S Sun, Y Sun, M Goto, S Kondo, D Mikami… - Proceedings of the …, 2022 - dl.acm.org
This paper presents a motor learning method based on the presenting of a personalized
target motion, which we call a tentative goal. While many prior studies have focused on …

GenMotion: Data-driven Motion Generators for Real-time Animation Synthesis

Y Zhao, W Ai, L Qiu, P Lu, F Shi, T Han… - arxiv preprint arxiv …, 2021 - arxiv.org
With the recent success of deep learning algorithms, many researchers have focused on
generative models for human motion animation. However, the research community lacks a …