Motion Generation Review: Exploring Deep Learning for Lifelike Animation with Manifold
Not on the map. Why?
Abstract (arXiv)
Human motion generation involves creating natural sequences of human body poses, widely used in gaming, virtual reality, and human-computer interaction. It aims to produce lifelike virtual characters with realistic movements, enhancing virtual agents and immersive experiences. While previous work has focused on motion generation based on signals like movement, music, text, or scene background, the complexity of human motion and its relationships with these signals often results in unsatisfactory outputs. Manifold learning offers a solution by reducing data dimensionality and capturing subspaces of effective motion. In this review, we present a comprehensive overview of manifold applications in human motion generation, one of the first in this domain. We explore methods for extracting manifolds from unstructured data, their application in motion generation, and discuss their advantages and future directions. This survey aims to provide a broad perspective on the field and stimulate new approaches to ongoing challenges.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 38 of its 76 references that are in the map. First posted on arXiv 12 Dec 2024.
Builds on
38 of 76 references.
References · 38
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2022Generative Adversarial Networkscited by 5,603
- 2017Neural Discrete Representation Learningcited by 4,650
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
- 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
- 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
- 2022Human Motion Diffusion Modelcited by 1,062
- 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 768
- 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 530
- 2023MotionGPT: Human Motion as a Foreign Languagecited by 521
26 more
- 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
- 2022TEMOS: Generating diverse human motions from textual descriptionscited by 486
- 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 479
- 2023Human Motion Diffusion as a Generative Priorcited by 354
- 2016Ladder Variational Autoencoderscited by 315
- 2023ReMoDiffuse: Retrieval-Augmented Motion Diffusion Modelcited by 282
- 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
- 2023Diffusion-based Generation, Optimization, and Planning in 3D Scenescited by 237
- 2020STAR: Sparse Trained Articulated Human Body Regressorcited by 194
- 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
- 2021Synthesis of Compositional Animations from Textual Descriptionscited by 177
- 2020Populating 3D Scenes by Learning Human-Scene Interactioncited by 164
- 2020We are More than Our Joints: Predicting how 3D Bodies Movecited by 115
- 2017Text2Action: Generative Adversarial Synthesis from Language to Actioncited by 106
- 2023Human Motion Generation: A Surveycited by 95
- 2023CALM: Conditional Adversarial Latent Models for Directable Virtual Characterscited by 91
- 2022PoseGPT: Quantization-based 3D Human Motion Generation and Forecastingcited by 78
- 2022MoDi: Unconditional Motion Synthesis from Diverse Datacited by 59
- 20233D Human Mesh Estimation from Virtual Markerscited by 44
- 2023Music-Driven Group Choreographycited by 36
- 2019Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modelingcited by 32
- 2020Structure-Aware Human-Action Generationcited by 28
- 2023Motion In-Betweening with Phase Manifoldscited by 25
- 2021Generative Adversarial Graph Convolutional Networks for Human Action Synthesiscited by 23
- 2021Human Motion Prediction Using Manifold-Aware Wasserstein GANcited by 8
- 2020Constructing Human Motion Manifold with Sequential Networkscited by 7
Built on by
Citing papers per year: 2025: 1.
1 paper.