Motion Generation: A Survey of Generative Approaches and Benchmarks

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Khani, Aliasghar, Rampini, Arianna, Roy, Bruno, Nadela, Larasika, Kaplan, Noa, Atherton, Evan, Cheung, Derek, Bibliowicz, Jacky
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911044547379200
author Khani, Aliasghar
Rampini, Arianna
Roy, Bruno
Nadela, Larasika
Kaplan, Noa
Atherton, Evan
Cheung, Derek
Bibliowicz, Jacky
author_facet Khani, Aliasghar
Rampini, Arianna
Roy, Bruno
Nadela, Larasika
Kaplan, Noa
Atherton, Evan
Cheung, Derek
Bibliowicz, Jacky
contents Motion generation, the task of synthesizing realistic motion sequences from various conditioning inputs, has become a central problem in computer vision, computer graphics, and robotics, with applications ranging from animation and virtual agents to human-robot interaction. As the field has rapidly progressed with the introduction of diverse modeling paradigms including GANs, autoencoders, autoregressive models, and diffusion-based techniques, each approach brings its own advantages and limitations. This growing diversity has created a need for a comprehensive and structured review that specifically examines recent developments from the perspective of the generative approach employed. In this survey, we provide an in-depth categorization of motion generation methods based on their underlying generative strategies. Our main focus is on papers published in top-tier venues since 2023, reflecting the most recent advancements in the field. In addition, we analyze architectural principles, conditioning mechanisms, and generation settings, and compile a detailed overview of the evaluation metrics and datasets used across the literature. Our objective is to enable clearer comparisons and identify open challenges, thereby offering a timely and foundational reference for researchers and practitioners navigating the rapidly evolving landscape of motion generation.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05419
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Motion Generation: A Survey of Generative Approaches and Benchmarks
Khani, Aliasghar
Rampini, Arianna
Roy, Bruno
Nadela, Larasika
Kaplan, Noa
Atherton, Evan
Cheung, Derek
Bibliowicz, Jacky
Computer Vision and Pattern Recognition
Machine Learning
Motion generation, the task of synthesizing realistic motion sequences from various conditioning inputs, has become a central problem in computer vision, computer graphics, and robotics, with applications ranging from animation and virtual agents to human-robot interaction. As the field has rapidly progressed with the introduction of diverse modeling paradigms including GANs, autoencoders, autoregressive models, and diffusion-based techniques, each approach brings its own advantages and limitations. This growing diversity has created a need for a comprehensive and structured review that specifically examines recent developments from the perspective of the generative approach employed. In this survey, we provide an in-depth categorization of motion generation methods based on their underlying generative strategies. Our main focus is on papers published in top-tier venues since 2023, reflecting the most recent advancements in the field. In addition, we analyze architectural principles, conditioning mechanisms, and generation settings, and compile a detailed overview of the evaluation metrics and datasets used across the literature. Our objective is to enable clearer comparisons and identify open challenges, thereby offering a timely and foundational reference for researchers and practitioners navigating the rapidly evolving landscape of motion generation.
title Motion Generation: A Survey of Generative Approaches and Benchmarks
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2507.05419