paper-with-me

홈 › Papers

GenM$^3$: Generative Pretrained Multi-path Motion Model for Text Conditional Human Motion Generation

2025-03-19 · Junyu Shi, Lijiang Liu, Yong Sun, Zhiyuan Zhang, Jinni Zhou, Qiang Nie

Scaling up motion datasets is crucial to enhance motion generation capabilities. However, training on large-scale multi-source datasets introduces data heterogeneity challenges due to variations in motion content. To address this, we propose Generative Pretrained Multi-path Motion Model (GenM$^3$), a comprehensive framework designed to learn unified motion representations. GenM$^3$ comprises two components: 1) a Multi-Expert VQ-VAE (MEVQ-VAE) that adapts to different dataset distributions to learn a unified discrete motion representation, and 2) a Multi-path Motion Transformer (MMT) that improves intra-modal representations by using separate modality-specific pathways, each with densely activated experts to accommodate variations within that modality, and improves inter-modal alignment by the text-motion shared pathway. To enable large-scale training, we integrate and unify 11 high-quality motion datasets (approximately 220 hours of motion data) and augment it with textual annotations (nearly 10,000 motion sequences labeled by a large language model and 300+ by human experts). After training on our integrated dataset, GenM$^3$ achieves a state-of-the-art FID of 0.035 on the HumanML3D benchmark, surpassing state-of-the-art methods by a large margin. It also demonstrates strong zero-shot generalization on IDEA400 dataset, highlighting its effectiveness and adaptability across diverse motion scenarios.

📄 PDF Abstract BibTeX arXiv:2503.14919

Code (0)

등록된 구현이 없습니다.

Tasks

Large Language ModelMotion GenerationZero-shot Generalization

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Attention 설명 없음
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Example-based Motion Synthesis via Generative Motion Matching

2023-06-01 · Weiyu Li, Xuelin Chen, Peizhuo Li, Olga Sorkine-Hornung 외

We present GenMM, a generative model that "mines" as many diverse motions as possible from a single or few example sequences. In stark contrast to existing data-driven methods, which typically require long offline traini…

Motion GenerationMotion Synthesis

GENMO: A GENeralist Model for Human MOtion

2025-05-02 · Jiefeng Li, Jinkun Cao, Haotian Zhang, Davis Rempe 외

Human motion modeling traditionally separates motion generation and estimation into distinct tasks with specialized models. Motion generation models focus on creating diverse, realistic motions from inputs like text, aud…

modelMotion EstimationMotion GenerationTransfer Learning

The Wanderings of Odysseus in 3D Scenes

2021-12-16 · CVPR 2022 1 · Yan Zhang, Siyu Tang

Our goal is to populate digital environments, in which digital humans have diverse body shapes, move perpetually, and have plausible body-scene contact. The core challenge is to generate realistic, controllable, and infi…

GenMask: Adapting DiT for Segmentation via Direct Mask Generation

2026-03-25 · Yuhuan Yang, Xianwei Zhuang, Yuxuan Cai, Chaofan Ma 외 arxiv

Recent approaches for segmentation have leveraged pretrained generative models as feature extractors, treating segmentation as a downstream adaptation task via indirect feature retrieval. This implicit use suffers from a…

Image Generation

Generative Human Motion Stylization in Latent Space

2024-01-24 · Chuan Guo, Yuxuan Mu, Xinxin Zuo, Peng Dai 외

Human motion stylization aims to revise the style of an input motion while keeping its content unaltered. Unlike existing works that operate directly in pose space, we leverage the latent space of pretrained autoencoders…