OpenT2M: No-frill Motion Generation with Open-source,Large-scale, High-quality Data

• URL: http://arxiv.org/abs/2603.18623v1
• Date: Thu, 19 Mar 2026 08:43:16 GMT
• Title: OpenT2M: No-frill Motion Generation with Open-source,Large-scale, High-quality Data
• Abstract summary: Text-to-motion (T2M) generation aims to create realistic human movements from text descriptions.<n>Current T2M models perform poorly on unseen text descriptions due to the small scale and limited diversity of existing motion datasets.<n>OpenT2M and MonoFrill will advance the T2M field by addressing longstanding data quality and benchmarking challenges.
• Score: 32.853640288433304
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-to-motion (T2M) generation aims to create realistic human movements from text descriptions, with promising applications in animation and robotics. Despite recent progress, current T2M models perform poorly on unseen text descriptions due to the small scale and limited diversity of existing motion datasets. To address this problem, we introduce OpenT2M, a million-level, high-quality, and open-source motion dataset containing over 2800 hours of human motion. Each sequence undergoes rigorous quality control through physical feasibility validation and multi-granularity filtering, with detailed second-wise text annotations. We also develop an automated pipeline for creating long-horizon sequences, enabling complex motion generation. Building upon OpenT2M, we introduce MonoFrill, a pretrained motion model that achieves compelling T2M results without complicated designs or technique tricks as "frills". Its core component is 2D-PRQ, a novel motion tokenizer that captures spatiotemporal dependencies by dividing the human body into biology parts. Experiments show that OpenT2M significantly improves generalization of existing T2M models, while 2D-PRQ achieves superior reconstruction and strong zero-shot performance. We expect OpenT2M and MonoFrill will advance the T2M field by addressing longstanding data quality and benchmarking challenges.

Related papers

• RoboMIND 2.0: A Multimodal, Bimanual Mobile Manipulation Dataset for Generalizable Embodied Intelligence [59.39508501733987]
  We present RoboMIND 2.0, a comprehensive real-world dataset comprising over 310K dual-arm manipulation trajectories.<n>To support research in contact-rich and spatially extended tasks, the dataset incorporates 12K tactile-enhanced episodes and 20K mobile manipulation trajectories.<n>To fully exploit the potential of RoboMIND 2.0, we propose MIND-2 system, a hierarchical dual-system frame-work optimized via offline reinforcement learning.
  arXiv  Detail & Related papers  (2025-12-31T05:59:40Z)
• Toward Rich Video Human-Motion2D Generation [16.58311138197227]
  We introduce a new large-scale rich video human motion 2D dataset (Motion2D-Video-150K) comprising 150,000 video sequences.<n>Motion2D-Video-150K features a balanced distribution of diverse single-character and, crucially, double-character interactive actions.<n>We propose a novel diffusion-based rich video human motion2D generation model (RVHM2D) model.
  arXiv  Detail & Related papers  (2025-06-17T11:45:33Z)
• Training-free Guidance in Text-to-Video Generation via Multimodal Planning and Structured Noise Initialization [63.37161241355025]
  Video-MSG is a training-free method for T2V generation based on Multimodal planning and Structured noise initialization.<n>It guides a downstream T2V diffusion model with Video Sketch through noise inversion and denoising.<n>Video-MSG does not need fine-tuning or attention manipulation with additional memory during inference time, making it easier to adopt large T2V models.
  arXiv  Detail & Related papers  (2025-04-11T15:41:43Z)
• EfficientMT: Efficient Temporal Adaptation for Motion Transfer in Text-to-Video Diffusion Models [73.96414072072048]
  Existing motion transfer methods explored the motion representations of reference videos to guide generation.<n>We propose EfficientMT, a novel and efficient end-to-end framework for video motion transfer.<n>Our experiments demonstrate that our EfficientMT outperforms existing methods in efficiency while maintaining flexible motion controllability.
  arXiv  Detail & Related papers  (2025-03-25T05:51:14Z)
• Motion Anything: Any to Motion Generation [24.769413146731264]
  Motion Anything is a multimodal motion generation framework.<n>Our model adaptively encodes multimodal conditions, including text and music, improving controllability.<n>Text-Music-Dance dataset consists of 2,153 pairs of text, music, and dance, making it twice the size of AIST++.
  arXiv  Detail & Related papers  (2025-03-10T06:04:31Z)
• KETA: Kinematic-Phrases-Enhanced Text-to-Motion Generation via Fine-grained Alignment [5.287416596074742]
  State-of-the-art T2M techniques mainly leverage diffusion models to generate motions with text prompts as guidance.<n>We propose KETA, which decomposes the given text into several decomposed texts via a language model.<n>Experiments demonstrate that KETA achieves up to 1.19x, 2.34x better R precision and FID value on both backbones of the base model, motion diffusion model.
  arXiv  Detail & Related papers  (2025-01-25T03:43:33Z)
• Mogo: RQ Hierarchical Causal Transformer for High-Quality 3D Human Motion Generation [0.0]
  Bert-type Masked Models (MoMask, MMM) currently produce higher-quality outputs compared to GPT-type autoregressive models (T2M-GPT)<n>We propose a novel architecture, Mogo, which generates high-quality lifelike 3D human motions by training a single transformer model.<n>Mogo can generate continuous and cyclic motion sequences up to 260 frames (13 seconds), surpassing the 196 frames (10 seconds) length of existing datasets like HumanML3D.
  arXiv  Detail & Related papers  (2024-12-05T08:30:43Z)
• T2M-X: Learning Expressive Text-to-Motion Generation from Partially Annotated Data [6.6240820702899565]
  Existing methods only generate body motion data, excluding facial expressions and hand movements. Recent attempts to create such a dataset have resulted in either motion inconsistency among different body parts. We propose T2M-X, a two-stage method that learns expressive text-to-motion generation from partially annotated data.
  arXiv  Detail & Related papers  (2024-09-20T06:20:00Z)
• FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing [56.29102849106382]
  FineMoGen is a diffusion-based motion generation and editing framework. It can synthesize fine-grained motions, with spatial-temporal composition to the user instructions. FineMoGen further enables zero-shot motion editing capabilities with the aid of modern large language models.
  arXiv  Detail & Related papers  (2023-12-22T16:56:02Z)
• Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs [112.39389727164594]
  Text-to-video (T2V) synthesis has gained increasing attention in the community, in which the recently emerged diffusion models (DMs) have promisingly shown stronger performance than the past approaches. While existing state-of-the-art DMs are competent to achieve high-resolution video generation, they may largely suffer from key limitations (e.g., action occurrence disorders, crude video motions) with respect to the temporal dynamics modeling, one of the crux of video synthesis. In this work, we investigate strengthening awareness of video dynamics for DMs, for high-quality T2V generation
  arXiv  Detail & Related papers  (2023-08-26T08:31:48Z)
• SimDA: Simple Diffusion Adapter for Efficient Video Generation [102.90154301044095]
  We propose a Simple Diffusion Adapter (SimDA) that fine-tunes only 24M out of 1.1B parameters of a strong T2I model, adapting it to video generation in a parameter-efficient way. In addition to T2V generation in the wild, SimDA could also be utilized in one-shot video editing with only 2 minutes tuning.
  arXiv  Detail & Related papers  (2023-08-18T17:58:44Z)
• Make-A-Video: Text-to-Video Generation without Text-Video Data [69.20996352229422]
  Make-A-Video is an approach for translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V) We design a simple yet effective way to build on T2I models with novel and effective spatial-temporal modules. In all aspects, spatial and temporal resolution, faithfulness to text, and quality, Make-A-Video sets the new state-of-the-art in text-to-video generation.
  arXiv  Detail & Related papers  (2022-09-29T13:59:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.