OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers

• URL: http://arxiv.org/abs/2312.08985v3
• Date: Tue, 19 Mar 2024 06:50:17 GMT
• Title: OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers
• Authors: Han Liang, Jiacheng Bao, Ruichi Zhang, Sihan Ren, Yuecheng Xu, Sibei Yang, Xin Chen, Jingyi Yu, Lan Xu,
• Abstract summary: We present OMG, a novel framework, which enables compelling motion generation from zero-shot open-vocabulary text prompts. At the pre-training stage, our model improves the generation ability by learning the rich out-of-domain inherent motion traits. At the fine-tuning stage, we introduce motion ControlNet, which incorporates text prompts as conditioning information.
• Score: 45.808597624491156
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We have recently seen tremendous progress in realistic text-to-motion generation. Yet, the existing methods often fail or produce implausible motions with unseen text inputs, which limits the applications. In this paper, we present OMG, a novel framework, which enables compelling motion generation from zero-shot open-vocabulary text prompts. Our key idea is to carefully tailor the pretrain-then-finetune paradigm into the text-to-motion generation. At the pre-training stage, our model improves the generation ability by learning the rich out-of-domain inherent motion traits. To this end, we scale up a large unconditional diffusion model up to 1B parameters, so as to utilize the massive unlabeled motion data up to over 20M motion instances. At the subsequent fine-tuning stage, we introduce motion ControlNet, which incorporates text prompts as conditioning information, through a trainable copy of the pre-trained model and the proposed novel Mixture-of-Controllers (MoC) block. MoC block adaptively recognizes various ranges of the sub-motions with a cross-attention mechanism and processes them separately with the text-token-specific experts. Such a design effectively aligns the CLIP token embeddings of text prompts to various ranges of compact and expressive motion features. Extensive experiments demonstrate that our OMG achieves significant improvements over the state-of-the-art methods on zero-shot text-to-motion generation. Project page: https://tr3e.github.io/omg-page.

Related papers

• Textual Decomposition Then Sub-motion-space Scattering for Open-Vocabulary Motion Generation [74.94730615777212]
  Text-to-motion generation is a crucial task in computer vision, which generates the target 3D motion by the given text. The current annotated dataset's limited scale only allows them to achieve mapping from sub-text-space to sub-motion-space. This paper proposes to leverage the atomic motion as an intermediate representation, and leverage two orderly coupled steps, i.e., Textual Decomposition and Sub-motion-space Scattering.
  arXiv  Detail & Related papers  (2024-11-06T17:57:43Z)
• Infinite Motion: Extended Motion Generation via Long Text Instructions [51.61117351997808]
  "Infinite Motion" is a novel approach that leverages long text to extended motion generation. Key innovation of our model is its ability to accept arbitrary lengths of text as input. We incorporate the timestamp design for text which allows precise editing of local segments within the generated sequences.
  arXiv  Detail & Related papers  (2024-07-11T12:33:56Z)
• BAMM: Bidirectional Autoregressive Motion Model [14.668729995275807]
  Bidirectional Autoregressive Motion Model (BAMM) is a novel text-to-motion generation framework. BAMM consists of two key components: a motion tokenizer that transforms 3D human motion into discrete tokens in latent space, and a masked self-attention transformer that autoregressively predicts randomly masked tokens. This feature enables BAMM to simultaneously achieving high-quality motion generation with enhanced usability and built-in motion editability.
  arXiv  Detail & Related papers  (2024-03-28T14:04:17Z)
• Motion Generation from Fine-grained Textual Descriptions [29.033358642532722]
  We build a large-scale language-motion dataset specializing in fine-grained textual descriptions, FineHumanML3D. We design a new text2motion model, FineMotionDiffuse, making full use of fine-grained textual information. Our evaluation shows that FineMotionDiffuse trained on FineHumanML3D improves FID by a large margin of 0.38, compared with competitive baselines.
  arXiv  Detail & Related papers  (2024-03-20T11:38:30Z)
• 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)
• Action-GPT: Leveraging Large-scale Language Models for Improved and Generalized Zero Shot Action Generation [8.753131760384964]
  Action-GPT is a framework for incorporating Large Language Models into text-based action generation models. We show that utilizing detailed descriptions instead of the original action phrases leads to better alignment of text and motion spaces.
  arXiv  Detail & Related papers  (2022-11-28T17:57:48Z)
• Being Comes from Not-being: Open-vocabulary Text-to-Motion Generation with Wordless Training [178.09150600453205]
  In this paper, we investigate offline open-vocabulary text-to-motion generation in a zero-shot learning manner. Inspired by the prompt learning in NLP, we pretrain a motion generator that learns to reconstruct the full motion from the masked motion. Our method reformulates the input text into a masked motion as the prompt for the motion generator to reconstruct'' the motion.
  arXiv  Detail & Related papers  (2022-10-28T06:20:55Z)
• Text-driven Video Prediction [83.04845684117835]
  We propose a new task called Text-driven Video Prediction (TVP) Taking the first frame and text caption as inputs, this task aims to synthesize the following frames. To investigate the capability of text in causal inference for progressive motion information, our TVP framework contains a Text Inference Module (TIM)
  arXiv  Detail & Related papers  (2022-10-06T12:43:07Z)
• MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model [35.32967411186489]
  MotionDiffuse is a diffusion model-based text-driven motion generation framework. It excels at modeling complicated data distribution and generating vivid motion sequences. It responds to fine-grained instructions on body parts, and arbitrary-length motion synthesis with time-varied text prompts.
  arXiv  Detail & Related papers  (2022-08-31T17:58:54Z)

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.