Motion Mamba: Efficient and Long Sequence Motion Generation with Hierarchical and Bidirectional Selective SSM
- URL: http://arxiv.org/abs/2403.07487v3
- Date: Tue, 19 Mar 2024 07:05:37 GMT
- Title: Motion Mamba: Efficient and Long Sequence Motion Generation with Hierarchical and Bidirectional Selective SSM
- Authors: Zeyu Zhang, Akide Liu, Ian Reid, Richard Hartley, Bohan Zhuang, Hao Tang,
- Abstract summary: Recent advancements in state space models (SSMs) have showcased considerable promise in long sequence modeling.
We propose Motion Mamba, a simple and efficient approach that presents the pioneering motion generation model utilized SSMs.
Our proposed method achieves up to 50% FID improvement and up to 4 times faster on the HumanML3D and KIT-ML datasets.
- Score: 26.777455596989526
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Human motion generation stands as a significant pursuit in generative computer vision, while achieving long-sequence and efficient motion generation remains challenging. Recent advancements in state space models (SSMs), notably Mamba, have showcased considerable promise in long sequence modeling with an efficient hardware-aware design, which appears to be a promising direction to build motion generation model upon it. Nevertheless, adapting SSMs to motion generation faces hurdles since the lack of a specialized design architecture to model motion sequence. To address these challenges, we propose Motion Mamba, a simple and efficient approach that presents the pioneering motion generation model utilized SSMs. Specifically, we design a Hierarchical Temporal Mamba (HTM) block to process temporal data by ensemble varying numbers of isolated SSM modules across a symmetric U-Net architecture aimed at preserving motion consistency between frames. We also design a Bidirectional Spatial Mamba (BSM) block to bidirectionally process latent poses, to enhance accurate motion generation within a temporal frame. Our proposed method achieves up to 50% FID improvement and up to 4 times faster on the HumanML3D and KIT-ML datasets compared to the previous best diffusion-based method, which demonstrates strong capabilities of high-quality long sequence motion modeling and real-time human motion generation. See project website https://steve-zeyu-zhang.github.io/MotionMamba/
Related papers
- SMCD: High Realism Motion Style Transfer via Mamba-based Diffusion [12.426879081036116]
Style transfer is widely applied in multimedia scenarios such as movies, games, and the Metaverse.
Most of the current work in this field adopts the GAN, which may lead to instability and convergence issues.
We propose the Style Motion Conditioned Diffusion (SMCD) framework for the first time, which can more comprehensively learn the style features of motion.
arXiv Detail & Related papers (2024-05-05T08:28:07Z) - Large Motion Model for Unified Multi-Modal Motion Generation [50.56268006354396]
Large Motion Model (LMM) is a motion-centric, multi-modal framework that unifies mainstream motion generation tasks into a generalist model.
LMM tackles these challenges from three principled aspects.
arXiv Detail & Related papers (2024-04-01T17:55:11Z) - MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection [5.37935922811333]
MambaMixer is a new architecture with data-dependent weights that uses a dual selection mechanism across tokens and channels.
As a proof of concept, we design Vision MambaMixer (ViM2) and Time Series MambaMixer (TSM2) architectures based on the MambaMixer block.
arXiv Detail & Related papers (2024-03-29T00:05:13Z) - 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) - Spectral Motion Alignment for Video Motion Transfer using Diffusion Models [54.32923808964701]
Spectral Motion Alignment (SMA) is a framework that refines and aligns motion vectors using Fourier and wavelet transforms.
SMA learns motion patterns by incorporating frequency-domain regularization, facilitating the learning of whole-frame global motion dynamics.
Extensive experiments demonstrate SMA's efficacy in improving motion transfer while maintaining computational efficiency and compatibility across various video customization frameworks.
arXiv Detail & Related papers (2024-03-22T14:47:18Z) - 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) - Motion Flow Matching for Human Motion Synthesis and Editing [75.13665467944314]
We propose emphMotion Flow Matching, a novel generative model for human motion generation featuring efficient sampling and effectiveness in motion editing applications.
Our method reduces the sampling complexity from thousand steps in previous diffusion models to just ten steps, while achieving comparable performance in text-to-motion and action-to-motion generation benchmarks.
arXiv Detail & Related papers (2023-12-14T12:57:35Z) - Hierarchical Generation of Human-Object Interactions with Diffusion
Probabilistic Models [71.64318025625833]
This paper presents a novel approach to generating the 3D motion of a human interacting with a target object.
Our framework first generates a set of milestones and then synthesizes the motion along them.
The experiments on the NSM, COUCH, and SAMP datasets show that our approach outperforms previous methods by a large margin in both quality and diversity.
arXiv Detail & Related papers (2023-10-03T17:50:23Z) - MotionTrack: Learning Motion Predictor for Multiple Object Tracking [68.68339102749358]
We introduce a novel motion-based tracker, MotionTrack, centered around a learnable motion predictor.
Our experimental results demonstrate that MotionTrack yields state-of-the-art performance on datasets such as Dancetrack and SportsMOT.
arXiv Detail & Related papers (2023-06-05T04:24:11Z) - Interactive Character Control with Auto-Regressive Motion Diffusion Models [18.727066177880708]
We propose A-MDM (Auto-regressive Motion Diffusion Model) for real-time motion synthesis.
Our conditional diffusion model takes an initial pose as input, and auto-regressively generates successive motion frames conditioned on previous frame.
We introduce a suite of techniques for incorporating interactive controls into A-MDM, such as task-oriented sampling, in-painting, and hierarchical reinforcement learning.
arXiv Detail & Related papers (2023-06-01T07:48:34Z)
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.