Monkey See, Monkey Do: Harnessing Self-attention in Motion Diffusion for Zero-shot Motion Transfer

• URL: http://arxiv.org/abs/2406.06508v1
• Date: Mon, 10 Jun 2024 17:47:14 GMT
• Title: Monkey See, Monkey Do: Harnessing Self-attention in Motion Diffusion for Zero-shot Motion Transfer
• Authors: Sigal Raab, Inbar Gat, Nathan Sala, Guy Tevet, Rotem Shalev-Arkushin, Ohad Fried, Amit H. Bermano, Daniel Cohen-Or,
• Abstract summary: Existing diffusion-based motion editing methods overlook the profound potential of the prior embedded within the weights of pre-trained models. We uncover the roles and interactions of attention elements in capturing and representing motion patterns. We integrate these elements to transfer a leader motion to a follower one while maintaining the nuanced characteristics of the follower, resulting in zero-shot motion transfer.
• Score: 55.109778609058154
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Given the remarkable results of motion synthesis with diffusion models, a natural question arises: how can we effectively leverage these models for motion editing? Existing diffusion-based motion editing methods overlook the profound potential of the prior embedded within the weights of pre-trained models, which enables manipulating the latent feature space; hence, they primarily center on handling the motion space. In this work, we explore the attention mechanism of pre-trained motion diffusion models. We uncover the roles and interactions of attention elements in capturing and representing intricate human motion patterns, and carefully integrate these elements to transfer a leader motion to a follower one while maintaining the nuanced characteristics of the follower, resulting in zero-shot motion transfer. Editing features associated with selected motions allows us to confront a challenge observed in prior motion diffusion approaches, which use general directives (e.g., text, music) for editing, ultimately failing to convey subtle nuances effectively. Our work is inspired by how a monkey closely imitates what it sees while maintaining its unique motion patterns; hence we call it Monkey See, Monkey Do, and dub it MoMo. Employing our technique enables accomplishing tasks such as synthesizing out-of-distribution motions, style transfer, and spatial editing. Furthermore, diffusion inversion is seldom employed for motions; as a result, editing efforts focus on generated motions, limiting the editability of real ones. MoMo harnesses motion inversion, extending its application to both real and generated motions. Experimental results show the advantage of our approach over the current art. In particular, unlike methods tailored for specific applications through training, our approach is applied at inference time, requiring no training. Our webpage is at https://monkeyseedocg.github.io.

Related papers

• MotionFollower: Editing Video Motion via Lightweight Score-Guided Diffusion [94.66090422753126]
  MotionFollower is a lightweight score-guided diffusion model for video motion editing. It delivers superior motion editing performance and exclusively supports large camera movements and actions. Compared with MotionEditor, the most advanced motion editing model, MotionFollower achieves an approximately 80% reduction in GPU memory.
  arXiv  Detail & Related papers  (2024-05-30T17:57:30Z)
• CoMo: Controllable Motion Generation through Language Guided Pose Code Editing [57.882299081820626]
  We introduce CoMo, a Controllable Motion generation model, adept at accurately generating and editing motions. CoMo decomposes motions into discrete and semantically meaningful pose codes. It autoregressively generates sequences of pose codes, which are then decoded into 3D motions.
  arXiv  Detail & Related papers  (2024-03-20T18:11:10Z)
• MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation [19.999239668765885]
  MotionMix is a weakly-supervised diffusion model that leverages both noisy and unannotated motion sequences. Our framework consistently achieves state-of-the-art performances on text-to-motion, action-to-motion, and music-to-dance tasks.
  arXiv  Detail & Related papers  (2024-01-20T04:58:06Z)
• MotionCrafter: One-Shot Motion Customization of Diffusion Models [66.44642854791807]
  We introduce MotionCrafter, a one-shot instance-guided motion customization method. MotionCrafter employs a parallel spatial-temporal architecture that injects the reference motion into the temporal component of the base model. During training, a frozen base model provides appearance normalization, effectively separating appearance from motion.
  arXiv  Detail & Related papers  (2023-12-08T16:31:04Z)
• Universal Humanoid Motion Representations for Physics-Based Control [71.46142106079292]
  We present a universal motion representation that encompasses a comprehensive range of motor skills for physics-based humanoid control. We first learn a motion imitator that can imitate all of human motion from a large, unstructured motion dataset. We then create our motion representation by distilling skills directly from the imitator.
  arXiv  Detail & Related papers  (2023-10-06T20:48:43Z)
• Priority-Centric Human Motion Generation in Discrete Latent Space [59.401128190423535]
  We introduce a Priority-Centric Motion Discrete Diffusion Model (M2DM) for text-to-motion generation. M2DM incorporates a global self-attention mechanism and a regularization term to counteract code collapse. We also present a motion discrete diffusion model that employs an innovative noise schedule, determined by the significance of each motion token.
  arXiv  Detail & Related papers  (2023-08-28T10:40:16Z)
• 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)
• Self-supervised Motion Learning from Static Images [36.85209332144106]
  Motion from Static Images (MoSI) learns to encode motion information. MoSI can discover regions with large motion even without fine-tuning on the downstream datasets. We demonstrate that MoSI can discover regions with large motion even without fine-tuning on the downstream datasets.
  arXiv  Detail & Related papers  (2021-04-01T03:55:50Z)

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.