Learning Long-term Motion Embeddings for Efficient Kinematics Generation

• URL: http://arxiv.org/abs/2604.11737v1
• Date: Mon, 13 Apr 2026 17:14:47 GMT
• Title: Learning Long-term Motion Embeddings for Efficient Kinematics Generation
• Abstract summary: We show how a long-term motion embedding is learned from large-scale trajectories obtained from tracker models.<n>This enables efficient generation of long, realistic motions that fulfill goals specified via text prompts or spatial pokes.<n>The resulting motion distributions outperform those of both state-of-the-art video models and specialized task-specific approaches.
• Score: 22.395558604172127
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding and predicting motion is a fundamental component of visual intelligence. Although modern video models exhibit strong comprehension of scene dynamics, exploring multiple possible futures through full video synthesis remains prohibitively inefficient. We model scene dynamics orders of magnitude more efficiently by directly operating on a long-term motion embedding that is learned from large-scale trajectories obtained from tracker models. This enables efficient generation of long, realistic motions that fulfill goals specified via text prompts or spatial pokes. To achieve this, we first learn a highly compressed motion embedding with a temporal compression factor of 64x. In this space, we train a conditional flow-matching model to generate motion latents conditioned on task descriptions. The resulting motion distributions outperform those of both state-of-the-art video models and specialized task-specific approaches.

Related papers

• GENMO: A GENeralist Model for Human MOtion [64.16188966024542]
  We present GENMO, a unified Generalist Model for Human Motion that bridges motion estimation and generation in a single framework.<n>Our key insight is to reformulate motion estimation as constrained motion generation, where the output motion must precisely satisfy observed conditioning signals.<n>Our novel architecture handles variable-length motions and mixed multimodal conditions (text, audio, video) at different time intervals, offering flexible control.
  arXiv  Detail & Related papers  (2025-05-02T17:59:55Z)
• Segment Any Motion in Videos [80.72424676419755]
  We propose a novel approach for moving object segmentation that combines long-range trajectory motion cues with DINO-based semantic features.<n>Our model employs Spatio-Temporal Trajectory Attention and Motion-Semantic Decoupled Embedding to prioritize motion while integrating semantic support.
  arXiv  Detail & Related papers  (2025-03-28T09:34:11Z)
• A Self-supervised Motion Representation for Portrait Video Generation [19.56640370303683]
  We propose Semantic Latent Motion (SeMo), a compact and expressive motion representation.<n>Our approach achieves both high-quality visual results and efficient inference.<n>Our approach surpasses state-of-the-art models with an 81% win rate in realism.
  arXiv  Detail & Related papers  (2025-03-13T06:43:21Z)
• Motion Prompting: Controlling Video Generation with Motion Trajectories [57.049252242807874]
  We train a video generation model conditioned on sparse or dense video trajectories.<n>We translate high-level user requests into detailed, semi-dense motion prompts.<n>We demonstrate our approach through various applications, including camera and object motion control, "interacting" with an image, motion transfer, and image editing.
  arXiv  Detail & Related papers  (2024-12-03T18:59:56Z)
• Scaling Large Motion Models with Million-Level Human Motions [67.40066387326141]
  We present MotionLib, the first million-level dataset for motion generation.<n>We train a large motion model named projname, demonstrating robust performance across a wide range of human activities.
  arXiv  Detail & Related papers  (2024-10-04T10:48:54Z)
• Lagrangian Motion Fields for Long-term Motion Generation [51.02126882968116]
  We introduce the concept of Lagrangian Motion Fields, specifically designed for long-term motion generation.<n>By treating each joint as a Lagrangian particle with uniform velocity over short intervals, our approach condenses motion representations into a series of "supermotions"<n>Our solution is versatile and lightweight, eliminating the need for neural network preprocessing.
  arXiv  Detail & Related papers  (2024-09-03T01:38:06Z)
• Controllable Longer Image Animation with Diffusion Models [12.565739255499594]
  We introduce an open-domain controllable image animation method using motion priors with video diffusion models. Our method achieves precise control over the direction and speed of motion in the movable region by extracting the motion field information from videos. We propose an efficient long-duration video generation method based on noise reschedule specifically tailored for image animation tasks.
  arXiv  Detail & Related papers  (2024-05-27T16:08:00Z)
• 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)
• Dynamic Future Net: Diversified Human Motion Generation [31.987602940970888]
  Human motion modelling is crucial in many areas such as computer graphics, vision and virtual reality. We present Dynamic Future Net, a new deep learning model where we explicitly focuses on the intrinsic motionity of human motion dynamics. Our model can generate a large number of high-quality motions with arbitrary duration, and visuallyincing variations in both space and time.
  arXiv  Detail & Related papers  (2020-08-25T02:31:41Z)

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.