Unleashing Infinite Motion: Scaling Expressive Quadrupedal Motion via Generative Video Priors

• URL: http://arxiv.org/abs/2606.28237v1
• Date: Fri, 26 Jun 2026 16:23:40 GMT
• Title: Unleashing Infinite Motion: Scaling Expressive Quadrupedal Motion via Generative Video Priors
• Abstract summary: We release Quad-Imaginarium, an open-source dataset of 7,488 quadruped motions spanning acrobatic and performative behaviors.<n>We release Uni-Mo, a fully automated pipeline that removes the animal from the loop by reframing corresponding data as a generation problem.<n>We validate 392 randomly sampled motions on a real Unitree Go2 with a 96.7% success rate, complemented by a 97.6% success rate in simulation.
• Score: 16.885943699439377
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Quadruped robots have achieved remarkable locomotion, yet their behavioral repertoire remains confined to a few gaits--far from the expressive, companion-like presence long envisioned for them. Attempts to import the humanoid recipe of large-scale motion data have inherited one tacit assumption: that robot motion must first pass through an animal body, making data collection dependent on cooperative animals, reconstruction fragile across species, and retargeting ill-posed across incompatible morphologies. We propose Uni-Mo, a fully automated pipeline that removes the animal from the loop by reframing data scarcity as a generation problem: an LLM proposes motion prompts, a video diffusion model synthesizes the corresponding robot behaviors, and the generated videos are lifted into 3D reference trajectories used to train tracking policies deployed on a real Unitree Go2. To make naively-drifting generations reliably extractable, we introduce an Identity Consistency Loss that enforces appearance coherence across frames. We release Quad-Imaginarium at https://github.com/GaoLii/Quad-Imaginarium.git, the resulting open-source dataset of 7,488 language-annotated quadruped motions (18.5 hours) spanning acrobatic and performative behaviors. We validate 392 randomly sampled motions on a real Unitree Go2 with a 96.7% deployment success rate, complemented by a 97.6% success rate across the full dataset in simulation.

Related papers

• UniMo: Unifying Human and Animal Motion Generation [11.84736182625855]
  We propose a unified point cloud-based motion generation framework that bypasses topological discrepancies by converting parametric skeletons into unparametric representations.<n>We present UniML3D, a large-scale motion-language dataset spanning both human and animal categories.<n>Our method achieves state-of-the-art results on UniML3D and three public benchmarks including HumanML3D, KIT-ML, and AnimalML3D.
  arXiv  Detail & Related papers  (2026-09-11T02:08:54Z)
• Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report [25.18747802029395]
  We present ABot-C0, a generalist motion-control system for quadruped robots.<n>We construct a data pyramid through conditional video-generation, annotated motion capture, and human design, producing 16,074 physically feasible motion clips.<n>We then go a step further toward robust all-terrain locomotion by adopting a three-stage privileged-to-perceptive framework.
  arXiv  Detail & Related papers  (2026-07-08T13:04:07Z)
• TopoCap: Learning Topology-Agnostic Motion Priors for Monocular Video-to-Animation [44.79819257609757]
  We introduce TopoCap, the first unified framework capable of extracting motion from monocular video and rigging it onto characters with arbitrary, unseen skeletal topologies.<n>Our key insight is that while skeletal structures are discrete, the underlying physics of motion occupy a continuous, low-dimensional, manifold.<n>We materialize this insight via a two-stage generative pipeline.
  arXiv  Detail & Related papers  (2026-06-10T14:41:19Z)
• GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors [113.71148915419246]
  We present GRAIL, a digital generation pipeline that composes 3D assets, simulator-ready scenes, and priors from video foundation models (VFMs) to synthesize interactions without rebuilding physical environments or teleoperating the robot.<n>GRAIL starts from fully specified 3D configurations in which object geometry, camera parameters, metric scale, environment depth, and a robot-proportioned character are known before video generation and reused during reconstruction.<n>We retarget the recovered motions to a humanoid robot and train complementary task-general morphology trackers.<n>GRAIL produces over 20,000 sequences spanning pick-up, object manipulation, sitting
  arXiv  Detail & Related papers  (2026-06-03T17:57:45Z)
• Learning Reactive Human Motion Generation from Paired Interaction Data Using Transformer-Based Models [0.0]
  This study addresses the problem of generating the motion of one person based on the motion of another in interaction scenarios.<n>We implement and compare three models: a simple Transformer, iTransformer, and Crossformer.<n> Experimental results show that the simple Transformer can generate plausible interaction-aware motions without suffering from posture collapse.
  arXiv  Detail & Related papers  (2026-04-24T02:27:13Z)
• QuadFM: Foundational Text-Driven Quadruped Motion Dataset for Generation and Control [18.78068897227934]
  We introduce Quadruped Foundational Motion (QuadFM), the first large-scale, ultra-high-fidelity dataset for text-to-motion generation and general motion control.<n>QuadFM contains 11,784 curated motion clips spanning locomotion, interactive, and emotion-expressive behaviors.<n>We propose Gen2Control RL, a unified framework that jointly trains a general motion controller and a text-to-motion generator.
  arXiv  Detail & Related papers  (2026-03-25T07:30:25Z)
• RoboCurate: Harnessing Diversity with Action-Verified Neural Trajectory for Robot Learning [47.25770917635344]
  We introduce RoboCurate, a novel synthetic robot data generation framework that evaluates and filters the quality of annotated actions.<n>Specifically, RoboCurate replays the predicted actions in a simulator and assesses action quality by measuring the consistency of motion.<n>We observe RoboCurate's generated data yield substantial relative improvements in success rates compared to using real data only.
  arXiv  Detail & Related papers  (2026-02-21T07:33:24Z)
• Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction [51.49400490437258]
  This work develops a method for imitating articulated object manipulation from a single monocular RGB human demonstration. We first propose 4D Differentiable Part Models (4D-DPM), a method for recovering 3D part motion from a monocular video. Given this 4D reconstruction, the robot replicates object trajectories by planning bimanual arm motions that induce the demonstrated object part motion. We evaluate 4D-DPM's 3D tracking accuracy on ground truth annotated 3D part trajectories and RSRD's physical execution performance on 9 objects across 10 trials each on a bimanual YuMi robot.
  arXiv  Detail & Related papers  (2024-09-26T17:57:16Z)
• OmniMotionGPT: Animal Motion Generation with Limited Data [70.35662376853163]
  We introduce AnimalML3D, the first text-animal motion dataset with 1240 animation sequences spanning 36 different animal identities. We are able to generate animal motions with high diversity and fidelity, quantitatively and qualitatively outperforming the results of training human motion generation baselines on animal data.
  arXiv  Detail & Related papers  (2023-11-30T07:14:00Z)
• 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)
• Learning Motion Priors for 4D Human Body Capture in 3D Scenes [81.54377747405812]
  We propose LEMO: LEarning human MOtion priors for 4D human body capture. We introduce a novel motion prior, which reduces the jitters exhibited by poses recovered over a sequence. We also design a contact friction term and a contact-aware motion infiller obtained via per-instance self-supervised training. With our pipeline, we demonstrate high-quality 4D human body capture, reconstructing smooth motions and physically plausible body-scene interactions.
  arXiv  Detail & Related papers  (2021-08-23T20:47:09Z)
• High-Fidelity Neural Human Motion Transfer from Monocular Video [71.75576402562247]
  Video-based human motion transfer creates video animations of humans following a source motion. We present a new framework which performs high-fidelity and temporally-consistent human motion transfer with natural pose-dependent non-rigid deformations. In the experimental results, we significantly outperform the state-of-the-art in terms of video realism.
  arXiv  Detail & Related papers  (2020-12-20T16:54:38Z)

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.