Related papers: Kimodo: Scaling Controllable Human Motion Generation

Kimodo: Scaling Controllable Human Motion Generation

URL: http://arxiv.org/abs/2603.15546v1
Date: Mon, 16 Mar 2026 17:09:30 GMT
Title: Kimodo: Scaling Controllable Human Motion Generation
Abstract summary: Kimodo is a controllable kinematic motion diffusion model trained on 700 hours of optical motion capture data.<n>Our model generates high-quality motions while being easily controlled through text and a comprehensive suite of kinematic constraints.
Score: 77.66868439601062
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: High-quality human motion data is becoming increasingly important for applications in robotics, simulation, and entertainment. Recent generative models offer a potential data source, enabling human motion synthesis through intuitive inputs like text prompts or kinematic constraints on poses. However, the small scale of public mocap datasets has limited the motion quality, control accuracy, and generalization of these models. In this work, we introduce Kimodo, an expressive and controllable kinematic motion diffusion model trained on 700 hours of optical motion capture data. Our model generates high-quality motions while being easily controlled through text and a comprehensive suite of kinematic constraints including full-body keyframes, sparse joint positions/rotations, 2D waypoints, and dense 2D paths. This is enabled through a carefully designed motion representation and two-stage denoiser architecture that decomposes root and body prediction to minimize motion artifacts while allowing for flexible constraint conditioning. Experiments on the large-scale mocap dataset justify key design decisions and analyze how the scaling of dataset size and model size affect performance.

Related papers

XmoPipe: A Pipeline for Large-Scale In-the-Wild Human Motion Dataset Construction [39.41824537790665]
Large-scale human motion datasets are essential for training robust motion models for analysis, synthesis, and understanding.<n>Recent advances in monocular motion capture and video-language understanding open the way to extract plausible motion from online videos.<n>We present a scalable pipeline for constructing in-the-wild human motion datasets.
arXiv Detail & Related papers (2026-06-17T09:33:33Z)
Controllable Complex Human Motion Video Generation via Text-to-Skeleton Cascades [32.12940211414945]
We propose a two-stage cascaded framework that addresses both limitations.<n>An autoregressive text-to-skeleton model generates 2D pose sequences from natural language descriptions.<n>A pose-conditioned video diffusion model synthesizes videos from a reference image and the generated skeleton sequence.
arXiv Detail & Related papers (2026-03-09T07:04:29Z)
EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents [85.77432303199176]
We propose EmbodMocap, a portable and affordable data collection pipeline using two moving iPhones.<n>Our key idea is to jointly calibrate dual RGB-D sequences to reconstruct both humans and scenes.<n>Based on the collected data, we empower three embodied AI tasks: monocular human-scene-reconstruction, where we fine-tune feedforward models that output metric-scale, world-space aligned humans and scenes; physics-based character animation, where we prove our data could be used to scale human-object interaction skills and scene-aware motion tracking; and robot motion control, where we train a humanoid robot via
arXiv Detail & Related papers (2026-02-26T16:53:41Z)
FUSION: Full-Body Unified Motion Prior for Body and Hands via Diffusion [49.026972478098266]
Hands are central to interacting with our surroundings and conveying gestures.<n>Existing human motion synthesis methods fall short.<n>Key obstacle is the lack of large-scale datasets that jointly capture diverse full-body motion.
arXiv Detail & Related papers (2026-01-07T14:18:59Z)
FoundationMotion: Auto-Labeling and Reasoning about Spatial Movement in Videos [109.99404241220039]
We introduce FoundationMotion, a fully automated data curation pipeline that constructs large-scale motion datasets.<n>Our approach first detects and tracks objects in videos to extract their trajectories, then leverages these trajectories and video frames with Large Language Models.<n>We fine-tune open-source models including NVILA-Video-15B and Qwen2.5-7B, achieving substantial improvements in motion understanding without compromising performance.
arXiv Detail & Related papers (2025-12-11T18:53:15Z)
SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control [85.91101551600978]
We show that scaling up model capacity, data, and compute yields a generalist humanoid controller capable of creating natural and robust whole-body movements.<n>We build a foundation model for motion tracking by scaling along three axes: network size, dataset volume, and compute.<n>We show the practical utility of our model through two mechanisms: (1) a real-time universal kinematic planner that bridges motion tracking to downstream task execution, enabling natural and interactive control, and (2) a unified token space that supports various motion input interfaces.
arXiv Detail & Related papers (2025-11-11T04:37:40Z)
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)
Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation [47.272177594990104]
We introduce Make-An-Animation, a text-conditioned human motion generation model. It learns more diverse poses and prompts from large-scale image-text datasets. It reaches state-of-the-art performance on text-to-motion generation.
arXiv Detail & Related papers (2023-05-16T17:58:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.