# DancingBox: A Lightweight MoCap System for Character Animation from Physical Proxies

arXiv: https://arxiv.org/abs/2603.17704 · HTML: https://mlsanity.com/paper/2603.17704/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 66 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Builds on (most cited first, 25 of 25)

- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [OmniControl: Control Any Joint at Any Time for Human Motion Generation](https://mlsanity.com/paper/2310.08580/) (2023)
- [MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model](https://mlsanity.com/paper/2404.19759/) (2024)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [Locally Attentional SDF Diffusion for Controllable 3D Shape Generation](https://mlsanity.com/paper/2305.04461/) (2023)
- [CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos](https://mlsanity.com/paper/2410.11831/) (2024)
- [Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation](https://mlsanity.com/paper/2305.09662/) (2023)
- [PhysCap: Physically Plausible Monocular 3D Motion Capture in Real Time](https://mlsanity.com/paper/2008.08880/) (2020)
- [GENMO: A GENeralist Model for Human MOtion](https://mlsanity.com/paper/2505.01425/) (2025)
- [Puppeteer: Rig and Animate Your 3D Models](https://mlsanity.com/paper/2508.10898/) (2025)
- [AnyTop: Character Animation Diffusion with Any Topology](https://mlsanity.com/paper/2502.17327/) (2025)
- [Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement](https://mlsanity.com/paper/2311.16495/) (2023)
- [SketchDream: Sketch-based Text-to-3D Generation and Editing](https://mlsanity.com/paper/2405.06461/) (2024)
- [A review of 3D human pose estimation algorithms for markerless motion capture](https://mlsanity.com/paper/2010.06449/) (2020)
- [OmniMotionGPT: Animal Motion Generation with Limited Data](https://mlsanity.com/paper/2311.18303/) (2023)
- [Sketch2Anim: Towards Transferring Sketch Storyboards into 3D Animation](https://mlsanity.com/paper/2504.19189/) (2025)
- [MOSPA: Human Motion Generation Driven by Spatial Audio](https://mlsanity.com/paper/2507.11949/) (2025)
- [Multi-Person Interaction Generation from Two-Person Motion Priors](https://mlsanity.com/paper/2505.17860/) (2025)
- [DualMotion: Global-to-Local Casual Motion Design for Character Animations](https://mlsanity.com/paper/2208.08636/) (2022)

## Built on by (most cited first, 1 of 1)

- [AnyAct: Towards Human Reenactment of Character Motion From Video](https://mlsanity.com/paper/2605.15497/) (2026)

## Abstract (arXiv)

Creating compelling 3D character animations typically requires either expert use of professional software or expensive motion capture systems operated by skilled actors. We present DancingBox, a lightweight, vision-based system that makes motion capture accessible to novices by reimagining the process as digital puppetry. Instead of tracking precise human motions, DancingBox captures the approximate movements of everyday objects manipulated by users with a single webcam. These coarse proxy motions are then refined into realistic character animations by conditioning a generative motion model on bounding-box representations, enriched with human motion priors learned from large-scale datasets. To overcome the lack of paired proxy-animation data, we synthesize training pairs by converting existing motion capture sequences into proxy representations. A user study demonstrates that DancingBox enables intuitive and creative character animation using diverse proxies, from plush toys to bananas, lowering the barrier to entry for novice animators.