Abstract
DragMesh is a real-time interactive 3D framework that decouples kinematic reasoning from motion generation, using Dual Quaternion VAE and FiLM conditioning to achieve plausible, generative articulation.
While generative models have excelled at creating static 3D content, the pursuit of systems that understand how objects move and respond to interactions remains a fundamental challenge. Current methods for articulated motion lie at a crossroads: they are either physically consistent but too slow for real-time use, or generative but violate basic kinematic constraints. We present DragMesh, a robust framework for real-time interactive 3D articulation built around a lightweight motion generation core. Our core contribution is a novel decoupled kinematic reasoning and motion generation framework. First, we infer the latent joint parameters by decoupling semantic intent reasoning (which determines the joint type) from geometric regression (which determines the axis and origin using our Kinematics Prediction Network (KPP-Net)). Second, to leverage the compact, continuous, and singularity-free properties of dual quaternions for representing rigid body motion, we develop a novel Dual Quaternion VAE (DQ-VAE). This DQ-VAE receives these predicted priors, along with the original user drag, to generate a complete, plausible motion trajectory. To ensure strict adherence to kinematics, we inject the joint priors at every layer of the DQ-VAE's non-autoregressive Transformer decoder using FiLM (Feature-wise Linear Modulation) conditioning. This persistent, multi-scale guidance is complemented by a numerically-stable cross-product loss to guarantee axis alignment. This decoupled design allows DragMesh to achieve real-time performance and enables plausible, generative articulation on novel objects without retraining, offering a practical step toward generative 3D intelligence. Code: https://github.com/AIGeeksGroup/DragMesh. Website: https://aigeeksgroup.github.io/DragMesh.
Community
DragMesh enables real time, physically valid 3D object articulation by decoupling kinematic reasoning from motion generation and producing plausible motions via a dual quaternion based generative model.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- UniArt: Unified 3D Representation for Generating 3D Articulated Objects with Open-Set Articulation (2025)
- ArtiLatent: Realistic Articulated 3D Object Generation via Structured Latents (2025)
- URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model (2025)
- KineDiff3D: Kinematic-Aware Diffusion for Category-Level Articulated Object Shape Reconstruction and Generation (2025)
- SPARK: Sim-ready Part-level Articulated Reconstruction with VLM Knowledge (2025)
- ArtiWorld: LLM-Driven Articulation of 3D Objects in Scenes (2025)
- Joint 3D Geometry Reconstruction and Motion Generation for 4D Synthesis from a Single Image (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 1
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper