DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos
cs.CV, cs.RO
Submitted: 2026-05-10
Updated: 2026-11-15
Code: https://github.com/IDEA-Research/Grounded-SAM-2
Project page: https://can-lee.github.io/deformmaster-web
Terminology
Sources
- PhysGen3D: Crafting a Miniature Interactive World from a Single Image
- EMPM: Embodied MPM for Modeling and Simulation of Deformable Objects
- Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals
- Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals
- SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes
- PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos
- CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos
- Learning Physics-Grounded 4D Dynamics with Neural Gaussian Force Fields
- PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification
- WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions
- Depth Anything 3: Recovering the Visual Space from Any Views
- OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation
- RealWonder: Real-Time Physical Action-Conditioned Video Generation
- PhysFlow: Unleashing the Potential of Multi-modal Foundation Models and Video Diffusion for 4D Dynamic Physical Scene Simulation
- Phys4D: Fine-Grained Physics-Consistent 4D Modeling from Video Diffusion
- PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis
- Learning to Simulate Complex Physics with Graph Networks
- MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details
- Structured 3D Latents for Scalable and Versatile 3D Generation
- PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs