RoboSnap: One-Shot Real-to-Sim Scene Generation for Generalizable Robot Learning and Evaluation
cs.RO
Submitted: 2026-07-07
Updated: 2026-10-31
Comments: 26 pages, 19 figures, Project page: https://robosnap.github.io
Code: https://github.com/isaac-sim/IsaacSim
Project page: https://robosnap.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- RT-1: Robotics Transformer for Real-World Control at Scale
- OpenVLA: An Open-Source Vision-Language-Action Model
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models
- TabletopGen: Tabletop Scene Generation and Interactive Simulation for Robotic Manipulation
- Scaling Sim-to-Real VLA Reinforcement Learning with Generative 3D Worlds
- SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splatting
- SAM 3D: 3Dfy Anything in Images
- Structured 3D Latents for Scalable and Versatile 3D Generation
- InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts
- Depth Pro: Sharp Monocular Metric Depth in Less Than a Second
- Robo-GS: A Physics Consistent Spatial-Temporal Model for Robotic Arm with Hybrid Representation
- TwinAligner: Visual-Dynamic Alignment Empowers Physics-aware Real2Sim2Real for Robotic Manipulation
- ReBot: Scaling Robot Learning with Real-to-Sim-to-Real Robotic Video Synthesis
- RoboEngine: Plug-and-Play Robot Data Augmentation with Semantic Robot Segmentation and Background Generation
- Real2Render2Real: Scaling Robot Data Without Dynamics Simulation or Robot Hardware
- Novel Demonstration Generation with Gaussian Splatting Enables Robust One-Shot Manipulation
- RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation