mlsanityData to 7 Oct 2026

TwinAligner: Visual-Dynamic Alignment Empowers Physics-aware Real2Sim2Real for Robotic Manipulation

arXiv 2512.19390 ↗First posted 22 Dec 2025cs.RO cs.CV cs.GRcited by 7

Not on the map. Why?

Abstract (arXiv)

The robotics field is evolving towards data-driven, end-to-end learning, inspired by multimodal large models. However, reliance on expensive real-world data limits progress. Simulators offer cost-effective alternatives, but the gap between simulation and reality challenges effective policy transfer. This paper introduces TwinAligner, a novel Real2Sim2Real system that addresses both visual and dynamic gaps. The visual alignment module achieves pixel-level alignment through SDF reconstruction and editable 3DGS rendering, while the dynamic alignment module ensures dynamic consistency by identifying rigid physics from robot-object interaction. TwinAligner improves robot learning by providing scalable data collection and establishing a trustworthy iterative cycle, accelerating algorithm development. Quantitative evaluations highlight TwinAligner's strong capabilities in visual and dynamic real-to-sim alignment. This system enables policies trained in simulation to achieve strong zero-shot generalization to the real world. The high consistency between real-world and simulated policy performance underscores TwinAligner's potential to advance scalable robot learning. Code and data will be released on https://twin-aligner.github.io

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 40 of its 49 references that are in the map. First posted on arXiv 22 Dec 2025.

Builds on

40 of 49 references.

References · 40

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2025Qwen2.5-VL Technical Reportcited by 5,418
  3. 2024GPT-4o System Cardcited by 4,467
  4. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  5. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  6. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  7. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  8. 2024Depth Anything V2cited by 1,385
  9. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  10. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  11. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 914
  12. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
28 more
  1. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
  2. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 411
  3. 2025AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systemscited by 390
  4. 2023PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamicscited by 368
  5. 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 280
  6. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  7. 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 239
  8. 2024PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generationcited by 185
  9. 2024Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulationcited by 135
  10. 2024Reconstruction and Simulation of Elastic Objects with Spring-Mass 3D Gaussianscited by 92
  11. 2025PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videoscited by 78
  12. 2025OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generationcited by 64
  13. 2024SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splattingcited by 63
  14. 2024RoboGSim: A Real2Sim2Real Robotic Gaussian Splatting Simulatorcited by 50
  15. 2024Physical Property Understanding from Language-Embedded Feature Fieldscited by 45
  16. 2025Novel Demonstration Generation with Gaussian Splatting Enables Robust One-Shot Manipulationcited by 45
  17. 2024Dynamic 3D Gaussian Tracking for Graph-Based Neural Dynamics Modelingcited by 42
  18. 2024RISE: 3D Perception Makes Real-World Robot Imitation Simple and Effectivecited by 41
  19. 2025RoboEngine: Plug-and-Play Robot Data Augmentation with Semantic Robot Segmentation and Background Generationcited by 40
  20. 2024Physically Embodied Gaussian Splatting: A Realtime Correctable World Model for Roboticscited by 39
  21. 2025Re3Sim: Generating High-Fidelity Simulation Data via 3D-Photorealistic Real-to-Sim for Robotic Manipulationcited by 38
  22. 2024Gaussian Splashing: Unified Particles for Versatile Motion Synthesis and Renderingcited by 34
  23. 2023Understanding 3D Object Interaction from a Single Imagecited by 33
  24. 2025Scalable Real2Sim: Physics-Aware Asset Generation Via Robotic Pick-and-Place Setupscited by 29
  25. 2025DRAWER: Digital Reconstruction and Articulation With Environment Realismcited by 29
  26. 2025PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulationcited by 22
  27. 2025PUGS: Zero-shot Physical Understanding with Gaussian Splattingcited by 20
  28. 2025DISCOVERSE: Efficient Robot Simulation in Complex High-Fidelity Environmentscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026ContactGaussian-WM: Learning Physics-Grounded World Model from Videoscited by 7
  2. 2026Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agentscited by 6
  3. 2026GASE: Gaussian Splatting-Based Automated System for Reconstructing Embodied-Simulation Environmentscited by 1
  4. 20263D Generation for Embodied AI and Robotic Simulation: A Surveycited by 0
  5. 2026MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searchingcited by 0
  6. 2026TSD: A Physics-Inspired Trajectory Saliency Detector for Efficient Imitation Learningcited by 0
  7. 2026Agentic RSR: Real-to-Sim-to-Real through Scene Reconstruction and Execution-Grounded Robot Policiescited by 0