# IM-ENGINE: Image Editing for Embodied Data Generation

arXiv: https://arxiv.org/abs/2609.06279 · HTML: https://mlsanity.com/paper/2609.06279/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 40 of its 56 references that are in the map.
- First posted on arXiv 5 Sep 2026.

## Builds on (most cited first, 30 of 40)

- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models](https://mlsanity.com/paper/2503.22020/) (2025)
- [GRAB: A Dataset of Whole-Body Human Grasping of Objects](https://mlsanity.com/paper/2008.11200/) (2020)
- [Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots](https://mlsanity.com/paper/2402.10329/) (2024)
- [Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models](https://mlsanity.com/paper/2409.17146/) (2024)
- [DexYCB: A Benchmark for Capturing Hand Grasping of Objects](https://mlsanity.com/paper/2104.04631/) (2021)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models](https://mlsanity.com/paper/2310.10639/) (2023)
- [GELLO: A General, Low-Cost, and Intuitive Teleoperation Framework for Robot Manipulators](https://mlsanity.com/paper/2309.13037/) (2023)
- [ContactPose: A Dataset of Grasps with Object Contact and Hand Pose](https://mlsanity.com/paper/2007.09545/) (2020)
- [OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction](https://mlsanity.com/paper/2203.15709/) (2022)
- [EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos](https://mlsanity.com/paper/2507.12440/) (2025)
- [PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI](https://mlsanity.com/paper/2404.09465/) (2024)
- [FoundPose: Unseen Object Pose Estimation with Foundation Features](https://mlsanity.com/paper/2311.18809/) (2023)
- [What's in your hands? 3D Reconstruction of Generic Objects in Hands](https://mlsanity.com/paper/2204.07153/) (2022)
- [Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction](https://mlsanity.com/paper/2404.00562/) (2024)
- [Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation](https://mlsanity.com/paper/2505.02836/) (2025)
- [ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning](https://mlsanity.com/paper/2503.21860/) (2025)
- [DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation](https://mlsanity.com/paper/2505.21864/) (2025)
- [AffordPose: A Large-scale Dataset of Hand-Object Interactions with Affordance-driven Hand Pose](https://mlsanity.com/paper/2309.08942/) (2023)
- [D(R,O) Grasp: A Unified Representation of Robot and Object Interaction for Cross-Embodiment Dexterous Grasping](https://mlsanity.com/paper/2410.01702/) (2024)
- [Grasp as You Say: Language-guided Dexterous Grasp Generation](https://mlsanity.com/paper/2405.19291/) (2024)
- [Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting](https://mlsanity.com/paper/2411.09823/) (2024)
- [Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations](https://mlsanity.com/paper/2507.00990/) (2025)
- [Revisiting Image Pyramid Structure for High Resolution Salient Object Detection](https://mlsanity.com/paper/2209.09475/) (2022)
- [EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild](https://mlsanity.com/paper/2411.14280/) (2024)

## Abstract (arXiv)

Learning-based manipulation requires supervision that is both semantically meaningful and physically executable, but current data pipelines often provide only one of these properties. Human demonstrations capture intent but are costly to collect and constrained by the human-robot embodiment gap, while simulation can scale data generation but often under-specifies functional behavior. We present IM-ENGINE, a simulator-grounded pipeline that uses image editing as an intermediate representation for embodied data generation. Given a rendered scene with known geometry, depth, segmentation, and camera parameters, IM-ENGINE edits the image to inject task-relevant semantics, recovers explicit 3D state using simulator priors and an unchanged anchor object, refines the state in physics, and converts it into robot-executable supervision. We instantiate the pipeline for dexterous grasp synthesis and goal-state generation. For grasping, IM-ENGINE generates a human grasp in image space, recovers the hand-object interaction, retargets it to a robot hand, and refines it into physically validated robot grasps. For goal generation, it edits a rendered scene into a desired outcome, recovers the target-object pose, and refines it into physically valid, semantically meaningful goals and trajectories. This combination of generative semantic priors and simulator grounding enables scalable task-relevant supervision for robot learning.