LAMP: Lift Image-Editing as General 3D Priors for Open-world Manipulation

TL;DR

LAMP leverages image-editing as 3D priors to extract detailed 3D transformations, enabling precise and generalizable open-world manipulation in robotics.

Contribution

It introduces a novel method that lifts 2D image-editing cues into 3D representations for improved manipulation tasks.

Findings

Achieves accurate 3D transformations in manipulation tasks.

Demonstrates strong zero-shot generalization in open-world scenarios.

Outperforms existing methods in fine-grained spatial reasoning.

Abstract

Human-like generalization in open-world remains a fundamental challenge for robotic manipulation. Existing learning-based methods, including reinforcement learning, imitation learning, and vision-language-action-models (VLAs), often struggle with novel tasks and unseen environments. Another promising direction is to explore generalizable representations that capture fine-grained spatial and geometric relations for open-world manipulation. While large-language-model (LLMs) and vision-language-model (VLMs) provide strong semantic reasoning based on language or annotated 2D representations, their limited 3D awareness restricts their applicability to fine-grained manipulation. To address this, we propose LAMP, which lifts image-editing as 3D priors to extract inter-object 3D transformations as continuous, geometry-aware representations. Our key insight is that image-editing inherently encodes rich 2D spatial cues, and lifting these implicit cues into 3D transformations provides fine-grained and accurate guidance for open-world manipulation. Extensive experiments demonstrate that \codename delivers precise 3D transformations and achieves strong zero-shot generalization in open-world manipulation. Project page: https://zju3dv.github.io/LAMP/.