2024/11/27 by Yueru Jia, Jia, Yueru, Jiaming Liu +19 · 1 voice · 29 citations
Engineering · #Artificial intelligence #Cartography #Computer science #Foundation (evidence) #Geography #Law #Manufacturing Process and Optimization #Political science #Robot Manipulation and Learning #Robotic Mechanisms and Dynamics #Scale (ratio)
paper · pdf · doi:10.48550/arxiv.2411.18623
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2024/11/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
3D geometric information is essential for manipulation tasks, as robots need to perceive the 3D environment, reason about spatial relationships, and interact with intricate spatial configurations. Recent research has increasingly focused on the explicit extraction of 3D features, while still facing challenges such as the lack of large-scale robotic 3D data and the potential loss of spatial geometry. To address these limitations, we propose the Lift3D framework, which progressively enhances 2D foundation models with implicit and explicit 3D robotic representations to construct a robust 3D manipulation policy. Specifically, we first design a task-aware masked autoencoder that masks task-relevant affordance patches and reconstructs depth information, enhancing the 2D foundation model's implicit 3D robotic representation. After self-supervised fine-tuning, we introduce a 2D model-lifting strategy that establishes a positional mapping between the input 3D points and the positional embeddings of the 2D model. Based on the mapping, Lift3D utilizes the 2D foundation model to directly encode point cloud data, leveraging large-scale pretrained knowledge to construct explicit 3D robotic representations while minimizing spatial information loss. In experiments, Lift3D consistently outperforms previous state-of-the-art methods across several simulation benchmarks and real-world scenarios.