Recent works have shown that visual pretraining on egocentric datasets using masked autoencoders (MAE) can improve generalization for downstream robotics tasks. However, these approaches pretrain only on 2D images, while many robotics applications require 3D scene understanding. In this work, we propose 3D-MVP, a novel approach for 3D Multi-View Pretraining using masked autoencoders. We leverage Robotic View Transformer (RVT), which uses a multi-view transformer to understand the 3D scene and predict gripper pose actions. We split RVT's multi-view transformer into visual encoder and action decoder, and pretrain its visual encoder using masked autoencoding on large-scale 3D datasets such as Objaverse. We evaluate 3D-MVP on a suite of virtual robot manipulation tasks and demonstrate improved performance over baselines. Our results suggest that 3D-aware pretraining is a promising approach to improve generalization of vision-based robotic manipulation policies. Project site: https://jasonqsy.github.io/3DMVP

翻译：近期研究表明，利用掩码自编码器（MAE）在以自我为中心的数据集上进行视觉预训练，能够提升下游机器人任务的泛化能力。然而，这些方法仅在二维图像上进行预训练，而许多机器人应用需要三维场景理解。本工作提出3D-MVP，一种基于掩码自编码器的三维多视角预训练新方法。我们利用机器人视角变换器（RVT），该模型采用多视角变换器来理解三维场景并预测夹爪位姿动作。我们将RVT的多视角变换器拆分为视觉编码器与动作解码器，并利用Objaverse等大规模三维数据集，通过掩码自编码任务对其视觉编码器进行预训练。我们在系列虚拟机器人操作任务上评估3D-MVP，结果表明其性能优于基线方法。我们的研究结果揭示，三维感知预训练是提升基于视觉的机器人操作策略泛化能力的有效途径。项目主页：https://jasonqsy.github.io/3DMVP