Multi-View Masked Autoencoders for Visual Control
ICLR 2023(2023)
摘要
This paper investigates how to leverage data from multiple cameras to learn representations beneficial for visual control. To this end, we present the Multi-View Masked Autoencoder (MV-MAE), a simple and scalable framework for multi-view representation learning. Our main idea is to mask multiple viewpoints from video frames at random and train a video autoencoder to reconstruct pixels of both masked and unmasked viewpoints. This allows the model to learn representations that capture useful information of the current viewpoint but also the cross-view information from different viewpoints. We evaluate MV-MAE on challenging RLBench visual manipulation tasks by training a reinforcement learning agent on top of frozen representations. Our experiments demonstrate that MV-MAE significantly outperforms other multi-view representation learning approaches. Moreover, we show that the number of cameras can differ between the representation learning phase and the behavior learning phase. By training a single-view control agent on top of multi-view representations from MV-MAE, we achieve 62.3% success rate while the single-view representation learning baseline achieves 42.3%.
更多查看译文
关键词
visual control,masked autoencoder,representation learning,world model
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要