StereoPolicy Learns 3D Structure Directly From Stereo Images

Loading video

Loading video

StereoPolicy removes the need for depth sensors, depth maps, point clouds, and LiDAR by learning 3D structure directly from stereo image pairs. Across five real-world tabletop manipulation tasks, it reaches 59% success compared with 42% for RGB, 41% for RGB-D, and 14% for PointNet.