ARKitScenes is an RGB-D dataset captured with the widely available Apple LiDAR scanner. Along with the per-frame raw data (Wide Camera RGB, Ultra Wide camera RGB, LiDar scanner depth, IMU) the authors also provide the estimated ARKit camera pose and ARKit scene reconstruction for each iPad Pro sequence. In addition to the raw and processed data from the mobile device, ARKit.
31 PAPERS • 1 BENCHMARK
Boombox is a multi-modal dataset for visual reconstruction from acoustic vibrations. Involves dropping objects into a box and capturing resulting images and vibrations. Used for training ML systems that predict images from vibration.
1 PAPER • NO BENCHMARKS YET