DISCOMAN: Dataset of Indoor SCenes for Odometry, Mapping And Navigation
This dataset addresses the need for large-scale benchmarks focused on mapping in SLAM, particularly for indoor navigation and robotics applications, though it is incremental as it builds on existing dataset efforts.
The authors introduced DISCOMAN, a novel dataset of 200 long sequences with 3000-5000 frames each for training and benchmarking semantic SLAM methods, featuring RGB images, depth, IMU readings, and ground truth occupancy grids, and presented benchmarking results for various algorithms including classical and learning-based SLAM.
We present a novel dataset for training and benchmarking semantic SLAM methods. The dataset consists of 200 long sequences, each one containing 3000-5000 data frames. We generate the sequences using realistic home layouts. For that we sample trajectories that simulate motions of a simple home robot, and then render the frames along the trajectories. Each data frame contains a) RGB images generated using physically-based rendering, b) simulated depth measurements, c) simulated IMU readings and d) ground truth occupancy grid of a house. Our dataset serves a wider range of purposes compared to existing datasets and is the first large-scale benchmark focused on the mapping component of SLAM. The dataset is split into train/validation/test parts sampled from different sets of virtual houses. We present benchmarking results forboth classical geometry-based and recent learning-based SLAM algorithms, a baseline mapping method, semantic segmentation and panoptic segmentation.