EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI
This addresses the problem of enabling embodied agents to understand 3D scenes from a first-person view for robotics and computer vision, though it is incremental as it builds on existing datasets and methods.
The authors tackled the gap in ego-centric 3D scene understanding for embodied AI by introducing EmbodiedScan, a multi-modal dataset with over 5k scans, 1M RGB-D views, and 1M language prompts, and a baseline framework that demonstrates strong performance in benchmarks.
In the realm of computer vision and robotics, embodied agents are expected to explore their environment and carry out human instructions. This necessitates the ability to fully understand 3D scenes given their first-person observations and contextualize them into language for interaction. However, traditional research focuses more on scene-level input and output setups from a global view. To address the gap, we introduce EmbodiedScan, a multi-modal, ego-centric 3D perception dataset and benchmark for holistic 3D scene understanding. It encompasses over 5k scans encapsulating 1M ego-centric RGB-D views, 1M language prompts, 160k 3D-oriented boxes spanning over 760 categories, some of which partially align with LVIS, and dense semantic occupancy with 80 common categories. Building upon this database, we introduce a baseline framework named Embodied Perceptron. It is capable of processing an arbitrary number of multi-modal inputs and demonstrates remarkable 3D perception capabilities, both within the two series of benchmarks we set up, i.e., fundamental 3D perception tasks and language-grounded tasks, and in the wild. Codes, datasets, and benchmarks will be available at https://github.com/OpenRobotLab/EmbodiedScan.