Frustum PointNets for 3D Object Detection from RGB-D Data
This addresses 3D object detection for robotics and autonomous systems, offering an incremental improvement over existing methods by better handling occlusion and sparse data.
The paper tackles 3D object detection from RGB-D data by directly operating on raw point clouds, combining 2D object detectors with 3D deep learning for efficient localization. It achieves state-of-the-art performance on KITTI and SUN RGB-D benchmarks with real-time capability.
In this work, we study 3D object detection from RGB-D data in both indoor and outdoor scenes. While previous methods focus on images or 3D voxels, often obscuring natural 3D patterns and invariances of 3D data, we directly operate on raw point clouds by popping up RGB-D scans. However, a key challenge of this approach is how to efficiently localize objects in point clouds of large-scale scenes (region proposal). Instead of solely relying on 3D proposals, our method leverages both mature 2D object detectors and advanced 3D deep learning for object localization, achieving efficiency as well as high recall for even small objects. Benefited from learning directly in raw point clouds, our method is also able to precisely estimate 3D bounding boxes even under strong occlusion or with very sparse points. Evaluated on KITTI and SUN RGB-D 3D detection benchmarks, our method outperforms the state of the art by remarkable margins while having real-time capability.