Frustum PointNets for 3D Object Detection from RGB-D Data
read the original abstract
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Deep Radar Detector
A deep neural network trained on radar calibration data with custom augmentations outperforms classical methods on 4D detection while running in real time.
-
Voxel-FPN: multi-scale voxel feature aggregation in 3D object detection from point clouds
Voxel-FPN proposes an encoder-decoder architecture for multi-scale voxel feature aggregation in one-stage 3D object detection from point clouds, reporting competitive speed and accuracy on KITTI-3D.
-
End-to-End 3D-PointCloud Semantic Segmentation for Autonomous Driving
Proposes weighted self-incremental transfer learning to address class imbalance in 3D point cloud semantic segmentation and reports a new benchmark on the KITTI dataset.
-
A review on deep learning techniques for 3D sensed data classification
A survey of deep learning architectures for 3D sensed data classification covering RGB-D, multi-view, volumetric and end-to-end methods along with datasets and future directions.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.