Deep Stereo Geometry Network is a 3D object detection pipeline that relies on space transformation from 2D features to an effective 3D structure, called 3D geometric volume (3DGV). The whole neural network consists of four components. (a) A 2D image feature extractor for capture of both pixel- and high-level feature. (b) Constructing the plane-sweep volume and 3D geometric volume. (c) Depth Estimation on the plane-sweep volume. (d) 3D object detection on 3D geometric volume.
Source: DSGN: Deep Stereo Geometry Network for 3D Object DetectionPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
3D Object Detection | 3 | 30.00% |
3D Object Detection From Stereo Images | 2 | 20.00% |
Object Detection | 2 | 20.00% |
Autonomous Driving | 1 | 10.00% |
Autonomous Vehicles | 1 | 10.00% |
Vehicle Pose Estimation | 1 | 10.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |