Disp R-CNN is a 3D object detection system for stereo images. It utilizes an instance disparity estimation network (iDispNet) that predicts disparity only for pixels on objects of interest and learns a category-specific shape prior for more accurate disparity estimation. To address the challenge from scarcity of disparity annotation in training, a statistical shape model is used to generate dense disparity pseudo-ground-truth without the need of LiDAR point clouds.
Source: Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity EstimationPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
3D Object Detection | 1 | 20.00% |
3D Object Detection From Stereo Images | 1 | 20.00% |
Disparity Estimation | 1 | 20.00% |
Object Detection | 1 | 20.00% |
Vehicle Pose Estimation | 1 | 20.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |