ViP-DeepLab is a model for depth-aware video panoptic segmentation. It extends Panoptic-DeepLab by adding a depth prediction head to perform monocular depth estimation and a next-frame instance branch which regresses to the object centers in frame $t$ for frame $t + 1$. This allows the model to jointly perform video panoptic segmentation and monocular depth estimation.
Source: ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic SegmentationPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Depth Estimation | 1 | 25.00% |
Monocular Depth Estimation | 1 | 25.00% |
Panoptic Segmentation | 1 | 25.00% |
Video Panoptic Segmentation | 1 | 25.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |