AICurious Logo

What is: ViP-DeepLab?

SourceViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

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 tt for frame t+1t + 1. This allows the model to jointly perform video panoptic segmentation and monocular depth estimation.