PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation

Winner method of the ICCV-2021 SemKITTI-DVPS Challenge.

[arxiv] [code]

_{Code and model will be available soon. ( 🍺 pending on review)}

Introduction

In this repo, we present PolyphonicFormer, a unified framework for Depth-aware Video Panoptic Segmentation (DVPS).

Demo