MGNiceNet: Unified Monocular Geometric Scene Understanding

Abstract

Monocular geometric scene understanding combines panoptic segmentation and self-supervised depth estimation, focusing on real-time application in autonomous vehicles. We introduce MGNiceNet, a unified approach that uses a linked kernel formulation for panoptic segmentation and self-supervised depth estimation. MGNiceNet is based on the state-of-the-art real-time panoptic segmentation method RT-K-Net and extends the architecture to cover both panoptic segmentation and self-supervised monocular depth estimation. To this end, we introduce a tightly coupled self-supervised depth estimation predictor that explicitly uses information from the panoptic path for depth prediction. Furthermore, we introduce a panoptic-guided motion masking method to improve depth estimation without relying on video panoptic segmentation annotations. We evaluate our method on two popular autonomous driving datasets, Cityscapes and KITTI. Our model shows state-of-the-art results compared to other real-time methods and closes the gap to computationally more demanding methods. Source code and trained models are available at https://github.com/markusschoen/MGNiceNet.

References in corpus (5)

• Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
• MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer
• MGNet: Monocular Geometric Scene Understanding for Autonomous Driving
• PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation
• RT-K-Net: Revisiting K-Net for Real-Time Panoptic Segmentation