# Veritatem Dies Aperit- Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach

## TL;DR

This paper introduces a multi-task recurrent network that jointly predicts depth and semantic labels with temporal consistency, enhancing scene understanding for autonomous systems.

## Contribution

It presents a novel multi-task learning framework with skip connections and adversarial training for consistent depth and semantic predictions over time.

## Key findings

- Outperforms state-of-the-art methods in depth prediction accuracy.
- Achieves more temporally consistent semantic segmentation.
- Demonstrates robustness across various datasets.

## Abstract

Robust geometric and semantic scene understanding is ever more important in many real-world applications such as autonomous driving and robotic navigation. In this paper, we propose a multi-task learning-based approach capable of jointly performing geometric and semantic scene understanding, namely depth prediction (monocular depth estimation and depth completion) and semantic scene segmentation. Within a single temporally constrained recurrent network, our approach uniquely takes advantage of a complex series of skip connections, adversarial training and the temporal constraint of sequential frame recurrence to produce consistent depth and semantic class labels simultaneously. Extensive experimental evaluation demonstrates the efficacy of our approach compared to other contemporary state-of-the-art techniques.