Veritatem Dies Aperit- Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach
This addresses the need for robust geometric and semantic scene understanding in applications like autonomous driving and robotic navigation, representing an incremental improvement through multi-task integration.
The paper tackles the problem of temporally consistent depth prediction by proposing a multi-task learning approach that jointly performs depth estimation/completion and semantic segmentation within a single recurrent network, achieving state-of-the-art performance compared to contemporary techniques.
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.