Deep Planar Parallax for Monocular Depth Estimation
This work addresses depth estimation for autonomous driving systems, representing an incremental improvement over prior learning-based approaches.
The paper tackles monocular depth estimation by improving the use of Planar Parallax Geometry with flow-pretraining and Planar Position Embedding, achieving significant performance gains over existing methods on KITTI and Waymo Open Dataset.
Recent research has highlighted the utility of Planar Parallax Geometry in monocular depth estimation. However, its potential has yet to be fully realized because networks rely heavily on appearance for depth prediction. Our in-depth analysis reveals that utilizing flow-pretrain can optimize the network's usage of consecutive frame modeling, leading to substantial performance enhancement. Additionally, we propose Planar Position Embedding (PPE) to handle dynamic objects that defy static scene assumptions and to tackle slope variations that are challenging to differentiate. Comprehensive experiments on autonomous driving datasets, namely KITTI and the Waymo Open Dataset (WOD), prove that our Planar Parallax Network (PPNet) significantly surpasses existing learning-based methods in performance.