DOC-Depth: A novel approach for dense depth ground truth generation
This provides a scalable solution for creating dense depth annotations to facilitate research in computer vision, though it is incremental as it builds on existing LiDAR and odometry techniques.
The paper tackles the lack of dense, accurate depth datasets for dynamic environments by introducing DOC-Depth, a method that uses LiDAR odometry and dynamic object classification to generate dense depth ground truth, improving density on KITTI from 16.1% to 71.2%.
Accurate depth information is essential for many computer vision applications. Yet, no available dataset recording method allows for fully dense accurate depth estimation in a large scale dynamic environment. In this paper, we introduce DOC-Depth, a novel, efficient and easy-to-deploy approach for dense depth generation from any LiDAR sensor. After reconstructing consistent dense 3D environment using LiDAR odometry, we address dynamic objects occlusions automatically thanks to DOC, our state-of-the art dynamic object classification method. Additionally, DOC-Depth is fast and scalable, allowing for the creation of unbounded datasets in terms of size and time. We demonstrate the effectiveness of our approach on the KITTI dataset, improving its density from 16.1% to 71.2% and release this new fully dense depth annotation, to facilitate future research in the domain. We also showcase results using various LiDAR sensors and in multiple environments. All software components are publicly available for the research community.