Depth completion from sparse LiDAR and high-resolution RGB data is one of the foundations for autonomous driving techniques. Current approaches often rely on CNN-based methods with several known drawbacks: flying pixel at depth discontinuities, overfitting to both a given data set as well as error metric, and many more. Thus, we propose our novel Piecewise Depth Completion (PDC), which works completely without deep learning. PDC segments the RGB image into superpixels corresponding the regions with similar depth value. Superpixels corresponding to same objects are gathered using a cost map. At the end, we receive detailed depth images with state of the art accuracy. In our evaluation, we can show both the influence of the individual proposed processing steps and the overall performance of our method on the challenging KITTI dataset.
PDC: Piecewise Depth Completion utilizing Superpixels
2021-09-19
3075255 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Structure-Sensitive Superpixels via Geodesic Distance
British Library Online Contents | 2013
|SEEDS: Superpixels Extracted Via Energy-Driven Sampling
British Library Online Contents | 2015
|Superpixels: An evaluation of the state-of-the-art
British Library Online Contents | 2018
|Image dehazing using adaptive bi-channel priors on superpixels
British Library Online Contents | 2017
|Image dehazing using adaptive bi-channel priors on superpixels
British Library Online Contents | 2017
|