Plug-and-Play: Improve Depth Prediction via Sparse Data Propagation
| Autor: | Juan-Ting Lin, Yi-Hsuan Tsai, Min Sun, Tsun-Hsuan Wang, Fu-En Wang, Wei-Chen Chiu |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
business.industry Plug and play Pattern recognition 02 engineering and technology 010501 environmental sciences 01 natural sciences Lidar Feature (computer vision) Depth map 0202 electrical engineering electronic engineering information engineering RGB color model 020201 artificial intelligence & image processing Artificial intelligence business 0105 earth and related environmental sciences Sparse matrix |
| Zdroj: | ICRA |
| DOI: | 10.1109/icra.2019.8794404 |
| Popis: | We propose a novel plug-and-play (PnP) module for improving depth prediction with taking arbitrary patterns of sparse depths as input. Given any pre-trained depth prediction model, our PnP module updates the intermediate feature map such that the model outputs new depths consistent with the given sparse depths. Our method requires no additional training and can be applied to practical applications such as leveraging both RGB and sparse LiDAR points to robustly estimate dense depth map. Our approach achieves consistent improvements on various state-of-the-art methods on indoor (i.e., NYU-v2) and outdoor (i.e., KITTI) datasets. Various types of LiDARs are also synthesized in our experiments to verify the general applicability of our PnP module in practice. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|