Plug-and-Play: Improve Depth Estimation via Sparse Data Propagation
This provides a practical solution for applications like autonomous driving by enabling robust dense depth estimation from RGB and sparse LiDAR data, though it is incremental as it builds on existing depth prediction models.
The paper tackles the problem of improving depth estimation by incorporating sparse depth data, such as from LiDAR, into pre-trained models without retraining, achieving consistent improvements on indoor and outdoor datasets like NYU-v2 and KITTI.
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. For project page, see https://zswang666.github.io/PnP-Depth-Project-Page/