|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
Depth completion, the technique of estimating a dense depth image from sparse depth measurements, has a variety of applications in robotics and autonomous driving.
In this paper, we propose a simple yet effective convolutional spatial propagation network (CSPN) to learn the affinity matrix for various depth estimation tasks.
With the rise of data driven deep neural networks as a realization of universal function approximators, most research on computer vision problems has moved away from hand crafted classical image processing algorithms.
However, we additionally propose a fusion method with RGB guidance from a monocular camera in order to leverage object information and to correct mistakes in the sparse input.
We therefore accept this task and propose an evaluation framework for predictive uncertainty estimation that is specifically designed to test the robustness required in real-world computer vision applications.
Comprehensive experiments are performed on the KITTI-Depth benchmark and the results clearly demonstrate that the proposed approach achieves superior performance while requiring only about 5% of the number of parameters compared to the state-of-the-art methods.
To tackle this challenging problem, we introduce an algebraically-constrained convolution layer for CNNs with sparse input and demonstrate its capabilities for the scene depth completion task.
The complementary characteristics of active and passive depth sensing techniques motivate the fusion of the Li-DAR sensor and stereo camera for improved depth perception.