Dynamic Spatial Propagation Network for Depth Completion about digital_image_processing HOT 3 OPEN

from digital_image_processing.

Image-guided depth completion aims to generate dense depth maps with sparse depth measurements and corresponding
RGB images. Currently, spatial propagation networks (SPNs) are the most popular affinity-based methods in depth completion, but they still suffer from the representation limitation of the fixed affinity and the over smoothing during iterations. Our solution is to estimate independent affinity matrices in each SPN iteration, but it is over-parameterized and heavy calculation. This paper introduces an efficient model that learns the affinity among neighboring pixels with an attention-based, dynamic approach. It decouples the neighborhood into parts regarding to different distances and recursively generates independent attention maps to refine these parts into adaptive affinity matrices. Furthermore, we adopt a diffusion suppression (DS) operation so that the model converges at an early stage to prevent oversmoothing of dense depth. Finally, in order to decrease the computational cost required, we also introduce three variations that reduce the amount of neighbors and attentions needed while still retaining similar accuracy.

from digital_image_processing.

So the paper source code is not open until now, when will the author upload the code?

from digital_image_processing.