fangchangma/sparse-to-dense
A Torch implementation of a deep neural network for predicting dense depth maps from sparse depth samples and a single RGB image.
Velocity · 7d
+0.1
★ / day
Trend
→steady
star history
This repository implements the training and testing of deep regression neural networks for depth prediction from sparse depth samples combined with a single image input. The model supports RGB-based, sparse-depth-based, and RGBd-based depth prediction modes. It uses Torch with CUDA and cuDNN for GPU acceleration and was originally published at ICRA 2018.