Abstract:
Convolutional neural networks are designed for dense data, but vision data is often sparse (stereo depth, point clouds, pen stroke, etc.). We present a method to handle s...Show MoreMetadata
Abstract:
Convolutional neural networks are designed for dense data, but vision data is often sparse (stereo depth, point clouds, pen stroke, etc.). We present a method to handle sparse depth data with optional dense RGB, and accomplish depth completion and semantic segmentation changing only the last layer. Our proposal efficiently learns sparse features without the need of an additional validity mask. We show how to ensure network robustness to varying input sparsities. Our method even works with densities as low as 0.8% (8 layer lidar), and outperforms all published state-of-the-art on the Kitti depth completion benchmark.
Published in: 2018 International Conference on 3D Vision (3DV)
Date of Conference: 05-08 September 2018
Date Added to IEEE Xplore: 14 October 2018
ISBN Information: