Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation

Autor:	Jaritz, Maximilian, de Charette, Raoul, Wirbel, Emilie, Perrotton, Xavier, Nashashibi, Fawzi
Rok vydání:	2018
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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. Comment: 3DV 2018
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1808.00769 Zobrazit plný text záznamu View this record from Arxiv