Fast Semi-dense Depth Map Estimation

P. 18–21.

Макаров И. А., Alisa Korinevskaya, Vladimir Aliev

We consider the problem of depth reconstruction from downsampled sparse depth values. We compare our approach with semi-dense depth map interpolation and direct RGB-to-Depth reconstruction solutions on several datasets, including Matterport 3D dataset containing RGB and depth images of 90 building-scale scenes. We demonstrate that the proposed model can produce approximate depth map for over two hundreds images per second.

Ключевые слова: computer vision, depth reconstruction

ПУБЛИКАЦИЯ ПОДГОТОВЛЕНА ПО РЕЗУЛЬТАТАМ ПРОЕКТА: Прикладные сетевые исследования в эпоху больших данных и новых технологических разработок (2018)

В книге

Proceedings of the 2018 ACM ICMR Workshop on Multimedia for Real Estate Tech

NY: Association for Computing Machinery (ACM), 2018.