Exploring Deep 3D Spatial Encodings for Large-Scale 3D Scene Understanding

no code implementations • 29 Nov 2020 • Saqib Ali Khan, Yilei Shi, Muhammad Shahzad, Xiao Xiang Zhu

In this letter, we have proposed an alternative approach to overcome the limitations of CNN based approaches by encoding the spatial features of raw 3D point clouds into undirected symmetrical graph models.

Scene Understanding Semantic Segmentation

Table Structure Extraction with Bi-directional Gated Recurrent Unit Networks

no code implementations • 8 Jan 2020 • Saqib Ali Khan, Syed Muhammad Daniyal Khalid, Muhammad Ali Shahzad, Faisal Shafait

Tables present summarized and structured information to the reader, which makes table structure extraction an important part of document understanding applications.

document understanding Optical Character Recognition +1