A survey on Deep Learning Advances on Different 3D Data Representations
This is an incremental survey that synthesizes existing knowledge for researchers in computer vision and deep learning.
The paper provides a comprehensive survey of deep learning advances on various 3D data representations, highlighting differences between Euclidean and non-Euclidean types and discussing how deep learning methods are applied to tasks like segmentation and recognition.
3D data is a valuable asset the computer vision filed as it provides rich information about the full geometry of sensed objects and scenes. Recently, with the availability of both large 3D datasets and computational power, it is today possible to consider applying deep learning to learn specific tasks on 3D data such as segmentation, recognition and correspondence. Depending on the considered 3D data representation, different challenges may be foreseen in using existent deep learning architectures. In this work, we provide a comprehensive overview about various 3D data representations highlighting the difference between Euclidean and non-Euclidean ones. We also discuss how Deep Learning methods are applied on each representation, analyzing the challenges to overcome.