Evaluating the Impact of Specular-Aware Data Augmentation on State-of-the-Art Disparity Estimation Networks

Description

Disparity estimation plays a crucial role in computer vision, particularly for depth perception and 3D reconstruction. While neural networks have achieved remarkable performance in this domain, they struggle with smooth and textureless surfaces like plastics. To address this issue, state-of-the-art networks for disparity estimation shall be retrained with additional data.

Prerequisites

Excellent knowledge of Python programming, experience in ML/DL