Disparity Estimation of Multi-faceted Objects using Specular Reflections

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, the non-neural disparity estimation algorithm SRDE (Specular Reflection Disparity Estimation) was developed. It exploits the specular reflection that smooth surfaces often exhibit.

Prerequisites

Very good performance in the course “Image, Video, and Multidimensional Signal Processing”, excellent Python programming skills, strong mathematical background