SOURCE-LINKED INTELLIGENCE

3D scene understanding in two glances

CORDIS · observation · Publication date unknown

ay device and experimental methods to study how adults segment scenes when realistic visual information is available, and develop ground-breaking new technologies using advanced computer graphics and machine learning to simulate the inputs to the visual system from early development to adulthood. We will then conduct in silico experiments in artificial neural networks to understand segmentation learning, by systematically restricting or manipulating different factors. We will compare the learned behaviours of different artificial networks to adults performing segmentation during active exploration of 3D scenes, and use similarities and differences to better understand a fundamental puzzle of perception: how the mind makes sense of scenes. Vision, psychophysics, multifocal display, differentiable rendering, deep neural networks

Read original source ↗ Open in workspace

recordType

award

status

SIGNED

region

EU

value

2083091.25

unit

EUR