Institute of Applied Optics

1 to 2 of 2 Results

Replication Data for: Deep learning based computational imaging and optical metrology Oct 1, 2025 Fu, Liwei, 2025, "Replication Data for: Deep learning based computational imaging and optical metrology", https://doi.org/10.18419/DARUS-5331, DaRUS, V1 A new study explores using deep learning to speed up optical scatterometry, a key quality control technique in computer chip manufacturing. This method could replace older, slower, and data-heavy processes. Manufacturing computer chips involves creating tiny, complex patterns on silicon wafers. The accuracy of these microscopic features is vital fo...
Object Detection on Depth Map with YOLO Nov 9, 2023 Wang, Xiwei, 2023, "Object Detection on Depth Map with YOLO", https://doi.org/10.18419/DARUS-3766, DaRUS, V1 A neural network, based on the ‘You Only Look Once’ (YOLO) network, has been trained to detect objects, using conventional RGB images. Taking advantage of the pixel relationship between the RGB image and the depth map, the positions of the detected objects will be projected onto a depth map. After some statistic analysis, the pixels pertaining to o...

Replication Data for: Deep learning based computational imaging and optical metrology

Oct 1, 2025

Fu, Liwei, 2025, "Replication Data for: Deep learning based computational imaging and optical metrology", https://doi.org/10.18419/DARUS-5331, DaRUS, V1

A new study explores using deep learning to speed up optical scatterometry, a key quality control technique in computer chip manufacturing. This method could replace older, slower, and data-heavy processes. Manufacturing computer chips involves creating tiny, complex patterns on silicon wafers. The accuracy of these microscopic features is vital fo...

Object Detection on Depth Map with YOLO

Nov 9, 2023

Wang, Xiwei, 2023, "Object Detection on Depth Map with YOLO", https://doi.org/10.18419/DARUS-3766, DaRUS, V1

A neural network, based on the ‘You Only Look Once’ (YOLO) network, has been trained to detect objects, using conventional RGB images. Taking advantage of the pixel relationship between the RGB image and the depth map, the positions of the detected objects will be projected onto a depth map. After some statistic analysis, the pixels pertaining to o...

Add Data