Expanding Synthetic Real-World Degradations for Blind Video Super Resolution

no code implementations • 4 May 2023 • Mehran Jeelani, Sadbhawna, Noshaba Cheema, Klaus Illgner-Fehns, Philipp Slusallek, Sunil Jaiswal

Video super-resolution (VSR) techniques, especially deep-learning-based algorithms, have drastically improved over the last few years and shown impressive performance on synthetic data.

Video Compression Video Super-Resolution

Edge-aware Consistent Stereo Video Depth Estimation

no code implementations • 4 May 2023 • Elena Kosheleva, Sunil Jaiswal, Faranak Shamsafar, Noshaba Cheema, Klaus Illgner-Fehns, Philipp Slusallek

As a benefit of using stereo inputs, a left-right consistency loss is introduced to improve the performance.

Depth Estimation Pose Estimation

High-Resolution Synthetic RGB-D Datasets for Monocular Depth Estimation

no code implementations • 2 May 2023 • Aakash Rajpal, Noshaba Cheema, Klaus Illgner-Fehns, Philipp Slusallek, Sunil Jaiswal

For experiments and analysis, we train the DPT algorithm, a state-of-the-art transformer-based MDE algorithm on the proposed synthetic dataset, which significantly increases the accuracy of depth maps on different scenes by 9 %.

Autonomous Driving Depth Prediction +2

Leveraging Multi-view Data for Improved Detection Performance: An Industrial Use Case

no code implementations • 17 Apr 2023 • Faranak Shamsafar, Sunil Jaiswal, Benjamin Kelkel, Kireeti Bodduna, Klaus Illgner-Fehns

Printed circuit boards (PCBs) are essential components of electronic devices, and ensuring their quality is crucial in their production.

Multiview Detection Object