Master Theses – Offered

Browse all posts in the Master Theses – Offered category.

1 to 6 of 11

11MAY 2026
Master Theses – Offered
Differentiable Digital Signal Processing for Audio
Description Classical DSP gives us compact, interpretable building blocks — filters, oscillators, delay lines, nonlinearities — that have powered audio technology for decades. Deep learning, on the other hand, offers powerful data-driven modeling but often at the cost of efficiency and transparency. Differentiable DSP brings the two together: by making signal processing structures differentiable, their […]Description Classical DSP gives us compact, interpretable building blocks — filters, oscillators, delay lines, nonlinearities — that have powered audio technology for decades. Deep learning, on the other hand, offers powerful data-driven modeling but often at the cost of efficiency and transparency. Differentiable DSP brings the two together: by making signal processing structures differentiable, their […]
Read more about Differentiable Digital Signal Processing for Audio
21APR 2026
Master Theses – Offered
Generative Models for Audio Inverse Problems
Description Inverse problems concern the estimation of an unobserved signal from degraded observations produced by a forward process. Such problems are inherently challenging, as the inverse mapping is often ill-posed: solutions may be non-unique, unstable, or may not exist. In the audio domain, examples include stem separation, dereverberation, denoising, and timbre transfer. Recent approaches address […]Description Inverse problems concern the estimation of an unobserved signal from degraded observations produced by a forward process. Such problems are inherently challenging, as the inverse mapping is often ill-posed: solutions may be non-unique, unstable, or may not exist. In the audio domain, examples include stem separation, dereverberation, denoising, and timbre transfer. Recent approaches address […]
Read more about Generative Models for Audio Inverse Problems
02APR 2026
Bachelor Theses – Offered
Analysis of Visual Foundation Models with Applications to Video Coding for Machines
Description Visual Foundation models (VFM), like DINOv3, V-JEPA,… are widely employed for diverse computer vision tasks. Unlike traditional computer vision pipelines, VFMs learn rich, transferable representations from vast amounts of data, enabling strong generalization across tasks with little to no finetuning. This research shall explore the usage of VFM models in machine-to-machine communication of visual […]Description Visual Foundation models (VFM), like DINOv3, V-JEPA,… are widely employed for diverse computer vision tasks. Unlike traditional computer vision pipelines, VFMs learn rich, transferable representations from vast amounts of data, enabling strong generalization across tasks with little to no finetuning. This research shall explore the usage of VFM models in machine-to-machine communication of visual […]
Read more about Analysis of Visual Foundation Models with Applications to Video Coding for Machines
24MAR 2026
Master Theses – Offered
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 […]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 […]
Read more about Disparity Estimation of Multi-faceted Objects using Specular Reflections
16MAR 2026
Master Theses – Completed
Exploring Multi-View Image Fusion for LiDAR Upsampling
Description Recent advances in autonomous driving perception increasingly rely on multi-view,multi-sensor fusion to recover dense and semantically consistent 3D scene representations.While LiDAR upsampling has been explored, it remains an open problem. Often treated as astandalone task without leveraging complementary visual cues or learning consistent geometricpriors across modalities. This thesis proposes a cross modal transformer framework […]Description Recent advances in autonomous driving perception increasingly rely on multi-view,multi-sensor fusion to recover dense and semantically consistent 3D scene representations.While LiDAR upsampling has been explored, it remains an open problem. Often treated as astandalone task without leveraging complementary visual cues or learning consistent geometricpriors across modalities. This thesis proposes a cross modal transformer framework […]
Read more about Exploring Multi-View Image Fusion for LiDAR Upsampling
17FEB 2026
Bachelor Theses – Offered
Adaptive coding in JPEG AI
Description The recently adopted image coding standard JPEG AI uses neural networks to encode images efficiently. In doing so, it achieves a comparatively low bitrate while maintaining high image quality. Both in classical and learning-based coding, it has been shown that techniques that adaptively respond to image content enable higher compression rates. When adopting a […]
Read more about Adaptive coding in JPEG AI