This paper introduces a novel self-supervised learning method for completing depth maps of transparent objects, a challenging task for conventional sensors. By simulating transparent object depth deficits within non-transparent regions, the approach significantly reduces reliance on costly labeled data while achieving comparable performance to supervised methods.

This paper explores the use of a lightweight and scalable EfficientNet architecture, combined with global jet features, for the computationally inexpensive yet competitive classification of top-quark jets. It aims to address the high computational demands of current state-of-the-art jet tagging methods like Transformers and GNNs.

MLLMs often lack transparent reasoning, merely providing final predictions without intermediate steps or visual evidence. This paper introduces the Visual Reasoning Tracer (VRT) task and associated benchmarks (VRT-Bench, VRT-80k) to explicitly require models to localize intermediate objects in their reasoning paths, significantly enhancing model interpretability and reliability.

This paper introduces a modular architecture for autonomous vehicles designed for racing in closed circuits. It integrates perception, localization, path planning, and control subsystems to achieve real-time, precise autonomous navigation in controlled environments.

This paper introduces "Artificial Microsaccade Compensation," a real-time video stabilization method inspired by biological microsaccades. It enables stable camera-based perception for aggressively shaking tailless ornithopters, a significant challenge for autonomous flapping-wing robots.

This PhD thesis presents innovations to improve the efficiency of normalizing flows through new architectures and algorithms, alongside applying generative models to diverse computer vision challenges such as agricultural quality assessment, privacy-preserving autonomous driving, geological mapping, art restoration, and missing traffic sign detection.

This study evaluates the performance of YOLOv7, an advanced object detection model, in identifying kitchen safety risks related to knife handling, specifically improper finger placement and blade contact with the hand. The findings highlight YOLOv7's strong potential for accurately detecting these hazards to improve kitchen safety.