Dietmar Tutsch

In autonomous driving scenarios, the collected LiDAR point clouds can be challenged by occlusion and long-range sparsity, limiting the perception of autonomous driving systems. Scene completion methods can infer the missing parts of incomplete 3D LiDAR scenes. Recent methods adopt local point-level denoising diffusion probabilistic models, which require predicting Gaussian noise, leading to a mismatch between training and inference initial distributions. This paper introduces the first flow matching framework for 3D LiDAR scene completion, improving upon diffusion-based methods by ensuring consistent initial distributions between training and inference. The model employs a nearest neighbor flow matching loss and a Chamfer distance loss to enhance both local structure and global coverage in the alignment of point clouds. LiFlow achieves state-of-the-art performance across multiple metrics. Code: https://github.com/matteandre/LiFlow.

LiDAR scenes constitute a fundamental source for several autonomous driving applications. Despite the existence of several datasets, scenes from adverse weather conditions are rarely available. This limits the robustness of downstream machine learning models, and restrains the reliability of autonomous driving systems in particular locations and seasons. Collecting feature-diverse scenes under adverse weather conditions is challenging due to seasonal limitations. Generative models are therefore essentials, especially for generating adverse weather conditions for specific driving scenarios. In our work, we propose a latent diffusion process constituted by autoencoder and latent diffusion models. Moreover, we leverage the clear condition LiDAR scenes with a postprocessing step to improve the realism of the generated adverse weather condition scenes.

In recent years considerable research in LiDAR semantic segmentation was conducted, introducing several new state of the art models. However, most research focuses on single-scan point clouds, limiting performance especially in long distance outdoor scenarios, by omitting time-sequential information. Moreover, varying-density and occlusions constitute significant challenges in single-scan approaches. In this paper we propose a LiDAR point cloud preprocessing and postprocessing method. This multi-stage approach, in conjunction with state of the art models in a multi-scan setting, aims to solve those challenges. We demonstrate the benefits of our method through quantitative evaluation with the given models in single-scan settings. In particular, we achieve significant improvements in mIoU performance of over 5 percentage point in medium range and over 10 percentage point in far range. This is essential for 3D semantic scene understanding in long distance as well as for applications where offline processing is permissible.

We present a hardware data structure specifically designed for FPGAs that enables the execution of the hard real-time database CRUD operations using a hybrid data structure that combines trees and rings. While the number of rows and columns has to be limited for hard real-time execution, the actual content can be of any size. Our structure restricts full navigational freedom to every but the leaf layer, thus keeping the memory overhead for the data stored in the leaves low. Although its nodes differ in function, all have exactly the same size and structure, reducing the number of cascaded decisions required in the database operations. This enables fast and efficient hardware implementation on FPGAs. In addition to the usual comparison with known data structures, we also analyze the tradeoff between the memory consumption of our approach and a simplified version that is doubly linked in all layers.

In the smart manufacturing sector, analyzing time series data is essential for monitoring plants and machinery to prevent costly failures or shutdowns. In order to gain new insights and make better control decisions, new methods are needed for extracting information and interpreting sensor data from hundreds of systems. In this paper, we present an approach for visualizing and interpreting sensor data from TRIMET Aluminium SE Essen (TAE) using time series meta-features and principal component analysis (PCA). We describe our general approach of generating multiple two-dimensional feature spaces to identify salient and implausible sensor data. Using a set of 20 time series meta-features, we applied our approach to sensor data from TAE which were generated by thermocouples. Each step of the approach was integrated into a dashboard to ensure a user-friendly and approachable interaction in finding salient and implausible sensor data.