Tim Rolff
YOU?
Author Swipe
View article: Tokenization of Gaze Data
Tokenization of Gaze Data Open
A considerable part of the performance of today's large language models (LLM's) and multimodal large language models (MLLM's) depends on their tokenization strategies. While tokenizers are extensively researched for textual and visual inpu…
View article: A Hands-free Spatial Selection and Interaction Technique using Gaze and Blink Input with Blink Prediction for Extended Reality
A Hands-free Spatial Selection and Interaction Technique using Gaze and Blink Input with Blink Prediction for Extended Reality Open
Gaze-based interaction techniques have created significant interest in the field of spatial interaction. Many of these methods require additional input modalities, such as hand gestures (e.g., gaze coupled with pinch). Those can be uncomfo…
View article: A Toolkit for Virtual Reality Data Collection
A Toolkit for Virtual Reality Data Collection Open
Due to the still relatively low number of users, acquiring large-scale and multidimensional virtual reality datasets remains a significant challenge. Consequently, VR datasets comparable in size to state-of-the-art collections in natural l…
View article: SOS: Segment Object System for Open-World Instance Segmentation With Object Priors
SOS: Segment Object System for Open-World Instance Segmentation With Object Priors Open
We propose an approach for Open-World Instance Segmentation (OWIS), a task that aims to segment arbitrary unknown objects in images by generalizing from a limited set of annotated object classes during training. Our Segment Object System (…
View article: Magic NeRF lens: interactive fusion of neural radiance fields for virtual facility inspection
Magic NeRF lens: interactive fusion of neural radiance fields for virtual facility inspection Open
Virtual reality (VR) has become an important interactive visualization tool for various industrial processes including facility inspection and maintenance. The capability of a VR application to present users with realistic simulations of c…
View article: Select High-Level Features: Efficient Experts from a Hierarchical Classification Network
Select High-Level Features: Efficient Experts from a Hierarchical Classification Network Open
This study introduces a novel expert generation method that dynamically reduces task and computational complexity without compromising predictive performance. It is based on a new hierarchical classification network topology that combines …
View article: High-Level Parallelism and Nested Features for Dynamic Inference Cost and Top-Down Attention
High-Level Parallelism and Nested Features for Dynamic Inference Cost and Top-Down Attention Open
This paper introduces a novel network topology that seamlessly integrates dynamic inference cost with a top-down attention mechanism, addressing two significant gaps in traditional deep learning models. Drawing inspiration from human perce…
View article: Magic NeRF Lens: Interactive Fusion of Neural Radiance Fields for Virtual Facility Inspection
Magic NeRF Lens: Interactive Fusion of Neural Radiance Fields for Virtual Facility Inspection Open
Large industrial facilities such as particle accelerators and nuclear power plants are critical infrastructures for scientific research and industrial processes. These facilities are complex systems that not only require regular maintenanc…
View article: Immersive Neural Graphics Primitives
Immersive Neural Graphics Primitives Open
Neural radiance field (NeRF), in particular its extension by instant neural graphics primitives, is a novel rendering method for view synthesis that uses real-world images to build photo-realistic immersive virtual scenes. Despite its pote…
View article: Gaze Mapping for Immersive Virtual Environments Based on Image Retrieval
Gaze Mapping for Immersive Virtual Environments Based on Image Retrieval Open
In this paper, we introduce a novel gaze mapping approach for free viewing conditions in dynamic immersive virtual environments (VEs), which projects recorded eye fixation data of users, who viewed the VE from different perspectives, to th…
View article: Segmenting Computer-Tomographic Scans of Ancient Clay Artefacts for Visual Analysis of Cuneiform Inscriptions
Segmenting Computer-Tomographic Scans of Ancient Clay Artefacts for Visual Analysis of Cuneiform Inscriptions Open
We address the automatic segmentation of computer tomographic scans of ancient clay tablets with cuneiform inscriptions enclosed inside a clay envelope. Such separation of parts of similar material properties in the scan enables domain sci…