6 papers
Curating Synthetic Data for Task-Specific Visual Perception
Saptarshi Neil Sinha, Paul Julius Kühn, Michael Weinmann
Synthetic data are most valuable where general-purpose datasets cannot provide the domain-specific priors a task requires, and where manual annotation is expensive, imprecise, or i…
AgenticCADedit: A Stateful, Tool-Mediated Agentic Approach to Multimodal 3D CAD Editing
Saptarshi Neil Sinha, Mika Silvan Goschke, Paul Julius Kühn +2
Computer-aided design is central to industrial manufacturing, and much of a designer's daily work consists of editing existing models from multimodal requests involving speech, ske…
TinyDETR-Pose: Towards End-to-End Real-Time Single-Stage 6DoF Object Pose Estimation with Lightweight Transformers
Paul Julius Kühn, Duc Anh Nguyen, Saptarshi Neil Sinha +2
Real-time 6DoF object pose estimation on resource-constrained hardware remains challenging, as accurate correspondence-based and refinement pipelines typically rely on non-differen…
ScratchSim: A Procedural Synthetic Data Pipeline for Surface Scratch Detection
Paul Julius Kühn, Saptarshi Neil Sinha, Tiago Kleist +3
While automated defect detection such as the detection of surface scratched is an important aspect in industrial quality control, the scarcity of annotated defect data make this ta…
Human-in-the-Loop Atlas-Based 3D Asset Segmentation for Interactive Content Workflows
Paul Julius Kühn, Saptarshi Neil Sinha, Jakob Hansen +1
Segmenting 3D assets into meaningful regions remains challenging, especially when segmentation criteria are application-dependent and require user control. We present a human-in-th…
SynSur: An end-to-end generative pipeline for synthetic industrial surface defect generation and detection
Paul Julius Kühn, Mika Pommeranz, Arjan Kuijper +1
Industrial surface defect inspection suffers from a fundamental data bottleneck: defects are rare, annotations require expert knowledge, and collecting balanced training sets is sl…