6 papers
SynGallery: A Synthetic Gallery of Real Paintings for Instance-Level Artwork Recognition
Patryk Bartkowiak, Jakub Markil, Bartosz Kotrys +4
Instance-level artwork recognition requires matching a handheld visitor photograph to a specific work in a large museum collection. This is challenging because painting datasets ty…
MaSC: A Masked Similarity Metric for Evaluating Concept-Driven Generation
Patryk Bartkowiak, Lennart Petersen, Bartosz Kotrys +3
Evaluating single-concept personalization in text-to-image diffusion requires measuring both concept preservation, which captures identity fidelity to a reference, and prompt follo…
SADGE: Structure and Appearance Domain Gap Estimation of Synthetic and Real Data
Patryk Bartkowiak, Bartosz Kotrys, Dominik Michels +2
We propose SADGE, a quantitative similarity metric that predicts the performance of synthetic image datasets for common computer vision tasks without downstream model training. Est…
SynVA: A Modular Toolkit for Vessel Generation and Aneurysm Editing
Marten J. Finck, Niklas C. Koser, Sarker M. Mahfuz +7
Intracranial aneurysms (IAs), characterized by unpredictable growth and risk of rupture, are a major cause of stroke and can lead to life-threatening hemorrhages with high mortalit…
ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic Inference
Ali Hojjat, Janek Haberer, Soren Pirk +1
ViTs deliver SOTA performance, yet their fixed computational budget prevents scalable deployment across heterogeneous hardware. Recent Matryoshka-style Transformer architectures mi…
Prompt Pirates Need a Map: Stealing Seeds helps Stealing Prompts
Felix Mächtle, Ashwath Shetty, Jonas Sander +3
Diffusion models have significantly advanced text-to-image generation, enabling the creation of highly realistic images conditioned on textual prompts and seeds. Given the consider…