4 citations · 10 across the 7 of their papers we have counts for
8 papers
Geometric Inconsistency Localization in Multi-View Image Sets
Xander Staelens, Albéric Loos, Bert Ramlot +3
Novel view synthesis (NVS) models can produce realistic new views of the same scene from different viewpoints. However, these generated views are not always geometrically consisten…
TGIF2: Extended Text-Guided Inpainting Forgery Dataset & Benchmark
Hannes Mareen, Dimitrios Karageorgiou, Paschalis Giakoumoglou +3
Generative AI has made text-guided inpainting a powerful image editing tool, but at the same time a growing challenge for media forensics. Existing benchmarks, including our text-g…
Generative Anchored Fields: Controlled Data Generation via Emergent Velocity Fields and Transport Algebra
Deressa Wodajo Deressa, Hannes Mareen, Peter Lambert +1
We present Generative Anchored Fields (GAF), a generative model that learns independent endpoint predictors, (noise) and (data), from any point on a linear bridge. Unlike e…
TGIF: Text-Guided Inpainting Forgery Dataset
Hannes Mareen, Dimitrios Karageorgiou, Glenn Van Wallendael +2
Digital image manipulation has become increasingly accessible and realistic with the advent of generative AI technologies. Recent developments allow for text-guided inpainting, mak…
Blind Deep-Learning-Based Image Watermarking Robust Against Geometric Transformations
Hannes Mareen, Lucas Antchougov, Glenn Van Wallendael +1
Digital watermarking enables protection against copyright infringement of images. Although existing methods embed watermarks imperceptibly and demonstrate robustness against attack…
GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer
Deressa Wodajo Deressa, Hannes Mareen, Peter Lambert +3
Deepfakes have raised significant concerns due to their potential to spread false information and compromise digital media integrity. Current deepfake detection models often strugg…
Training Data Improvement for Image Forgery Detection using Comprint
Hannes Mareen, Dante Vanden Bussche, Glenn Van Wallendael +2
Manipulated images are a threat to consumers worldwide, when they are used to spread disinformation. Therefore, Comprint enables forgery detection by utilizing JPEG-compression fin…
Comprint: Image Forgery Detection and Localization using Compression Fingerprints
Hannes Mareen, Dante Vanden Bussche, Fabrizio Guillaro +4
Manipulation tools that realistically edit images are widely available, making it easy for anyone to create and spread misinformation. In an attempt to fight fake news, forgery det…