5 papers
BenthicFlow: Generating Extensible Underwater Environments via Flow Matching
Joaquín Figueira, Camile Lendering, Manfred Gonzalez-Hernandez +3
Computer vision applications for 3D scene understanding in underwater environments remain challenging due to the lack of high-quality 3D data and the inability of surface-trained m…
ReFP-AD: Rectified Flow Preconditioning for Energy-Based Anomaly Detection
Camile Lendering, Erkut Akdag, Joaquín Figueira +1
Unified anomaly detection requires modeling highly heterogeneous normal data without access to anomalous samples. While foundation models like DINOv2 provide rich token representat…
Boxes2Pixels: Learning Defect Segmentation from Noisy SAM Masks
Camile Lendering, Erkut Akdag, Egor Bondarev
Accurate defect segmentation is critical for industrial inspection, yet dense pixel-level annotations are rarely available. A common workaround is to convert inexpensive bounding b…
SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modeling
Camile Lendering, Erkut Akdag, Egor Bondarev
Detecting visual anomalies in industrial inspection often requires training with only a few normal images per category. Recent few-shot methods achieve strong results employing fou…
EdgeEar: Efficient and Accurate Ear Recognition for Edge Devices
Camile Lendering, Bernardo Perrone Ribeiro, Žiga Emeršič +1
Ear recognition is a contactless and unobtrusive biometric technique with applications across various domains. However, deploying high-performing ear recognition models on resource…