Showing 2026Show all
2 papers · 1 filter
cs.CV2026
VoxCor: Training-Free Volumetric Features for Multimodal Voxel Correspondence
Guney Tombak, Ertunc Erdil, Ender Konukoglu
Cross-modal 3D medical image analysis requires voxelwise representations that remain anatomically consistent across imaging contrasts, scanners, and acquisition protocols. Recent w…
cs.CV2026
Spatial Autoregressive Modeling of DINOv3 Embeddings for Unsupervised Anomaly Detection
Ertunc Erdil, Nico Schulthess, Guney Tombak +1
DINO models provide rich patch-level representations that have recently enabled strong performance in unsupervised anomaly detection (UAD). Most existing methods extract patch embe…