RADAR produces anomaly maps directly from attention-based diffusion models in a single forward pass, achieving higher F1 scores than reconstruction-based diffusion and statistical baselines on MVTec-AD and 3D-printed material data.
Diffusion models beat gans on image synthesis,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2025 3representative citing papers
A novel tri-plane equivariant volumetric grasp model adapts GIGA and IGD planners with flow matching and deformable attention to achieve higher real-time performance than non-equivariant baselines.
Synthetic data augmentation improves instance segmentation performance for chicken carcasses when real annotated data is limited.
citing papers explorer
-
Single-Step Reconstruction-Free Anomaly Detection and Segmentation via Diffusion Models
RADAR produces anomaly maps directly from attention-based diffusion models in a single forward pass, achieving higher F1 scores than reconstruction-based diffusion and statistical baselines on MVTec-AD and 3D-printed material data.
-
Equivariant Volumetric Grasping
A novel tri-plane equivariant volumetric grasp model adapts GIGA and IGD planners with flow matching and deformable attention to achieve higher real-time performance than non-equivariant baselines.
-
Synthetic Data Augmentation for Enhanced Chicken Carcass Instance Segmentation
Synthetic data augmentation improves instance segmentation performance for chicken carcasses when real annotated data is limited.