5 papers
Do Vision Models Learn Physical Constraints or Rendering Shortcuts? A Counterfactual Benchmark for Grounded Physical Consistency
M. Moein Esfahani, Sepehr Salem, Mohammed Alser +1
Modern image editing models can satisfy a text instruction while breaking the physics of the edited scene. A new object may cast no shadow, a mirror may fail to reflect visible geo…
NeuroGAN-3D: Enhancing Intrinsic Functional Brain Networks via High-Fidelity 3D Generative Super-Resolution
M. Moein Esfahani, Sepehr Salem Ghahfarokhi, Mohammed Alser +2
Recent advances in neuroimaging have deepened our understanding of the brain's complex functional and structural organization. Among these, functional Magnetic Resonance Imaging (f…
XMorph: Explainable Brain Tumor Analysis Via LLM-Assisted Hybrid Deep Intelligence
Sepehr Salem Ghahfarokhi, M. Moein Esfahani, Raj Sunderraman +2
Deep learning has significantly advanced automated brain tumor diagnosis, yet clinical adoption remains limited by interpretability and computational constraints. Conventional mode…
Breast Cancer Detection in Thermographic Images via Diffusion-Based Augmentation and Nonlinear Feature Fusion
Sepehr Salem, M. Moein Esfahani, Jingyu Liu +1
Data scarcity hinders deep learning for medical imaging. We propose a framework for breast cancer classification in thermograms that addresses this using a Diffusion Probabilistic…
A Comparative Study of NAFNet Baselines for Image Restoration
Vladislav Esaulov, M. Moein Esfahani
We study NAFNet (Nonlinear Activation Free Network), a simple and efficient deep learning baseline for image restoration. By using CIFAR10 images corrupted with noise and blur, we…