6 papers
UnSCAR: Universal, Scalable, Controllable, and Adaptable Image Restoration
Debabrata Mandal, Soumitri Chattopadhyay, Yujie Wang +2
Universal image restoration aims to recover clean images from arbitrary real-world degradations using a single inference model. Despite significant progress, existing all-in-one re…
On The Robustness of Foundational 3D Medical Image Segmentation Models Against Imprecise Visual Prompts
Soumitri Chattopadhyay, Basar Demir, Marc Niethammer
While 3D foundational models have shown promise for promptable segmentation of medical volumes, their robustness to imprecise prompts remains under-explored. In this work, we aim t…
NoTeS-Bank: Benchmarking Neural Transcription and Search for Scientific Notes Understanding
Aniket Pal, Sanket Biswas, Alloy Das +6
Understanding and reasoning over academic handwritten notes remains a challenge in document AI, particularly for mathematical equations, diagrams, and scientific notations. Existin…
Zero-shot Domain Generalization of Foundational Models for 3D Medical Image Segmentation: An Experimental Study
Soumitri Chattopadhyay, Basar Demir, Marc Niethammer
Domain shift, caused by variations in imaging modalities and acquisition protocols, limits model generalization in medical image segmentation. While foundation models (FMs) trained…
Downstream Analysis of Foundational Medical Vision Models for Disease Progression
Basar Demir, Soumitri Chattopadhyay, Thomas Hastings Greer +2
Medical vision foundational models are used for a wide variety of tasks, including medical image segmentation and registration. This work evaluates the ability of these models to p…
UniCoRN: Latent Diffusion-based Unified Controllable Image Restoration Network across Multiple Degradations
Debabrata Mandal, Soumitri Chattopadhyay, Guansen Tong +1
Image restoration is essential for enhancing degraded images across computer vision tasks. However, most existing methods address only a single type of degradation (e.g., blur, noi…