5 papers
PCM-NeRF: Probabilistic Camera Modeling for Neural Radiance Fields under Pose Uncertainty
Shravan Venkatraman, Rakesh Raj Madavan, Pavan Kumar Sathya Venkatesh
Neural surface reconstruction methods typically treat camera poses as fixed values, assuming perfect accuracy from Structure-from-Motion (SfM) systems. This assumption breaks down…
TIDE: Two-Stage Inverse Degradation Estimation with Guided Prior Disentanglement for Underwater Image Restoration
Shravan Venkatraman, Rakesh Raj Madavan, Pavan Kumar S +1
Underwater image restoration is essential for marine applications ranging from ecological monitoring to archaeological surveys, but effectively addressing the complex and spatially…
Med-GRIM: Enhanced Zero-Shot Medical VQA using prompt-embedded Multimodal Graph RAG
Rakesh Raj Madavan, Akshat Kaimal, Hashim Faisal +1
An ensemble of trained multimodal encoders and vision-language models (VLMs) has become a standard approach for visual question answering (VQA) tasks. However, such models often fa…
UGPL: Uncertainty-Guided Progressive Learning for Evidence-Based Classification in Computed Tomography
Shravan Venkatraman, Pavan Kumar S, Rakesh Raj Madavan +1
Accurate classification of computed tomography (CT) images is essential for diagnosis and treatment planning, but existing methods often struggle with the subtle and spatially dive…
GANESH: Generalizable NeRF for Lensless Imaging
Rakesh Raj Madavan, Akshat Kaimal, Badhrinarayanan K +4
Lensless imaging offers a significant opportunity to develop ultra-compact cameras by removing the conventional bulky lens system. However, without a focusing element, the sensor's…