4 papers
CREST: Curvature-Regulated Event-Centric Sampling for Efficient Long-Video Understanding
Mehrajul Abadin Miraj, Abdul Mohaimen Al Radi, Shariful Islam Rayhan +4
Selecting informative frames from long videos is a combinatorial problem that existing methods address either through efficient heuristics without explicit modeling of query-condit…
From Attention to Frequency: Integration of Vision Transformer and FFT-ReLU for Enhanced Image Deblurring
Syed Mumtahin Mahmud, Mahdi Mohd Hossain Noki, Prothito Shovon Majumder +3
Image deblurring is vital in computer vision, aiming to recover sharp images from blurry ones caused by motion or camera shake. While deep learning approaches such as CNNs and Visi…
SloMoDeblur: A Large-Scale Smartphone Image Deblurring Dataset
Syed Mumtahin Mahmud, Mahdi Mohd Hossain Noki, Prothito Shovon Majumder +4
Motion blur remains one of the most common and visually disruptive degradations in real-world smartphone imaging, yet existing deblurring benchmarks are often limited in scale, res…
Blind Image Deblurring with FFT-ReLU Sparsity Prior
Abdul Mohaimen Al Radi, Prothito Shovon Majumder, Md. Mosaddek Khan
Blind image deblurring is the process of recovering a sharp image from a blurred one without prior knowledge about the blur kernel. It is a small data problem, since the key challe…