3 papers
eess.IV2026
Severity-Channel Conditioning: An Injection-Level Study for Consumer-Device Deblurring
Abdullah Al Shafi, Kazi Saeed Alam, Sumaiya Rahim Suma +1
Motion-deblurring models lose substantial accuracy when transferred from professional cameras to smartphone-derived imagery. This paper studies whether a severity descriptor, partl…
cs.CV2026
Revisiting Ground-Truth Synthesis from High-Speed Video: Exact Validity Conditions and an Audited Consumer Capture Corpus
Abdullah Al Shafi, Sumaiya Rahim Suma
Motion-deblurring datasets are commonly synthesised by averaging consecutive high-frame-rate frames and labelling the result with the central frame. We show that this label is…
cs.CV2026
Closing the Null Space: Guidance-Aware Quantization for Classifier-Free Diffusion
Abdullah Al Shafi, Sumaiya Rahim Suma
Deploying classifier-free guidance (CFG) diffusion models under real-world compute budgets requires quantization, yet existing post-training quantization (PTQ) methods treat CFG mo…