PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-Video

Excerpt

arXiv:2610.01279v1 Announce Type: cross Abstract: Motion blur arises from the temporal integration of a continuous sharp signal over a finite exposure window, yet existing learning-based methods sidestep this physical model and predict only the sharp signal itself: most single-image deblurring methods recover a single frame at the exposure center, while blur-to-video methods predict a fixed set of frames. We introduce PickMoment, a continuous-time reformulation that directly learns the interval-