Abstract: Except for the first frame, a population Monte Carlo image plane (PMC-IP) sampler renders with a start-up kernel function learned from previous results by using motion analysis techniques in the vision community to explore the temporal coherence existing among kernel functions. The predicted kernel function can shift part of the uniformly distributed samples from regions with low visual variance to regions with high visual variance at the start-up iteration and reduce the temporal noise by considering the temporal relation of sample distributions among frames. In the following iterations, the PMC-IP sampler adapts the kernel function to select pixels for refinement according to a perceptually-weighted variance criterion. Our results improve the rendering efficiency by a factor between 2 to 5 over existing techniques in single frame rendering. The rendered animations are perceptually more pleasant.