We present TimeNeRF, a generalizable neural rendering approach for rendering novel
views at arbitrary viewpoints and at arbitrary times, even with few input views. For real-world …

The goal of unpaired image-to-image translation is to produce an output image reflecting the
target domain's style while keeping unrelated contents of the input source image …

Much of my work has focused on developing algorithms that extract temporal patterns in
sequences of images from static outdoor cameras. This work began when, as a graduate …