Ruyu Yan

We present a novel perceptually-motivated interactive tool for using color contrast to enhance details represented in the lightness channel of images and video.

We propose neural spline fields (NSFs) as a compact flow model, which maps input coordinates to spline control points for producing temporally consistent flow estimates that align with conventional optical flow references.

We propose ray conditioning, a lightweight and geometry-free technique for multi-view image generation. It enables enables photo-realistic multi-view image editing on natural photos via GAN inversion.

We present ReCapture, a system that leverages AR-based guidance to help users capture time-lapse data with hand-held mobile devices. ReCapture works by repeatedly guiding users back to the precise location of previously captured images so they can record time-lapse videos one frame at a time without leaving their camera in the scene.