I am a fourth year CS Ph.D. student at Princeton University working with Professors Adam Finkelstein and Felix Heide. My research spans graphics, vision, and HCI, with a focus on AI for content creation and computational photography. I am interested in exploring methods that combine mathematical models of both problems in image processing and user experience to tackle new applications.
Previously, I completed my undergraduate studies at Cornell University, majoring in Computer Science and minoring in Psychology. I was fortunate to be advised by Professor Abe Davis and spent two wonderful years with the Cornell Vision & Graphics Group, where I became good friends with the Lab Cat.
Publications
Lucky High Dynamic Range Smartphone Imaging
Baiang Li*, Ruyu Yan*, Ethan Tseng, Zhoutong Zhang, Adam Finkelstein, Jiawen Chen, Felix Heide
SIGGRAPH (ACM TOG), 2026
A lightweight HDR imaging system that performs iterative align-and-merge on handheld exposure-bracketed bursts, reconstructing up to 20 stops of dynamic range through convex combinations of input pixels while avoiding hallucination artifacts.
Chromaticity Gradient Mapping for Interactive Control of Color Contrast in Images and Video
A novel perceptually-motivated interactive tool for using color contrast to enhance details represented in the lightness channel of images and video.
Neural Spline Fields for Burst Image Fusion and Layer Separation
Ilya Chugunov, David Shustin, Ruyu Yan, Chenyang Lei, Felix Heide
CVPR, 2024
project website / paper / code
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.
Ray Conditioning: Trading Photo-realism for Photo-Consistency in Multi-view Image Generation
Eric Ming Chen, Sidhanth Holalkere, Ruyu Yan, Kai Zhang, Abe Davis
ICCV, 2023
project website / paper / code
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.
ReCapture: AR-Guided Time-lapse Photography
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.