about
Time-Travel Rephotography (arxiv.org)
3 points by nnx on Dec 15, 2021 | hide | past | pdf | discuss on HN

In plain words: Instead of cleaning old photos step by step—denoising, colorizing, then sharpening—it maps each faded portrait into a space of modern high-resolution faces, doing all three at once while keeping the person's look and pose. On famous historical portraits it beat today's best restoration filters.

Abstract

Many historical people were only ever captured by old, faded, black and white photos, that are distorted due to the limitations of early cameras and the passage of time. This paper simulates traveling back in time with a modern camera to rephotograph famous subjects. Unlike conventional image restoration filters which apply independent operations like denoising, colorization, and superresolution, we leverage the StyleGAN2 framework to project old photos into the space of modern high-resolution photos, achieving all of these effects in a unified framework. A unique challenge with this approach is retaining the identity and pose of the subject in the original photo, while discarding the many artifacts frequently seen in low-quality antique photos. Our comparisons to current state-of-the-art restoration filters show significant improvements and compelling results for a variety of important historical people.

Xuan Luo, Xuaner Zhang, Paul Yoo, Ricardo Martin-Brualla, Jason Lawrence, Steven M. Seitz
arXiv:2012.12261 · cs.CV · submitted Dec 22, 2020 · updated Dec 13, 2021
abstract · pdf · html · SIGGRAPH Asia 2021. Project Page: https://time-travel-rephotography.github.io Video: https://youtu.be/ceIopN2UZ_s

add comment on HN