CVLGIVMar 19, 2020

High-Resolution Daytime Translation Without Domain Labels

arXiv:2003.08791v275 citations
AI Analysis

This work addresses a challenging image manipulation task for computer vision applications, but it is incremental as it builds on existing generative models with a new upsampling scheme.

The paper tackles the problem of modeling daytime changes in high-resolution photographs without requiring domain labels, achieving competitive results in GAN metrics and human evaluation.

Modeling daytime changes in high resolution photographs, e.g., re-rendering the same scene under different illuminations typical for day, night, or dawn, is a challenging image manipulation task. We present the high-resolution daytime translation (HiDT) model for this task. HiDT combines a generative image-to-image model and a new upsampling scheme that allows to apply image translation at high resolution. The model demonstrates competitive results in terms of both commonly used GAN metrics and human evaluation. Importantly, this good performance comes as a result of training on a dataset of still landscape images with no daytime labels available. Our results are available at https://saic-mdal.github.io/HiDT/.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes