High-Resolution Daytime Translation Without Domain Labels

2020/03/19 by Anokhin, Ivan, Solovev, Pavel, Korzhenkov, Denis +6 · 1 citation
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2003.08791

Abstract

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/.

Cited by

• TimeNeRF: Building Generalizable Neural Radiance Fields across Time from Few-Shot Input Views

Related

• See Clearer at Night: Towards Robust Nighttime Semantic Segmentation through Day-Night Image Conversion
• Multi-Modality Image Super-Resolution using Generative Adversarial Networks
• Night-to-Day Translation via Illumination Degradation Disentanglement
• Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime
• Shadow Transfer: Single Image Relighting For Urban Road Scenes