Time-of-Day Neural Style Transfer for Architectural Photographs
Yingshu Chen, Tuan-Anh Vu, Ka-Chun Shum, Binh-Son Hua, Sai-Kit Yeung

TL;DR
This paper introduces a specialized neural style transfer method for architectural photographs that separately processes foreground and background to preserve geometric features and achieve photorealistic lighting and colors.
Contribution
It proposes a two-branch neural network with segmentation and image translation modules tailored for architectural photography style transfer, addressing composition challenges.
Findings
Produces photorealistic lighting and color on architectural images
Outperforms existing style transfer methods quantitatively and qualitatively
Utilizes a new dataset of outdoor architectural photos with semantic info
Abstract
Architectural photography is a genre of photography that focuses on capturing a building or structure in the foreground with dramatic lighting in the background. Inspired by recent successes in image-to-image translation methods, we aim to perform style transfer for architectural photographs. However, the special composition in architectural photography poses great challenges for style transfer in this type of photographs. Existing neural style transfer methods treat the architectural images as a single entity, which would generate mismatched chrominance and destroy geometric features of the original architecture, yielding unrealistic lighting, wrong color rendition, and visual artifacts such as ghosting, appearance distortion, or color mismatching. In this paper, we specialize a neural style transfer method for architectural photography. Our method addresses the composition of the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Enhancement Techniques · Generative Adversarial Networks and Image Synthesis · Advanced Vision and Imaging
