We address two aspects of computational flash photography, generation of flash illumination from a no flash image and decomposition of a flash photograph to its ambient and flash illumination components. These components allow us to edit the illuminations to make them stronger or weaker. We employ two methods to address our tasks; one using image-to-image translation, as seen on the left, and another using intrinsic components, as seen on the right.
Abstract
The majority of common cameras have an integrated flash that improves lighting in a variety of situations, particularly in low-light environments. Before capturing an image, the photographer must make a decision regarding the usage of flash. However, flash strength cannot be adjusted once it has been utilised in an image. In this work, we target two application scenarios in computational flash photography: decomposition of a flash photograph into its illumination components and generating the flash illumination from a given single no-flash photograph. Two distinct approaches based on image-to-image transfer and intrinsic decomposition with the use of convolutional neural networks are employed to address these tasks. An additional network boosts and upscales the estimated results to generate the final illuminations. Key advantages of our approach include the preparation of a large flash/no-flash dataset and presenting models based on state-of-the-art methods to address subtasks specific to our problem.
Dissertation
 |
Video Presentation
BibTeX
author={Sepideh Sarajian Maralan},
title={Computational Flash Photography},
year={2022},
school={Simon Fraser University},
}
Publications in the context of this thesis
|
CVPR, 2023
Flash is an essential tool as it often serves as the sole controllable light source in everyday photography.
However, the use of flash is a binary decision at the time a photograph is captured with limited control over its characteristics such as strength or color.
In this work, we study the computational control of the flash light in photographs taken with or without flash.
We present a physically motivated intrinsic formulation for flash photograph formation and develop flash decomposition and generation methods for flash and no-flash photographs, respectively.
We demonstrate that our intrinsic formulation outperforms alternatives in the literature and allows us to computationally control flash in in-the-wild images.
@INPROCEEDINGS{Maralan2023Flash,
author={Sepideh Sarajian Maralan and Chris Careaga and Ya\u{g}{\i}z Aksoy}, title={Computational Flash Photography through Intrinsics}, journal={Proc. CVPR}, year={2023}, } |
