DeepFlash: Turning a Flash Selfie into a Studio Portrait

@article{Capece2019DeepFlashTA,
  title={DeepFlash: Turning a Flash Selfie into a Studio Portrait},
  author={Nicola Felice Capece and Francesco Banterle and Paolo Cignoni and Fabio Ganovelli and Roberto Scopigno and Ugo Erra},
  journal={Signal Process. Image Commun.},
  year={2019},
  volume={77},
  pages={28-39}
}
Abstract We present a method for turning a flash selfie taken with a smartphone into a photograph as if it was taken in a studio setting with uniform lighting. Our method uses a convolutional neural network trained on a set of pairs of photographs acquired in an ad-hoc acquisition campaign. Each pair consists of one photograph of a subject’s face taken with the camera flash enabled and another one of the same subject in the same pose illuminated using a photographic studio-lighting setup. We… 
Turning a Smartphone Selfie Into a Studio Portrait
TLDR
A novel algorithm that turns a flash selfie taken with a smartphone into a studio-like photograph with uniform lighting is introduced, which can amend lighting artifacts introduced by a close-up camera flash, such as specular highlights, shadows, and skin shine.
Ambient Lighting Generation for Flash Images with Guided Conditional Adversarial Networks
TLDR
This work proposes a generative adversarial network in a guided conditional mode that not only generates natural illumination but also attenuates harsh shadows, simultaneously generating synthetic ambient shadows.
Realistic Transfer of Lighting to an Indoor Scene
The quality and appearance of an image is largely dependent on lighting. The complex interplay of objects and light (type of light, directions, etc) is central to the appearance of objects, thereby
A Deep Learning approach for the Motion Picture Content Rating
TLDR
This work provides a motion picture content rating model to automatically classify and censor violent scenes using a Deep Learning (DL) approach and demonstrates the effectiveness of the automatic classifier for supporting content providers to assign the rating.
A Preliminary Investigation into a Deep Learning Implementation for Hand Tracking on Mobile Devices
TLDR
This work presents a mobile application for 2D hand tracking from RGB images captured by the smartphone camera, modified specifically to tackle this task and run on mobile devices, looking for a compromise between performance and computational time.
FRGAN: A Blind Face Restoration with Generative Adversarial Networks
Recent works based on deep learning and facial priors have performed well in superresolving severely degraded facial images. However, due to the limitation of illumination, pixels of the monitoring
Human segmentation in surveillance video with deep learning
TLDR
The results show that the main benefit of the proposed method is the possibility to automatically recognize and segment people in videos without constraints on camera and people movements in the scene.
Exploring Upper Limb Segmentation with Deep Learning for Augmented Virtuality
TLDR
An augmented virtuality (AV) pipeline allows users to visualize their limbs in VE to overcome this limit and highlight the effectiveness of the proposed CNN achieving remarkable results in several real-life unconstrained scenarios.
Solid and Effective Upper Limb Segmentation in Egocentric Vision
TLDR
This work trained several segmentation networks based on the state-of-the-art DeepLabv3+ model, collecting a large-scale comprehensive dataset that consists of 46 thousand real-life and well-labeled RGB images with a great variety of skin colors, clothes, occlusions, and lighting conditions.
A Validation Approach for Deep Reinforcement Learning of a Robotic Arm in a 3D Simulated Environment
In recent years, deep reinforcement learning has increasingly contributed to the development of robotic applications and boosted research in robotics. Deep learning and model-free, off-policy,
...
1
2
...

References

SHOWING 1-10 OF 81 REFERENCES
Style transfer for headshot portraits
TLDR
A technique to transfer the style of an example headshot photo onto a new one, which can allow one to easily reproduce the look of renowned artists, and can successfully handle styles by a variety of different artists.
Exposure
Retouching can significantly elevate the visual appeal of photos, but many casual photographers lack the expertise to do this well. To address this problem, previous works have proposed automatic
Flash photography enhancement via intrinsic relighting
TLDR
This work uses the bilateral filter to decompose the images into detail and large scale and reconstruct the image using the large scale of the available lighting and the detail of the flash to enhance photographs shot in dark environments.
Exposure: A White-Box Photo Post-Processing Framework
TLDR
This paper presents a deep learning approach that is instead trained on unpaired data, namely a set of photographs that exhibits a retouching style the user likes, which is much easier to collect.
Digital photography with flash and no-flash image pairs
TLDR
A variety of applications that analyze and combine the strengths of flash/no-flash image pairs can synthesize new images that are of higher quality than either of the originals.
A Dataset of Flash and Ambient Illumination Pairs from the Crowd
TLDR
A dataset of thousands of ambient and flash illumination pairs is presented to enable studying flash photography and other applications that can benefit from having separate illuminations.
DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks
TLDR
An end-to-end deep learning approach that bridges the gap by translating ordinary photos into DSLR-quality images by learning the translation function using a residual convolutional neural network that improves both color rendition and image sharpness.
Portrait Lighting Transfer Using a Mass Transport Approach
TLDR
This work simplifies this task using a relighting technique that transfers the desired illumination of one portrait onto another using a 3D morphable face model and solves a mass-transport problem in this augmented space to generate a color remapping that achieves localized, geometry-aware relighting.
Neural Face Editing with Intrinsic Image Disentangling
TLDR
An end-to-end generative adversarial network is proposed that infers a face-specific disentangled representation of intrinsic face properties, including shape, albedo, and lighting, and an alpha matte, and it is shown that this network can be trained on in thewild images by incorporating an in-network physically-based image formation module and appropriate loss functions.
Automatic Portrait Segmentation for Image Stylization
TLDR
This paper introduces a new automatic segmentation algorithm dedicated to portraits and describes several portrait filters that exploit the results of this algorithm to generate high‐quality portraits.
...
1
2
3
4
5
...