Gan inversion: A survey
GAN inversion aims to invert a given image back into the latent space of a pretrained GAN
model so that the image can be faithfully reconstructed from the inverted code by the …
model so that the image can be faithfully reconstructed from the inverted code by the …
Learning to relight portrait images via a virtual light stage and synthetic-to-real adaptation
Given a portrait image of a person and an environment map of the target lighting, portrait
relighting aims to re-illuminate the person in the image as if the person appeared in an …
relighting aims to re-illuminate the person in the image as if the person appeared in an …
Face relighting with geometrically consistent shadows
Most face relighting methods are able to handle diffuse shadows, but struggle to handle
hard shadows, such as those cast by the nose. Methods that propose techniques for …
hard shadows, such as those cast by the nose. Methods that propose techniques for …
Geometry-aware single-image full-body human relighting
Single-image human relighting aims to relight a target human under new lighting conditions
by decomposing the input image into albedo, shape and lighting. Although plausible …
by decomposing the input image into albedo, shape and lighting. Although plausible …
Instance shadow detection with a single-stage detector
This article formulates a new problem, instance shadow detection, which aims to detect
shadow instance and the associated object instance that cast each shadow in the input …
shadow instance and the associated object instance that cast each shadow in the input …
Designing an illumination-aware network for deep image relighting
Lighting is a determining factor in photography that affects the style, expression of emotion,
and even quality of images. Creating or finding satisfying lighting conditions, in reality, is …
and even quality of images. Creating or finding satisfying lighting conditions, in reality, is …
BareSkinNet: De‐makeup and De‐lighting via 3D Face Reconstruction
X Yang, T Taketomi - Computer Graphics Forum, 2022 - Wiley Online Library
We propose BareSkinNet, a novel method that simultaneously removes makeup and lighting
influences from the face image. Our method leverages a 3D morphable model and does not …
influences from the face image. Our method leverages a 3D morphable model and does not …
Real-time shadow-aware portrait relighting in virtual backgrounds for realistic telepresence
While using virtual backgrounds has recently become a very popular feature in
videoconferencing, there often exists a jarring mismatch between the lighting of the user and …
videoconferencing, there often exists a jarring mismatch between the lighting of the user and …
[HTML][HTML] Swipes and saves: A taxonomy of factors influencing aesthetic assessments and perceived beauty of mobile phone photographs
Digital images taken by mobile phones are the most frequent class of images created today.
Due to their omnipresence and the many ways they are encountered, they require a specific …
Due to their omnipresence and the many ways they are encountered, they require a specific …
Deep portrait delighting
We present a deep neural network for removing undesirable shading features from an
unconstrained portrait image, recovering the underlying texture. Our training scheme …
unconstrained portrait image, recovering the underlying texture. Our training scheme …