De-lighting human images using region-specific data augmentation
J Weir, J Zhao, A Chalmers… - 2023 38th International …, 2023 - ieeexplore.ieee.org
This study aims to use deep learning to recover the diffuse albedo of human images
captured under a wide range of real-world lighting conditions. A key challenge here is the …
captured under a wide range of real-world lighting conditions. A key challenge here is the …
Single-image shadow removal using detail extraction and illumination estimation
W Wu, X Wu, Y Wan - The Visual Computer, 2022 - Springer
Deep learning-based shadow removal methods are frequently hard to obtain a detail-rich
and boundary-smoothing shadow removal result. In this work, we propose an illumination …
and boundary-smoothing shadow removal result. In this work, we propose an illumination …
A Deeper Analysis of Volumetric Relightable Faces
Portrait viewpoint and illumination editing is an important problem with several applications
in VR/AR, movies, and photography. Comprehensive knowledge of geometry and …
in VR/AR, movies, and photography. Comprehensive knowledge of geometry and …
AdvShadow: Evading DeepFake Detection via Adversarial Shadow Attack
With the emergence of techniques called DeepFakes, there has been a notable proliferation
of DeepFake detectors rooted in deep learning. These detectors aim to expose subtle …
of DeepFake detectors rooted in deep learning. These detectors aim to expose subtle …
Benchmarking shadow removal for facial landmark detection and beyond
Facial landmark detection is a very fundamental and significant vision task with many
important applications. In practice, facial landmark detection can be affected by a lot of …
important applications. In practice, facial landmark detection can be affected by a lot of …
Non-Uniform Low-Light Face Image Enhancement Based on Dark Channel Prior and Image Uniform Posterior
BY Zhang, QC Zhang, WY Zhang - IEEE Access, 2024 - ieeexplore.ieee.org
Non-uniform low-light images, characterized by complex lighting conditions, pose a
significant challenge in image restoration and enhancement, particularly under backlit …
significant challenge in image restoration and enhancement, particularly under backlit …
Coarse-to-fine: facial structure editing of portrait images via latent space classifications
Facial structure editing of portrait images is challenging given the facial variety, the lack of
ground-truth, the necessity of jointly adjusting color and shape, and the requirement of no …
ground-truth, the necessity of jointly adjusting color and shape, and the requirement of no …
Shadow Harmonization for Realistic Compositing
Compositing virtual objects into real background images requires one to carefully match the
scene's camera parameters, surface geometry, textures, and lighting to obtain plausible …
scene's camera parameters, surface geometry, textures, and lighting to obtain plausible …
Autoencoder and partially impossible reconstruction losses
The generally unsupervised nature of autoencoder models implies that the main training
metric is formulated as the error between input images and their corresponding …
metric is formulated as the error between input images and their corresponding …
Temporally consistent relighting for portrait videos
S Chandran, Y Hold-Geoffroy… - Proceedings of the …, 2022 - openaccess.thecvf.com
Ensuring ideal lighting when recording videos of people can be a daunting task requiring a
controlled environment and expensive equipment. Methods were recently proposed to …
controlled environment and expensive equipment. Methods were recently proposed to …