Gated-gan: Adversarial gated networks for multi-collection style transfer
Style transfer describes the rendering of an image's semantic content as different artistic
styles. Recently, generative adversarial networks (GANs) have emerged as an effective …
styles. Recently, generative adversarial networks (GANs) have emerged as an effective …
Single image super resolution using joint regularization
This letter proposes a reconstruction-based single image super resolution method by using
joint regularization, where a group-residual-based regularization (GRR) and a ridge …
joint regularization, where a group-residual-based regularization (GRR) and a ridge …
Wasserstein loss for image synthesis and restoration
G Tartavel, G Peyré, Y Gousseau - SIAM Journal on Imaging Sciences, 2016 - SIAM
This paper presents a novel variational approach to imposing statistical constraints on the
output of both image generation (typically to perform texture synthesis) and image …
output of both image generation (typically to perform texture synthesis) and image …
Semi-unbalanced regularized optimal transport for image restoration
We consider in this paper the use of a penalty based on the theory of optimal transport (OT)
in order to regularize inverse problems in imaging. The proposed approach is formulated in …
in order to regularize inverse problems in imaging. The proposed approach is formulated in …
[HTML][HTML] Toward universal texture synthesis by combining texton broadcasting with noise injection in StyleGAN-2
We present a universal texture synthesis approach that incorporates a novel multiscale
texton broadcasting module in the StyleGAN-2 framework. The texton broadcasting module …
texton broadcasting module in the StyleGAN-2 framework. The texton broadcasting module …
Structure preserving image denoising based on low-rank reconstruction and gradient histograms
M Zhang, C Desrosiers - Computer Vision and Image Understanding, 2018 - Elsevier
One of the main challenges of denoising approaches is preserving images details, like
textures and edges, while suppressing noise. The preservation of such details is essential to …
textures and edges, while suppressing noise. The preservation of such details is essential to …
Semi-unbalanced optimal transport for image restoration and synthesis
In this paper, we build on optimal transport (OT) theory to present a novel asymmetrically
unbalanced variant, the semi-unbalanced optimal transport (SUOT), specifically designed …
unbalanced variant, the semi-unbalanced optimal transport (SUOT), specifically designed …
RWRM: Residual Wasserstein regularization model for image restoration
R He, X Feng, X Zhu, H Huang… - Inverse Problems and …, 2020 - aimsciences.org
Existing image restoration methods mostly make full use of various image prior information.
However, they rarely exploit the potential of residual histograms, especially their role as …
However, they rarely exploit the potential of residual histograms, especially their role as …
3-D Material Style Transfer for Reconstructing Unknown Appearance in Complex Natural Materials
S Ranjan, C Toler-Franklin - arXiv preprint arXiv:2112.15589, 2021 - arxiv.org
We propose a 3-D material style transfer framework for reconstructing invisible (or faded)
appearance properties in complex natural materials. Our algorithm addresses the technical …
appearance properties in complex natural materials. Our algorithm addresses the technical …
Super-resolution of multiscale 3D images from materials science
DPL Nguyen - 2023 - theses.hal.science
Recent developments in imaging techniques and computational analysis deeply modify the
way materials sciences. The materials image has moved from microscale resolution to true …
way materials sciences. The materials image has moved from microscale resolution to true …