Image-to-Image
文章平均质量分 93
Phoenixtree_DongZhao
深度学习 图像处理
展开
-
ColorMamba:面向基于Mamba的高质量NIR到RGB光谱转换
为了探索全局长距离依赖性和局部上下文以实现高效的光谱转换,我们引入了可学习的填充标记来增强图像边界的区分度,并防止序列模型内部潜在的混淆。然而,标准的Mamba模型在处理图像时采用的默认扫描策略会不经意间将空间上接近的像素放置在一维数组中的不同位置,导致所谓的“局部上下文忽视”现象,即相邻像素之间的空间相关性没有得到充分保留。为了弥补这一缺陷,我们在Mamba块之前和之后添加了卷积层。这些卷积层能够提取图像的局部特征,并将这些特征作为Mamba处理的输入和输出的一部分,从而增强了模型对局部上下文的敏感性。原创 2024-08-17 09:53:27 · 1065 阅读 · 0 评论 -
PreciseControl:增强文本到图像的扩散模型与细粒度属性控制
W+W+W+在文本到图像(Text-to-Image, T2I)生成任务中,实现高度的个性化控制是一项极具挑战性的目标。现有的文本到图像扩散模型(T2I diffusion models)尽管已经展示了从文本描述生成高质量图像的能力,但它们在精细控制面部属性方面仍面临限制。特别是,这些方法通常依赖于文本提示进行图像编辑,这种方式的控制能力相对粗糙,难以实现精细化的面部属性调整。与此相对,StyleGAN模型通过学习丰富的面部先验,实现了对面部属性的平滑控制。原创 2024-08-14 15:39:46 · 859 阅读 · 0 评论 -
无监督去雨论文(一):DerainCycleGAN: Rain Attentive CycleGAN for Single ImageDeraining and Rainmaking
本文提出了无监督注意引导下的雨条纹提取器。并构建了接近真实场景的雨图像数据集。原创 2022-06-07 06:09:10 · 2270 阅读 · 1 评论 -
懂点深度学习,就能发 Nature ?找对问题、有科学价值的问题更重要
Solar magnetograms are important for studying solar activity and predicting space weather disturbances1 . Farside magnetograms can be constructed from local helioseismology without any farside data2-4, but their quality is lower than that of typical fr...原创 2021-12-17 14:51:40 · 2258 阅读 · 0 评论 -
ICCV2021 频域图像翻译 Frequency Domain Image Translation: More Photo-realistic, Better Identity-preserving
本文提出了一种新的频域图像翻译(FDIT) 框架,利用频率信息增强图像生成过程(研究方法)。本文的主要想法是将图像分解为低频和高频成分,其中高频特征捕获类似于 identity 的对象结构(核心思想)。本文的训练目标有利于在像素空间和傅里叶频谱空间中保持频率信息(方法优/特点)。原创 2021-11-27 13:23:12 · 3319 阅读 · 7 评论 -
ICLR2021 用可逆生成流解耦全局和局部表示 Decoupling Global and Local Representations via Invertible Generative Flows
Decoupling Global and Local Representations via Invertible Generative Flows[PDF] [GitHub]Figure 1: Examples of the switch operation, which switches the global representations of two images from four datasets: (a) CIFAR-10, (b) ImageNet, (c) LSUN B.原创 2021-10-24 01:02:13 · 1030 阅读 · 0 评论 -
ICCV 2021可逆的跨空间映射实现多样化的图像风格传输:Diverse Image Style Transfer via Invertible Cross-Space Mapping
Diverse Image Style Transfer via Invertible Cross-Space MappingHaibo Chen, Lei Zhao∗ , Huiming Zhang, Zhizhong Wang Zhiwen Zuo, Ailin Li, Wei Xing∗ , Dongming LuCollege of Computer Science and Technology, Zhejiang University[paper]目录Abstract1原创 2021-11-28 15:59:16 · 1504 阅读 · 0 评论 -
可逆网络风格迁移-解决内容泄漏问题 [CVPR 2021] ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows
ArtFlow: Unbiased Image Style Transfer via Reversible Neural FlowsJie An1∗ Siyu Huang2∗ Yibing Song3 Dejing Dou2 Wei Liu4 Jiebo Luo1 1 University of Rochester 2 Baidu Research 3 Tencent AI Lab 4 Tence...原创 2021-10-16 01:42:52 · 3284 阅读 · 2 评论 -
论文阅读 Glow: Generative Flow with Invertible 1×1 Convolutions
Glow: Generative Flow with Invertible 1×1 Convolutions[pdf] [github]目录Glow: Generative Flow with Invertible 1×1 ConvolutionsAbstractIntroductionBackground: Flow-based Generative ModelsProposed Generative Flow1. Actnorm: scale and bias .原创 2021-10-06 09:28:13 · 2434 阅读 · 1 评论 -
内存高效的可逆 GAN 网络:Reversible GANs for Memory-efficient Image-to-Image Translation
Reversible GANs for Memory-efficient Image-to-Image Translation[pdf]目录AbstractIntroductionBackground and Related WorkMethodAbstractThe Pix2pix [17] and CycleGAN [40] losses have vastly improved the qualitative and quantitative visua.原创 2021-10-04 09:14:20 · 1278 阅读 · 0 评论 -
【转】知乎 —— AdaIN 笔记
这个博客写的不要太好,强烈推荐并转载。【https://zhuanlan.zhihu.com/p/158657861】AdaIN 笔记Liewschild计算机视觉练习生,中国科学院大学硕士在读论文Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization的阅读笔记ICCV 2017的一篇论文,有点老,不过是一篇很棒的论文,做了非常多的实验,靠谱、实在,对我的研究也有非常大的帮助。风格迁移主转载 2021-01-31 09:36:44 · 1986 阅读 · 0 评论 -
MyDLNote-High-Resolution: CVPR2020 High-Resolution Daytime Translation 不带域名标签的高分辨率日间图像翻译
High-Resolution Daytime Translation Without Domain Labels[CVPR 2020] [GitHub]Abstract Modeling daytime changes in high resolution photographs, e.g., re-rendering the same scene under different illuminations typical for day, night, or dawn, is a.原创 2021-01-31 07:56:39 · 1001 阅读 · 1 评论 -
MyDLNote-High-Resolution: CooGAN: 协同GAN网络,高分辨率面部属性的高效记忆框架
CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing[ECCV 2020]AbstractIn contrast to great success of memory-consuming face editing methods at a low resolution, to manipulate high-resolution (HR) facial images, i.e.,原创 2021-01-14 01:32:07 · 685 阅读 · 0 评论 -
2020 Domain Adaptation 最新论文:插图速览(二)
Spatial Attention Pyramid Network for Unsupervised Domain Adaptation[paper]CSCL: Critical Semantic-Consistent Learning for Unsupervised Domain Adaptation[paper]Learning to Combine: Knowledge Aggregation for Multi-Source D...原创 2020-11-30 14:54:47 · 2601 阅读 · 0 评论 -
[论文速读] : ICCV 2019 少量学习无监督的图像翻译 Few-Shot Unsupervised Image-to-Image Translation
Few-Shot Unsupervised Image-to-Image Translation[paper] [github]Fig. 1 Training. The training set consists of images of various object classes (source classes). We train a model to translate images between these source object classes. Deployment.原创 2020-11-25 18:57:54 · 818 阅读 · 0 评论