检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

187 篇 会议

馆藏范围

187 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

187 篇 工学
- 187 篇 计算机科学与技术...
- 61 篇 软件工程
1 篇 医学
- 1 篇 临床医学

主题

187 篇 image and video ...
1 篇 computational ph...
1 篇 stable diffusion
1 篇 vision applicati...
1 篇 low-level vision
1 篇 vision + graphic...

机构

7 篇 tencent ai lab p...
7 篇 carnegie mellon ...
7 篇 ant grp peoples ...
7 篇 peng cheng lab p...
6 篇 univ sci & techn...
5 篇 shanghai ai lab ...
5 篇 alibaba grp peop...
5 篇 tsinghua univ pe...
5 篇 nanyang technol ...
4 篇 swiss fed inst t...
4 篇 adobe res ca usa
4 篇 natl univ singap...
3 篇 hkust peoples r ...
3 篇 google res mount...
3 篇 hong kong polyte...
3 篇 univ wisconsin m...
3 篇 ucl england
3 篇 bytedance people...
3 篇 univ trento tren...
3 篇 max planck inst ...

作者

5 篇 shan ying
5 篇 tulyakov sergey
5 篇 zhang yong
4 篇 lee hsin-ying
4 篇 wang xuan
4 篇 ren jian
4 篇 sohn kihyuk
3 篇 tang hao
3 篇 rombach robin
3 篇 shi humphrey
3 篇 zhan fangneng
3 篇 zhu jun-yan
3 篇 feng jiashi
3 篇 chang huiwen
3 篇 zhang bo
3 篇 lu shijian
3 篇 fan yanbo
3 篇 wu si
3 篇 wong hau san
3 篇 li xiaoyu

语言

187 篇 英文

检索条件"主题词=Image and video synthesis and generation"

共 187 条记录，以下是1-10 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

TextCraftor: Your Text Encoder Can be image Quality Controller

TextCraftor: Your Text Encoder Can be Image Quality Controll...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Li, Yanyu Liu, Xian Kag, Anil Hu, Ju Idelbayev, Yerlan Sagar, Dhritiman Wang, Yanzhi Tulyakov, Sergey Ren, Jian Snap Inc Santa Monica CA 90405 USA Northeastern Univ Boston MA 02115 USA

ISBN: (纸本)9798350353013;9798350353006

Diffusion-based text-to-image generative models, e.g., Stable Diffusion, have revolutionized the field of content generation, enabling significant advancements in areas like image editing and video synthesis. Despite their formidable capabilities, these models are not without their limitations. It is still challenging to synthesize an image that aligns well with the input text, and multiple runs with carefully crafted prompts are required to achieve satisfactory results. To mitigate these limitations, numerous studies have endeavored to fine-tune the pre-trained diffusion models, i.e., UNet, utilizing various technologies. Yet, amidst these efforts, a pivotal question of text-to-image diffusion model training has remained largely unexplored: Is it possible and feasible to fine-tune the text encoder to improve the performance of text-to-image diffusion models? Our findings reveal that, instead of replacing the CLIP text encoder used in Stable Diffusion with other large language models, we can enhance it through our proposed fine-tuning approach, TextCraftor, leading to substantial improvements in quantitative benchmarks and human assessments. Interestingly, our technique also empowers controllable image generation through the interpolation of different text encoders fine-tuned with various rewards. We also demonstrate that TextCraftor is orthogonal to UNet finetuning, and can be combined to further improve generative quality.

关键词： image and video synthesis and generation Stable Diffusion

来源：评论

学校读者我要写书评

暂无评论

Readout Guidance: Learning Control from Diffusion Features

Readout Guidance: Learning Control from Diffusion Features

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Luo, Grace Darrell, Trevor Wang, Oliver Goldman, Dan B. Holynski, Aleksander Google Res Mountain View CA 94043 USA Univ Calif Berkeley Berkeley CA 94720 USA

ISBN: (纸本)9798350353013;9798350353006

We present Readout Guidance, a method for controlling text-to-image diffusion models with learned signals. Readout Guidance uses readout heads, lightweight networks trained to extract signals from the features of a pre-trained, frozen diffusion model at every timestep. These readouts can encode single-image properties, such as pose, depth, and edges;or higher-order properties that relate multiple images, such as correspondence and appearance similarity. Furthermore, by comparing the readout estimates to a user-defined target, and back-propagating the gradient through the readout head, these estimates can be used to guide the sampling process. Compared to prior methods for conditional generation, Readout Guidance requires significantly fewer added parameters and training samples, and offers a convenient and simple recipe for reproducing different forms of conditional control under a single framework, with a single architecture and sampling procedure. We showcase these benefits in the applications of drag-based manipulation, identity-consistent generation, and spatially aligned control. Project page: https://***.

关键词： image and video synthesis and generation

来源：评论

学校读者我要写书评

暂无评论

Rethinking the Objectives of Vector-Quantized Tokenizers for image synthesis

Rethinking the Objectives of Vector-Quantized Tokenizers for...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Gu, Yuchao Wang, Xintao Ge, Yixiao Shan, Ying Shou, Mike Zheng Natl Univ Singapore Show Lab Singapore Singapore Tencent PCG ARC Lab Shenzhen Peoples R China

ISBN: (纸本)9798350353013;9798350353006

Vector-Quantized (VQ-based) generative models usually consist of two basic components, i.e., VQ tokenizers and generative transformers. Prior research focuses on improving the reconstruction fidelity of VQ tokenizers but rarely examines how the improvement in reconstruction affects the generation ability of generative transformers. In this paper, we surprisingly find that improving the reconstruction fidelity of VQ tokenizers does not necessarily improve the generation. Instead, learning to compress semantic features within VQ tokenizers significantly improves generative transformers' ability to capture textures and structures. We thus highlight two competing objectives of VQ tokenizers for image synthesis: semantic compression and details preservation. Different from previous work that prioritizes better details preservation, we propose Semantic-Quantized GAN (SeQ-GAN) with two learning phases to balance the two objectives. In the first phase, we propose a semantic-enhanced perceptual loss for better semantic compression. In the second phase, we fix the encoder and codebook, but enhance and finetune the decoder to achieve better details preservation. Our proposed SeQ-GAN significantly improves VQ-based generative models for both unconditional and conditional image generation. Specifically, SeQ-GAN achieves a Frechet Inception Distance (FID) of 6.25 and Inception Score (IS) of 140.9 on 256x256 imageNet generation, which is a remarkable improvement over VIT-VQGAN (714M), which obtains 11.2 FID and 97.2 IS.

关键词： image and video synthesis and generation

来源：评论

学校读者我要写书评

暂无评论

Your Student is Better Than Expected: Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models

Your Student is Better Than Expected: Adaptive Teacher-Stude...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Starodubcev, Nikita Baranchuk, Dmitry Fedorov, Artem Babenko, Artem Yandex Res Moscow Russia

ISBN: (纸本)9798350353006

Knowledge distillation methods have recently shown to be a promising direction to speedup the synthesis of large-scale diffusion models by requiring only a few inference steps. While several powerful distillation methods were recently proposed, the overall quality of student samples is typically lower compared to the teacher ones, which hinders their practical usage. In this work, we investigate the relative quality of samples produced by the teacher text-to-image diffusion model and its distilled student version. As our main empirical finding, we discover that a noticeable portion of student samples exhibit superior fidelity compared to the teacher ones, despite the "approximate" nature of the student. Based on this finding, we propose an adaptive collaboration between student and teacher diffusion models for effective text-to-image synthesis. Specifically, the distilled model produces an initial image sample, and then an oracle decides whether it needs further improvements with the teacher model. Extensive experiments demonstrate that the designed pipeline surpasses state-of-the-art text-to-image alternatives for various inference budgets in terms of human preference. Furthermore, the proposed approach can be naturally used in popular applications such as text-guided image editing and controllable generation.

关键词： image and video synthesis and generation

来源：评论

学校读者我要写书评

暂无评论

StyleCineGAN: Landscape Cinemagraph generation using a Pre-trained StyleGAN

StyleCineGAN: Landscape Cinemagraph Generation using a Pre-t...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Choi, Jongwoo Seo, Kwanggyoon Ashtari, Amirsaman Noh, Junyong Korea Adv Inst Sci & Technol Visual Media Lab Daejeon South Korea

ISBN: (纸本)9798350353013;9798350353006

We propose a method that can generate cinemagraphs automatically from a still landscape image using a pre-trained StyleGAN. Inspired by the success of recent unconditional video generation, we leverage a powerful pre-trained image generator to synthesize high-quality cinemagraphs. Unlike previous approaches that mainly utilize the latent space of a pre-trained StyleGAN, our approach utilizes its deep feature space for both GAN inversion and cinemagraph generation. Specifically, we propose multi-scale deep feature warping (MSDFW), which warps the intermediate features of a pre-trained StyleGAN at different resolutions. By using MSDFW, the generated cinemagraphs are of high resolution and exhibit plausible looping animation. We demonstrate the superiority of our method through user studies and quantitative comparisons with state-of-the-art cinemagraph generation methods and a video generation method that uses a pre-trained StyleGAN.

关键词： image and video synthesis and generation Vision + graphics Vision applications and systems

来源：评论

学校读者我要写书评

暂无评论

videoSwap: Customized video Subject Swapping with Interactive Semantic Point Correspondence

VideoSwap: Customized Video Subject Swapping with Interactiv...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Gu, Yuchao Zhou, Yipin Wu, Bichen Yu, Licheng Liu, Jia-Wei Zhao, Rui Wu, Jay Zhangjie Zhang, David Junhao Shou, Mike Zheng Tang, Kevin Natl Univ Singapore Show Lab Singapore Singapore Meta GenAI Menlo Pk CA USA

ISBN: (纸本)9798350353013;9798350353006

Current diffusion-based video editing primarily focuses on structure-preserved editing by utilizing various dense correspondences to ensure temporal consistency and motion alignment. However, these approaches are often ineffective when the target edit involves a shape change. To embark on video editing with shape change, we explore customized video subject swapping in this work, where we aim to replace the main subject in a source video with a target subject having a distinct identity and potentially different shape. In contrast to previous methods that rely on dense correspondences, we introduce the videoSwap framework that exploits semantic point correspondences, inspired by our observation that only a small number of semantic points are necessary to align the subject's motion trajectory and modify its shape. We also introduce various user-point interactions (e.g., removing points and dragging points) to address various semantic point correspondence. Extensive experiments demonstrate state-of-the-art video subject swapping results across a variety of real-world videos.

关键词： image and video synthesis and generation

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity Guided image synthesis with Latent Diffusion Models

High-Fidelity Guided Image Synthesis with Latent Diffusion M...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Singh, Jaskirat Gould, Stephen Zheng, Liang Australian Natl Univ Canberra ACT Australia Australian Ctr Robot Vis Brisbane Qld Australia

ISBN: (纸本)9798350301298

Controllable image synthesis with user scribbles has gained huge public interest with the recent advent of text-conditioned latent diffusion models. The user scribbles control the color composition while the text prompt provides control over the overall image semantics. However, we note that prior works in this direction suffer from an intrinsic domain shift problem wherein the generated outputs often lack details and resemble simplistic representations of the target domain. In this paper, we propose a novel guided image synthesis framework, which addresses this problem by modelling the output image as the solution of a constrained optimization problem. We show that while computing an exact solution to the optimization is infeasible, an approximation of the same can be achieved while just requiring a single pass of the reverse diffusion process. Additionally, we show that by simply defining a cross-attention based correspondence between the input text tokens and the user stroke-painting, the user is also able to control the semantics of different painted regions without requiring any conditional training or finetuning. Human user study results show that the proposed approach outperforms the previous state-of-the-art by over 85.32% on the overall user satisfaction scores. Project page for our paper is available at https://***/gradop.

关键词： image and video synthesis and generation

来源：评论

学校读者我要写书评

暂无评论

Inversion-based Style Transfer with Diffusion Models

Inversion-based Style Transfer with Diffusion Models

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhang, Yuxin Huang, Nisha Tang, Fan Huang, Haibin Ma, Chongyang Dong, Weiming Xu, Changsheng Chinese Acad Sci Inst Automat MAIS Beijing Peoples R China UCAS Sch AI Beijing Peoples R China Chinese Acad Sci Inst Comp Technol Beijing Peoples R China Kuaishou Technol Beijing Peoples R China

ISBN: (纸本)9798350301298

The artistic style within a painting is the means of expression, which includes not only the painting material, colors, and brushstrokes, but also the high-level attributes, including semantic elements and object shapes. Previous arbitrary example-guided artistic image generation methods often fail to control shape changes or convey elements. Pre-trained text-to-image synthesis diffusion probabilistic models have achieved remarkable quality but often require extensive textual descriptions to accurately portray the attributes of a particular painting. The uniqueness of an artwork lies in the fact that it cannot be adequately explained with normal language. Our key idea is to learn the artistic style directly from a single painting and then guide the synthesis without providing complex textual descriptions. Specifically, we perceive style as a learnable textual description of a painting. We propose an inversion-based style transfer method (InST), which can efficiently and accurately learn the key information of an image, thus capturing and transferring the artistic style of a painting. We demonstrate the quality and efficiency of our method on numerous paintings of various artists and styles. Codes are available at https://***/zyxElsa/InST.

关键词： image and video synthesis and generation

来源：评论

学校读者我要写书评

暂无评论

Catch Missing Details: image Reconstruction with Frequency Augmented Variational Autoencoder

Catch Missing Details: Image Reconstruction with Frequency A...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Lin, Xinmiao Li, Yikang Hsiao, Jenhao Ho, Chiuman Kong, Yu Rochester Inst Technol Rochester MN USA OPPO US Res Shenzhen Peoples R China Michigan State Univ E Lansing MI USA

ISBN: (纸本)9798350301298

The popular VQ-VAE models reconstruct images through learning a discrete codebook but suffer from a significant issue in the rapid quality degradation of image reconstruction as the compression rate rises. One major reason is that a higher compression rate induces more loss of visual signals on the higher frequency spectrum which reflect the details on pixel space. In this paper, a Frequency Complement Module (FCM) architecture is proposed to capture the missing frequency information for enhancing reconstruction quality. The FCM can be easily incorporated into the VQ-VAE structure, and we refer to the new model as Frequancy Augmented VAE (FA-VAE). In addition, a Dynamic Spectrum Loss (DSL) is introduced to guide the FCMs to balance between various frequencies dynamically for optimal reconstruction. FA-VAE is further extended to the text-to-image synthesis task, and a Cross-attention Autoregressive Transformer (CAT) is proposed to obtain more precise semantic attributes in texts. Extensive reconstruction experiments with different compression rates are conducted on several benchmark datasets, and the results demonstrate that the proposed FA-VAE is able to restore more faithfully the details compared to SOTA methods. CAT also shows improved generation quality with better image-text semantic alignment.

关键词： image and video synthesis and generation

来源：评论

学校读者我要写书评

暂无评论

GLeaD: Improving GANs with A Generator-Leading Task

GLeaD: Improving GANs with A Generator-Leading Task

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Bai, Qingyan Yang, Ceyuan Xu, Yinghao Liu, Xihui Yang, Yujiu Shen, Yujun Tsinghua Univ Tsinghua Shenzhen Int Grad Sch Beijing Peoples R China Shanghai AI Lab Shanghai Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China Univ Hong Kong Hong Kong Peoples R China Ant Grp Hangzhou Peoples R China

ISBN: (纸本)9798350301298

Generative adversarial network (GAN) is formulated as a two-player game between a generator (G) and a discriminator (D), where D is asked to differentiate whether an image comes from real data or is produced by G. Under such a formulation, D plays as the rule maker and hence tends to dominate the competition. Towards a fairer game in GANs, we propose a new paradigm for adversarial training, which makes G assign a task to D as well. Specifically, given an image, we expect D to extract representative features that can be adequately decoded by G to reconstruct the input. That way, instead of learning freely, D is urged to align with the view of G for domain classification. Experimental results on various datasets demonstrate the substantial superiority of our approach over the baselines. For instance, we improve the FID of StyleGAN2 from 4.30 to 2.55 on LSUN Bedroom and from 4.04 to 2.82 on LSUN Church. We believe that the pioneering attempt present in this work could inspire the community with better designed generator-leading tasks for GAN improvement. Project page is at https://***/glead/.

关键词： image and video synthesis and generation

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共19页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：