图像生成 - arXivDaily 专题

2011.13317 2020-11-30 cs.CV 74%

Adaptive Multiplane Image Generation from a Single Internet Picture

Diogo C. Luvizon, Gustavo Sutter P. Carvalho, Andreza A. dos Santos, Jhonatas S. Conceicao, Jose L. Flores-Campana, Luis G. L. Decker, Marcos R. Souza, Helio Pedrini, Antonio Joia, Otavio A. B. Penatti

专题命中可控生成：image generation(title)；分类 cs.CV

2010.05334 2020-11-24 cs.CV eess.IV 74%

Resolution Dependent GAN Interpolation for Controllable Image Synthesis Between Domains

Justin N. M. Pinkney, Doron Adler

专题命中可控生成：image synthesis(title)；分类 cs.CV

Comments 2 pages, 3 figures. Accepted to Machine Learning for Creativity and Design NeurIPS 2020 Workshop; Corrected typos

2005.02671 2020-10-20 cs.CV cs.LG 74%

CONFIG: Controllable Neural Face Image Generation

Marek Kowalski, Stephan J. Garbin, Virginia Estellers, Tadas Baltrušaitis, Matthew Johnson, Jamie Shotton

专题命中可控生成：image generation(title)；分类 cs.CV

Comments includes supplementary materials

2005.02133 2020-05-06 cs.CV eess.IV stat.ML 74%

Quality Guided Sketch-to-Photo Image Synthesis

Uche Osahor, Hadi Kazemi, Ali Dabouei, Nasser Nasrabadi

专题命中可控生成：image synthesis(title)；分类 cs.CV

Comments 10 pages, 9 figures

2004.12411 2020-05-06 cs.CV 74%

Disentangled Image Generation Through Structured Noise Injection

Yazeed Alharbi, Peter Wonka

专题命中可控生成：image generation(title)；分类 cs.CV

Comments CVPR2020 Oral. Project page: https://github.com/yalharbi/StructuredNoiseInjection

2004.04400 2020-04-10 cs.CV 74%

Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis

Jogendra Nath Kundu, Siddharth Seth, Varun Jampani, Mugalodi Rakesh, R. Venkatesh Babu, Anirban Chakraborty

专题命中可控生成：image synthesis(title)；分类 cs.CV

Comments CVPR 2020 (Oral)

2004.00642 2020-04-03 cs.LG cs.CV stat.ML 74%

Object-Centric Image Generation with Factored Depths, Locations, and Appearances

Titas Anciukevicius, Christoph H. Lampert, Paul Henderson

专题命中可控生成：image generation(title)；分类 cs.CV

1810.08534 2020-03-06 cs.CV 74%

MsCGAN: Multi-scale Conditional Generative Adversarial Networks for Person Image Generation

Wei Tang, Gui Li, Xinyuan Bao, Teng Li

专题命中可控生成：image generation(title)；分类 cs.CV

2001.02993 2020-01-10 cs.CV cs.LG eess.IV 74%

Spherical Image Generation from a Single Normal Field of View Image by Considering Scene Symmetry

Takayuki Hara, Tatsuya Harada

专题命中可控生成：image generation(title)；分类 cs.CV

Comments 15 pages

2001.01259 2020-01-07 cs.CV cs.LG eess.IV 74%

A Robust Pose Transformational GAN for Pose Guided Person Image Synthesis

Arnab Karmakar, Deepak Mishra

专题命中可控生成：image synthesis(title)；分类 cs.CV

Comments Accepted in 7th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG 2019)

1905.00007 2019-10-15 cs.CV 74%

Appearance and Pose-Conditioned Human Image Generation using Deformable GANs

Aliaksandr Siarohin, Stéphane Lathuilière, Enver Sangineto, Nicu Sebe

专题命中可控生成：image generation(title)；分类 cs.CV

Comments To appear on IEEE TPAMI. arXiv admin note: substantial text overlap with arXiv:1801.00055

1909.06436 2019-10-04 eess.IV cs.CV 74%

Coupling Rendering and Generative Adversarial Networks for Artificial SAS Image Generation

Albert Reed, Isaac Gerg, John McKay, Daniel Brown, David Williams, Suren Jayasuriya

专题命中可控生成：image generation(title)；分类 cs.CV

Comments 10 pages, 9 figures. Submitted to IEEE OCEANS 2019 (Seattle). Updated acknowledgements

1907.12296 2019-07-30 eess.IV cs.CV 74%

A Two Stage GAN for High Resolution Retinal Image Generation and Segmentation

Paolo Andreini, Simone Bonechi, Monica Bianchini, Alessandro Mecocci, Franco Scarselli, Andrea Sodi

专题命中可控生成：image generation(title)；分类 cs.CV

1901.02284 2019-06-06 cs.CV 74%

Unpaired Pose Guided Human Image Generation

Xu Chen, Jie Song, Otmar Hilliges

专题命中可控生成：image generation(title)；分类 cs.CV

Comments camera ready for CVPR 2019 VUHCS workshop

1904.03349 2019-05-14 cs.CV 74%

Progressive Pose Attention Transfer for Person Image Generation

Zhen Zhu, Tengteng Huang, Baoguang Shi, Miao Yu, Bofei Wang, Xiang Bai

专题命中可控生成：image generation(title)；分类 cs.CV

Comments To appear in CVPR 2019, oral presentation (21 pages, 15 figures including the supplementary materials)

1903.06814 2019-03-19 cs.CV cs.RO 74%

Generate What You Can't See - a View-dependent Image Generation

Karol Piaskowski, Rafal Staszak, Dominik Belter

专题命中可控生成：image generation(title)；分类 cs.CV

Comments Submitted to IROS 2019. Copyright 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses. Supplementary video: https://youtu.be/gCAoJ7BM5F0

1812.05083 2019-02-07 cs.CV cs.CL cs.LG 74%

Adversarial Learning of Semantic Relevance in Text to Image Synthesis

Miriam Cha, Youngjune L. Gwon, H. T. Kung

专题命中可控生成：image synthesis(title)；分类 cs.CV

1712.02621 2018-06-18 cs.CV 74%

Disentangled Person Image Generation

Liqian Ma, Qianru Sun, Stamatios Georgoulis, Luc Van Gool, Bernt Schiele, Mario Fritz

专题命中可控生成：image generation(title)；分类 cs.CV

Comments Published at CVPR'18 (Spotlight). Corresponding author is Qianru Sun

1805.10130 2018-05-28 cs.LG cs.CV stat.ML 74%

Cross Domain Image Generation through Latent Space Exploration with Adversarial Loss

Yingjing Lu

专题命中可控生成：image generation(title)；分类 cs.CV

1805.02481 2018-05-09 cs.CV 74%

MEGAN: Mixture of Experts of Generative Adversarial Networks for Multimodal Image Generation

David Keetae Park, Seungjoo Yoo, Hyojin Bahng, Jaegul Choo, Noseong Park

专题命中可控生成：image generation(title)；分类 cs.CV

Comments 27th International Joint Conference on Artificial Intelligence (IJCAI 2018)

1801.00055 2018-04-09 cs.CV 74%

Deformable GANs for Pose-based Human Image Generation

Aliaksandr Siarohin, Enver Sangineto, Stephane Lathuiliere, Nicu Sebe

专题命中可控生成：image generation(title)；分类 cs.CV

Comments CVPR 2018 version

1804.01622 2018-04-06 cs.CV cs.LG 74%

Image Generation from Scene Graphs

Justin Johnson, Agrim Gupta, Li Fei-Fei

专题命中可控生成：image generation(title)；分类 cs.CV

Comments To appear at CVPR 2018

1705.09368 2018-01-30 cs.CV 74%

Pose Guided Person Image Generation

Liqian Ma, Xu Jia, Qianru Sun, Bernt Schiele, Tinne Tuytelaars, Luc Van Gool

专题命中可控生成：image generation(title)；分类 cs.CV

Comments Xu Jia and Qianru Sun contribute equally. Accepted in Proceedings of 31st Conference on Neural Information Processing Systems (NIPS 2017)

1711.09767 2017-11-28 cs.CV cs.AI cs.HC 74%

GazeGAN - Unpaired Adversarial Image Generation for Gaze Estimation

Matan Sela, Pingmei Xu, Junfeng He, Vidhya Navalpakkam, Dmitry Lagun

专题命中可控生成：image generation(title)；分类 cs.CV

Comments Project was done when the first author was at Google Research

1707.06873 2017-07-24 cs.CV 74%

Semantic Image Synthesis via Adversarial Learning

Hao Dong, Simiao Yu, Chao Wu, Yike Guo

专题命中可控生成：image synthesis(title)；分类 cs.CV

Comments Accepted to ICCV 2017

2606.18780 2026-06-18 cs.CV cs.CL cs.MM 新提交 73%

SAMA: Semantic Anchor-aligned Augmentation for Unified Low-Resource Multimodal Information Extraction

SAMA：面向统一低资源多模态信息抽取的语义锚定对齐增强

Quanjiang Guo, Chong Mu, Jiazhou Pan, Ming Jia, Ling Tian, Hui Gao, Zhao Kang

机构 * School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）

专题命中可控生成：diffusion(abstract)；image synthesis(abstract)；分类 cs.CV、cs.MM

AI总结提出语义锚定对齐增强框架SAMA，通过构建结构化语义锚引导多专家多模态大模型生成高保真文本，并利用锚保留扩散机制合成图像，结合双约束过滤模块，在低资源多模态信息抽取任务中显著提升性能。

Comments Accepted by IEEE Transactions on Multimedia

2606.06498 2026-06-08 cs.GR cs.CV 新提交 73%

Semantic-Structural Alignment for Generative Pictorial Charts

生成式图形图表的语义-结构对齐

Zhida Sun, Yulin Zhang, Zheng Gu, Min Lu, Bongshin Lee, Daniel Cohen-Or, Hui Huang

机构 * Visual Computing Research Center (VCC), College of Computer Science and Software Engineering (CSSE) Shenzhen University China（视觉计算研究中心（VCC）、计算机科学与软件工程学院（CSSE）深圳大学中国）

专题命中可控生成：diffusion(abstract)；image editing(abstract)；分类 cs.CV、cs.GR

AI总结提出一种生成式框架，通过多模态扩散变压器中的结构对齐和语义对齐机制，实现兼具艺术表现力和结构保真度的图形图表自动合成。

Comments 11 pages, 17 figures, Accepted to ACM TOG

2605.14716 2026-05-18 cs.GR cs.CV cs.LG 73%

AnchorRoute: Human Motion Synthesis with Interval-Routed Sparse Contro

AnchorRoute: 通过区间路由稀疏控制的人体运动合成

Pengcheng Fang, Tengjiao Sun, Dongjie Fu, Xiaoyu Zhan, Yanwen Guo, Hansung Kim, Xiaohao Cai

机构 * University of Southampton（索姆塞特大学）； Mogo AI Ltd.（Mogo AI有限公司）； Nanjing University（南京大学）

专题命中可控生成：diffusion(abstract,abstract_cn)；分类 cs.CV、cs.GR

AI总结 AnchorRoute通过稀疏锚点实现人体运动合成，结合生成与细化过程，提升稀疏控制效果。

2604.10617 2026-04-14 eess.IV cs.CV cs.MM 73%

Brain-Grasp: Graph-based Saliency Priors for Improved fMRI-based Visual Brain Decoding

Brain-Grasp: 基于图的显著性先验用于改进基于fMRI的视觉脑解码

Mohammad Moradi, Morteza Moradi, Marco Grassia, Giuseppe Mangioni

机构 * University of Catania, Catania, Italy（卡塔尼亚大学，卡塔尼亚，意大利）

专题命中可控生成：image generation(abstract)；diffusion(abstract)；分类 cs.CV、cs.MM

AI总结本文提出基于图的显著性先验框架，利用脑信号结构线索生成空间掩码，结合语义信息引导扩散模型，提升fMRI视觉解码的结构和语义一致性。

2403.15048 2026-03-09 cs.CV cs.AI cs.LG cs.MM 73%

Make VLM Recognize Visual Hallucination on Cartoon Character Image with Pose Information

使VLM在卡通角色图像上通过姿态信息识别视觉幻觉

Bumsoo Kim, Wonseop Shin, Kyuchul Lee, Yonghoon Jung, Sanghyun Seo

机构 * Chung-Ang University（Chung-Ang 大学）； Coupang（韩国Coupang）

专题命中可控生成：text-to-image(abstract)；image synthesis(abstract)；分类 cs.CV、cs.MM

AI总结本文提出基于姿态信息的VLM幻觉检测方法，通过上下文学习提升识别准确率，实验表明在卡通角色图像中幻觉检测效果提升50%-80%。

Comments Accepted at WACV 2025, Project page: https://gh-bumsookim.github.io/Cartoon-Hallucinations-Detection/. (Fixed typos)

1. 可控生成 4210 篇

Adaptive Multiplane Image Generation from a Single Internet Picture

Resolution Dependent GAN Interpolation for Controllable Image Synthesis Between Domains

CONFIG: Controllable Neural Face Image Generation

Quality Guided Sketch-to-Photo Image Synthesis

Disentangled Image Generation Through Structured Noise Injection

Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis

Object-Centric Image Generation with Factored Depths, Locations, and Appearances

MsCGAN: Multi-scale Conditional Generative Adversarial Networks for Person Image Generation

Spherical Image Generation from a Single Normal Field of View Image by Considering Scene Symmetry

A Robust Pose Transformational GAN for Pose Guided Person Image Synthesis

Appearance and Pose-Conditioned Human Image Generation using Deformable GANs

Coupling Rendering and Generative Adversarial Networks for Artificial SAS Image Generation

A Two Stage GAN for High Resolution Retinal Image Generation and Segmentation

Unpaired Pose Guided Human Image Generation

Progressive Pose Attention Transfer for Person Image Generation

Generate What You Can't See - a View-dependent Image Generation

Adversarial Learning of Semantic Relevance in Text to Image Synthesis

Disentangled Person Image Generation

Cross Domain Image Generation through Latent Space Exploration with Adversarial Loss

MEGAN: Mixture of Experts of Generative Adversarial Networks for Multimodal Image Generation

Deformable GANs for Pose-based Human Image Generation

Image Generation from Scene Graphs

Pose Guided Person Image Generation

GazeGAN - Unpaired Adversarial Image Generation for Gaze Estimation

Semantic Image Synthesis via Adversarial Learning

SAMA: Semantic Anchor-aligned Augmentation for Unified Low-Resource Multimodal Information Extraction

Semantic-Structural Alignment for Generative Pictorial Charts

AnchorRoute: Human Motion Synthesis with Interval-Routed Sparse Contro

Brain-Grasp: Graph-based Saliency Priors for Improved fMRI-based Visual Brain Decoding

Make VLM Recognize Visual Hallucination on Cartoon Character Image with Pose Information