图像生成 - arXivDaily 专题

1510.00889 2015-10-06 cs.CV 74%

Background Image Generation Using Boolean Operations

Kardi Teknomo, Proceso Fernandez

专题命中其他图像生成：image generation(title)；分类 cs.CV

Journal ref Philippine Computing Journal Vol 4 No 2, December 2009, pp. 43-49

1506.00278 2015-06-02 cs.CV cs.CL 74%

Visual Madlibs: Fill in the blank Image Generation and Question Answering

Licheng Yu, Eunbyung Park, Alexander C. Berg, Tamara L. Berg

专题命中其他图像生成：image generation(title)；分类 cs.CV

Comments 10 pages; 8 figures; 4 tables

2004.07543 2021-12-15 cs.LG stat.ML 73%

Classify and Generate: Using Classification Latent Space Representations for Image Generations

Saisubramaniam Gopalakrishnan, Pranshu Ranjan Singh, Yasin Yazici, Chuan-Sheng Foo, Vijay Chandrasekhar, ArulMurugan Ambikapathi

专题命中其他图像生成：image generation(title,journal_ref)

Journal ref Saisubramaniam Gopalakrishnan, Pranshu Ranjan Singh et. al., Classify and generate: Using classification latent space representations for image generations, Neurocomputing, Volume 471, 2022, Pages 296-334, ISSN 0925-2312

2605.10898 2026-06-19 cs.HC 版本更新 71%

How Creatives Approach GenAI Image Generation: Tensions Between Structured Guidance, Self-Experimentation, and Creative Autonomy

创意人士如何接近生成式AI图像生成：结构化指导、自我实验与创意自主之间的张力

Haidan Liu, Isabelle Kwan, Taiga Okuma, Jeffrey Loverock, Nicholas Vincent, Parmit K Chilana

专题命中其他图像生成：image generation(title)

AI总结研究探讨创意人士在使用生成式AI图像工具时如何平衡结构化指导与自我实验，发现尽管指导有助于理解AI，但许多人仍倾向于自我探索以保持创意自由。

Comments Accepted at ACM Creativity & Cognition 2026

2501.04163 2026-05-19 cs.HC 71%

HistoryPalette: Supporting Exploration and Reuse of Past Alternatives in Image Generation and Editing

HistoryPalette: 支持在图像生成与编辑中探索和重用过去的选择

Karim Benharrak, Amy Pavel

专题命中其他图像生成：image generation(title)

AI总结 HistoryPalette通过组织历史设计替代方案，帮助创作者快速预览和重用先前工作，提升创意任务的效率与协作体验。

Comments Accepted to CHI 2026

2602.06339 2026-05-13 cs.RO cs.AI 71%

Action Hallucination in Generative Vision-Language-Action Models

生成视觉-语言-动作模型中的动作幻觉

Harold Soh, Eugene Lim

机构 * Department of Computer Science, School of Computing（计算机科学系，计算系）； Smart Systems Institute（智能系统研究所）

专题命中其他图像生成：generative vision(title)

AI总结研究分析生成视觉-语言-动作模型中动作幻觉的根源，揭示拓扑、精度和地平线三类障碍对动作生成的影响，提出改进模型可靠性和可信度的方法。

Comments 24 pages; updated setup with minor changes to proofs. changed template

2510.26828 2025-11-11 eess.IV cs.AI 71%

Beyond Data Scarcity Optimizing R3GAN for Medical Image Generation from Small Datasets

Tsung-Wei Pan, Chang-Hong Wu, Jung-Hua Wang, Ming-Jer Chen, Yu-Chiao Yi, Tsung-Hsien Lee

专题命中其他图像生成：image generation(title)

2306.08915 2024-02-01 cs.IR 71%

Prompt Performance Prediction for Image Generation

Nicolas Bizzozzero, Ihab Bendidi, Olivier Risser-Maroix

专题命中其他图像生成：image generation(title)

2307.05253 2023-10-24 quant-ph hep-ex 71%

Precise Image Generation on Current Noisy Quantum Computing Devices

Florian Rehm, Sofia Vallecorsa, Kerstin Borras, Dirk Krücker, Michele Grossi, Valle Varo

专题命中其他图像生成：image generation(title)

Journal ref IOP Quantum Science and Technology (October 2023)

2205.12900 2023-07-21 stat.ML cs.CR cs.LG 71%

Pre-trained Perceptual Features Improve Differentially Private Image Generation

Fredrik Harder, Milad Jalali Asadabadi, Danica J. Sutherland, Mijung Park

专题命中其他图像生成：image generation(title)

2107.01976 2021-07-06 physics.med-ph eess.IV 71%

DeepWL: Robust EPID based Winston-Lutz Analysis using Deep Learning and Synthetic Image Generation

Michael J. J. Douglass, James A. Keal

专题命中其他图像生成：image generation(title)

Comments 21 pages, 12 figures, 3 tables

2004.07603 2020-04-17 physics.bio-ph eess.IV q-bio.BM 71%

Liquified protein vibrations, classification and cross-paradigm de novo image generation using deep neural networks

Markus J. Buehler

专题命中其他图像生成：image generation(title)

Comments 19 pages, 11 figures

1810.07990 2018-10-19 cs.RO 71%

Deep Learning from Shallow Dives: Sonar Image Generation and Training for Underwater Object Detection

Sejin Lee, Byungjae Park, Ayoung Kim

专题命中其他图像生成：image generation(title)

2403.11626 2024-03-19 cs.GR cs.AI cs.CV cs.MM cs.SD eess.AS 67%

QEAN: Quaternion-Enhanced Attention Network for Visual Dance Generation

Zhizhen Zhou, Yejing Huo, Guoheng Huang, An Zeng, Xuhang Chen, Lian Huang, Zinuo Li

专题命中其他图像生成：image generation(abstract)；分类 cs.CV、cs.GR、cs.MM

Comments Accepted by The Visual Computer Journal

2510.03308 2025-10-21 cs.GR cs.AI cs.CV 62%

Creative synthesis of kinematic mechanisms

Jiong Lin, Jialong Ning, Judah Goldfeder, Hod Lipson

机构 * Creative Machines Lab, Columbia University（创意机器实验室，哥伦比亚大学）

专题命中其他图像生成：image generation(abstract)；分类 cs.CV、cs.GR

Comments 6pages, 6 figures

2510.04536 2025-10-07 cs.GR cs.AI cs.CV 62%

3Dify: a Framework for Procedural 3D-CG Generation Assisted by LLMs Using MCP and RAG

Shun-ichiro Hayashi, Daichi Mukunoki, Tetsuya Hoshino, Satoshi Ohshima, Takahiro Katagiri

机构 * Graduate School of Informatics（信息科学研究生学校）； Nagoya University（名古屋大学）； Research Institute for Information Technology（信息科学技术研究所）

专题命中其他图像生成：image generation(abstract)；分类 cs.CV、cs.GR

2403.04800 2024-03-11 eess.AS cs.CV cs.GR cs.LG 62%

(Un)paired signal-to-signal translation with 1D conditional GANs

Eric Easthope

专题命中其他图像生成：image generation(abstract)；分类 cs.CV、cs.GR

2312.07132 2023-12-13 cs.CV cs.MM 62%

Image Content Generation with Causal Reasoning

Xiaochuan Li, Baoyu Fan, Runze Zhang, Liang Jin, Di Wang, Zhenhua Guo, Yaqian Zhao, Rengang Li

专题命中其他图像生成：image generation(abstract)；分类 cs.CV、cs.MM

Comments Accepted by the 38th Annual AAAI Conference on Artificial Intelligence (AAAI 2024) in December 2023

2305.05838 2023-05-11 cs.CV cs.MM 62%

Generative Steganographic Flow

Ping Wei, Ge Luo, Qi Song, Xinpeng Zhang, Zhenxing Qian, Sheng Li

专题命中其他图像生成：image generation(abstract)；分类 cs.CV、cs.MM

Comments The accepted paper in ICME 2022

2207.13867 2022-08-16 cs.CV cs.MM 62%

Generative Steganography Network

Ping Wei, Sheng Li, Xinpeng Zhang, Ge Luo, Zhenxing Qian, Qing Zhou

专题命中其他图像生成：image generation(abstract)；分类 cs.CV、cs.MM

2007.08457 2022-03-21 cs.CR cs.CV cs.CY cs.GR cs.LG 62%

Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data

Ning Yu, Vladislav Skripniuk, Sahar Abdelnabi, Mario Fritz

专题命中其他图像生成：image generation(abstract)；分类 cs.CV、cs.GR

Comments Accepted to ICCV'21 as Oral

2106.10876 2021-06-22 cs.CV cs.AI cs.MM 62%

Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes

Hao Tang, Nicu Sebe

专题命中其他图像生成：image generation(abstract)；分类 cs.CV、cs.MM

Comments Accepted to TMM, an extended version of a paper published in ACM MM 2019. arXiv admin note: substantial text overlap with arXiv:1908.00999

2007.00074 2020-08-20 cs.GR cs.CV cs.LG 62%

Deep Geometric Texture Synthesis

Amir Hertz, Rana Hanocka, Raja Giryes, Daniel Cohen-Or

专题命中其他图像生成：image generation(abstract)；分类 cs.CV、cs.GR

Comments SIGGRAPH 2020

1706.00082 2017-06-02 cs.CV cs.GR cs.LG 62%

Megapixel Size Image Creation using Generative Adversarial Networks

Marco Marchesi

专题命中其他图像生成：image generation(abstract)；分类 cs.CV、cs.GR

Comments 3 pages, 4 figures

2608.03471 2026-08-17 cs.CV 版本更新 57%

Hi-Token: Hierarchical Coordinate Tokenization for Generative Visual Grounding

Hi-Token：用于生成式视觉定位的分层坐标分词

Xiuyuan Zhu, Ke Lu, Kun Dong, Siwen Jiao, Hao Wu, Zijin Du, Shun Mao, Dongming Zhang, Jian Xue

专题命中其他图像生成：generative vision(abstract)；分类 cs.CV

AI总结该研究提出Hi-Token分层坐标分词方法，结合基于几何的Hi-GAR奖励，在生成式视觉定位任务中提升了多模型多基准的定位性能，优于强专用基线。

Comments 15 pages, 7 figures, 15 tables

2607.28974 2026-08-03 cs.CV cs.AI 新提交 57%

RAID: Towards Robust AI-Generated Image Detection with Bit-Reversed Images

RAID：利用位反转图像实现鲁棒的AI生成图像检测

Renxi Cheng, Jie Gui, Hongsong Wang

机构 * School of Cyber Science and Engineering, Southeast University（东南大学网络空间科学与工程学院）； Purple Mountain Laboratories（紫金山实验室）； School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）

专题命中其他图像生成：image generation(abstract)；分类 cs.CV

AI总结本研究提出RAID方法，通过位反转图像构建、梯度块选择与卷积分类器实现AI生成图像检测，在40多个基准上优于现有方法且速度快约100倍，还提供了理论分析与新数据集。

Comments 14 pages, 6 figures

2607.08434 2026-07-10 cs.CV 新提交 57%

DeltaV: Thinking with Visual State Updates in Unified Large Multimodal Models

DeltaV：在统一大型多模态模型中通过视觉状态更新进行思考

Pengjie Wang, Linger Deng, Zujia Zhang, Shaojie Zhang, Zhenbo Luo, Pei Fu, Jian Luan, Xiang Bai, Yuliang Liu

机构 * Huazhong University of Science and Technology（华中科技大学）； Xiaomi Inc.（小米公司）

专题命中其他图像生成：image generation(abstract)；分类 cs.CV

AI总结研究针对统一大型多模态模型全图像生成范式的问题，提出DeltaV模型，通过视觉更新避免冗余，引入TSIM路由器匹配令牌预算，构建StructCoT数据集，实验证明该范式能减少视觉令牌、提升推理能力，DeltaV - 2B性能优异。

2603.17390 2026-07-09 cs.CV 版本更新 57%

FMMC: Harnessing the Power of Foundation Models for Accurate Material Classification

利用基础模型提升材料分类的准确性

Qingran Lin, Fengwei Yang, Chaolun Zhu

机构 * Georgia Institute of Technology（佐治亚理工学院）； Duke University（杜克大学）； Waseda University（早稻田大学）

专题命中其他图像生成：image generation(abstract)；分类 cs.CV

AI总结本文提出一种利用基础模型克服数据限制并提升分类准确性的新框架，通过生成高质量数据集和融合视觉语言模型先验知识，有效提高材料分类性能。

2509.25682 2026-07-01 cs.CV 版本更新 57%

Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples

少样本合成图像溯源：有限样本下识别未见生成器

Shiyu Wu, Shuyan Li, Jing Li, Jing Liu, Yequan Wang

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）； Beijing Academy of Artificial Intelligence（北京智源人工智能研究院）； University of Chinese Academy of Sciences（中国科学院大学）； Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）； Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））； Peking University（北京大学）

专题命中其他图像生成：image generation(abstract)；分类 cs.CV

AI总结提出少样本合成图像溯源新范式，构建含45个生成器、117万图像的OmniFake数据集，并设计OmniDFA基线，实现少样本下识别未见生成器，在AIGI检测中达到最优泛化性能。

Comments ECCV 2026

2606.28386 2026-06-30 cs.CV cs.AI 57%

Data Provenance for Image Auto-Regressive Generation

图像自回归生成的数据溯源

Bihe Zhao, Louis Kerner, Michel Meintz, Tameem Bakr, Franziska Boenisch, Adam Dziedzic

机构 * CISPA Helmholtz Center for Information Security（CISPA海德堡信息安全研究中心）

专题命中其他图像生成：image generation(abstract)；分类 cs.CV

AI总结提出后验框架，利用自回归生成模型输出中的特征模式进行图像溯源，无需修改生成过程或输出，适用于无水印场景。

Comments Accepted at ICLR 2026

1. 其他图像生成 762 篇

Background Image Generation Using Boolean Operations

Visual Madlibs: Fill in the blank Image Generation and Question Answering

Classify and Generate: Using Classification Latent Space Representations for Image Generations

How Creatives Approach GenAI Image Generation: Tensions Between Structured Guidance, Self-Experimentation, and Creative Autonomy

HistoryPalette: Supporting Exploration and Reuse of Past Alternatives in Image Generation and Editing

Action Hallucination in Generative Vision-Language-Action Models

Beyond Data Scarcity Optimizing R3GAN for Medical Image Generation from Small Datasets

Prompt Performance Prediction for Image Generation

Precise Image Generation on Current Noisy Quantum Computing Devices

Pre-trained Perceptual Features Improve Differentially Private Image Generation

DeepWL: Robust EPID based Winston-Lutz Analysis using Deep Learning and Synthetic Image Generation

Liquified protein vibrations, classification and cross-paradigm de novo image generation using deep neural networks

Deep Learning from Shallow Dives: Sonar Image Generation and Training for Underwater Object Detection

QEAN: Quaternion-Enhanced Attention Network for Visual Dance Generation

Creative synthesis of kinematic mechanisms

3Dify: a Framework for Procedural 3D-CG Generation Assisted by LLMs Using MCP and RAG

(Un)paired signal-to-signal translation with 1D conditional GANs

Image Content Generation with Causal Reasoning

Generative Steganographic Flow

Generative Steganography Network

Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data

Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes

Deep Geometric Texture Synthesis

Megapixel Size Image Creation using Generative Adversarial Networks

Hi-Token: Hierarchical Coordinate Tokenization for Generative Visual Grounding

RAID: Towards Robust AI-Generated Image Detection with Bit-Reversed Images

DeltaV: Thinking with Visual State Updates in Unified Large Multimodal Models

FMMC: Harnessing the Power of Foundation Models for Accurate Material Classification

Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples

Data Provenance for Image Auto-Regressive Generation