图像生成

Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models

Theo Putterman, Derek Lim, Yoav Gelberg, Stefanie Jegelka, Haggai Maron

专题命中 文生图 ：text-to-image(abstract)；diffusion(abstract)

Comments 24 pages

GaNDLF-Synth: A Framework to Democratize Generative AI for (Bio)Medical Imaging

Sarthak Pati, Szymon Mazurek, Spyridon Bakas

专题命中 文生图 ：diffusion(abstract)；image synthesis(abstract)

CAD-Prompted Generative Models: A Pathway to Feasible and Novel Engineering Designs

Leah Chong, Jude Rayan, Steven Dow, Ioanna Lykourentzou, Faez Ahmed

专题命中 文生图 ：text-to-image(abstract)；diffusion(abstract)

Comments 11 pages, 3 figures, 4 tables

Can Generative AI Replace Immunofluorescent Staining Processes? A Comparison Study of Synthetically Generated CellPainting Images from Brightfield

Xiaodan Xing, Siofra Murdoch, Chunling Tang, Giorgos Papanastasiou, Jan Cross-Zamirski, Yunzhe Guo, Xianglu Xiao, Carola-Bibiane Schönlieb, Yinhai Wang, Guang Yang

专题命中 文生图 ：diffusion(abstract)；image synthesis(abstract)

Non-convergence of Adam and other adaptive stochastic gradient descent optimization methods for non-vanishing learning rates

Steffen Dereich, Robin Graeber, Arnulf Jentzen

专题命中 文生图 ：text-to-image(abstract)；diffusion(abstract)

Comments 54 pages

StoryDiffusion: How to Support UX Storyboarding With Generative-AI

Zhaohui Liang, Xiaoyu Zhang, Kevin Ma, Zhao Liu, Xipei Ren, Kosa Goucher-Lambert, Can Liu

专题命中 文生图 ：image generation(abstract)；text-to-image(abstract)

Prompting AI Art: An Investigation into the Creative Skill of Prompt Engineering

Jonas Oppenlaender, Rhema Linder, Johanna Silvennoinen

专题命中 文生图 ：image generation(abstract)；text-to-image(abstract)

Comments 42 pages, 8 figures

At the edge of a generative cultural precipice

Diego Porres, Alex Gomez-Villa

专题命中 文生图 ：text-to-image(abstract)；diffusion(abstract)

Comments Accepted at the CVPR Fourth Workshop on Ethical Considerations in Creative applications of Computer Vision

Equivalence: An analysis of artists' roles with Image Generative AI from Conceptual Art perspective through an interactive installation design practice

Yixuan Li, Dan C. Baciu, Marcos Novak, George Legrady

专题命中 文生图 ：text-to-image(abstract)；diffusion(abstract)

Can AI Outperform Human Experts in Creating Social Media Creatives?

Eunkyung Park, Raymond K. Wong, Junbum Kwon

专题命中 文生图 ：text-to-image(abstract)；diffusion(abstract)

Comments 17 pages, 5 figures

Disentanglement in a GAN for Unconditional Speech Synthesis

Matthew Baas, Herman Kamper

专题命中 文生图 ：diffusion(abstract)；image synthesis(abstract)

Comments 12 pages, 5 tables, 4 figures. Accepted to IEEE TASLP. arXiv admin note: substantial text overlap with arXiv:2210.05271

Learning the Visualness of Text Using Large Vision-Language Models

Gaurav Verma, Ryan A. Rossi, Christopher Tensmeyer, Jiuxiang Gu, Ani Nenkova

专题命中 文生图 ：image generation(abstract)；text-to-image(abstract)

Comments Accepted at EMNLP 2023 (Main, long); 9 pages, 5 figures

Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models

Alvin Heng, Harold Soh

专题命中 文生图 ：text-to-image(abstract)；diffusion(abstract)

Language as Reality: A Co-Creative Storytelling Game Experience in 1001 Nights using Generative AI

Yuqian Sun, Zhouyi Li, Ke Fang, Chang Hee Lee, Ali Asadipour

专题命中 文生图 ：text-to-image(abstract)；diffusion(abstract)

Comments The paper was accepted by The 19th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE 23)

Catch You Everything Everywhere: Guarding Textual Inversion via Concept Watermarking

Weitao Feng, Jiyan He, Jie Zhang, Tianwei Zhang, Wenbo Zhou, Weiming Zhang, Nenghai Yu

专题命中 文生图 ：text-to-image(abstract)；diffusion(abstract)

Gender Bias in Multimodal Models: A Transnational Feminist Approach Considering Geographical Region and Culture

Abhishek Mandal, Suzanne Little, Susan Leavy

专题命中 文生图 ：text-to-image(abstract)；diffusion(abstract)

Comments Selected for publication at the Aequitas 2023: Workshop on Fairness and Bias in AI | co-located with ECAI 2023, Kraków, Poland

Grimm in Wonderland: Prompt Engineering with Midjourney to Illustrate Fairytales

Martin Ruskov

专题命中 文生图 ：image generation(abstract)；text-to-image(abstract)

Comments 19th Conference on Information and Research science Connecting to Digital and Library Science, February 23-24, 2023, Bari, Italy

Journal ref in 19th IRCDL, CEUR WS vol. 3365, pp. 180-191 (2023)

Learning Disentangled Discrete Representations

David Friede, Christian Reimers, Heiner Stuckenschmidt, Mathias Niepert

专题命中 文生图 ：image generation(abstract)；text-to-image(abstract)

Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery

Yuxin Wen, Neel Jain, John Kirchenbauer, Micah Goldblum, Jonas Geiping, Tom Goldstein

专题命中 文生图 ：text-to-image(abstract)；diffusion(abstract)

Comments 15 pages, 12 figures, Code is available at https://github.com/YuxinWenRick/hard-prompts-made-easy

Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model

Siyuan Huang, Zhengkai Jiang, Hao Dong, Yu Qiao, Peng Gao, Hongsheng Li

专题命中 文生图 ：image generation(abstract)；text-to-image(abstract)

Constructing Dreams using Generative AI

Safinah Ali, Daniella DiPaola, Randi Williams, Prerna Ravi, Cynthia Breazeal

专题命中 文生图 ：image generation(abstract)；text-to-image(abstract)

The Prompt Artists

Minsuk Chang, Stefania Druga, Alex Fiannaca, Pedro Vergani, Chinmay Kulkarni, Carrie Cai, Michael Terry

专题命中 文生图 ：text-to-image(abstract)；image editing(abstract)

Comments 20 pages, 7 figures

ODIN: On-demand Data Formulation to Mitigate Dataset Lock-in

SP Choi, Jihun Lee, Hyeongseok Ahn, Sanghee Jung, Bumsoo Kang

专题命中 文生图 ：text-to-image(abstract)；diffusion(abstract)

Comments 15 pages

Visualize Before You Write: Imagination-Guided Open-Ended Text Generation

Wanrong Zhu, An Yan, Yujie Lu, Wenda Xu, Xin Eric Wang, Miguel Eckstein, William Yang Wang

专题命中 文生图 ：text-to-image(abstract)；image synthesis(abstract)

Comments EACL 2023

I Learn to Diffuse, or Data Alchemy 101: a Mnemonic Manifesto

Victor Schetinger, Velitchko Filipov, Ignacio Pérez-Messina, Ethan Smith, Rodrigo Oliveira de Oliveira

专题命中 文生图 ：text-to-image(abstract)；diffusion(abstract)

Comments Submission to IEEE alt.vis 2022. Short paper containing a 4-page comic, and an immense amount of content in a linked miro board

Learning Priors for Adversarial Autoencoders

Hui-Po Wang, Wen-Hsiao Peng, Wei-Jan Ko

专题命中 文生图 ：text-to-image(abstract)；image synthesis(abstract)

Comments Accepted by APSIPA ASC, 2018

On Conditioning GANs to Hierarchical Ontologies

Hamid Eghbal-zadeh, Lukas Fischer, Thomas Hoch

专题命中 文生图 ：image generation(abstract)；image synthesis(abstract)

Comments Under review at MLKgraphs2019: http://www.dexa.org/mlkgraphs2019

SCULPT: Subtractive Composition for 3D Part Generation

SCULPT：用于3D部件生成的减法组合方法

Sikuang Li, Chen Yang, Jiemin Fang, Jiazhong Cen, Yuhe Wei, Jichen Pang, Wei Shen, Qi Tian

机构 * Shanghai Jiao Tong University（上海交通大学） ； Huawei（华为） 纠错

专题命中 文生图 ：text-to-image(abstract)；分类 cs.CV、cs.GR

AI总结 SCULPT是一种3D部件生成框架，通过减法组合方式生成部件，解决了现有方法的边界问题，在PartObjaverse上实现了最优几何性能，还能完成细粒度纹理部件分解。

Comments Project page: https://sculpt-part.github.io/ Code: https://github.com/sculpt-part/SCULPT

DiffPhysCam: Differentiable Physics-Based Camera Simulation for Inverse Rendering and Embodied AI

DiffPhysCam：面向逆渲染与具身智能的可微分基于物理的相机仿真

Bo-Hsun Chen, Nevindu M. Batagoda, Dan Negrut

机构 * Simulation-Based Engineering Lab, University of Wisconsin-Madison（模拟基于工程实验室，威斯康星大学麦迪逊分校） 纠错

专题命中 文生图 ：image synthesis(abstract)；分类 cs.CV、cs.GR

AI总结 本文提出DiffPhysCam，一款可微分基于物理的相机模拟器，解决现有虚拟相机局限，支持正向与逆渲染，经实验验证可提升机器人感知性能，还用于自主地面车辆导航的虚拟实验。

Comments 37 pages, 24 figures, and 5 tables. Code of DiffPhysCam-CamCaliExp: https://github.com/DanielYamChen/DiffPhysCam-CamCaliExp Code of DiffPhysCam-NovelViewSynthesis: https://github.com/DanielYamChen/DiffPhysCam-NovelViewSynthesis Data of DiffPhysCam_Data: https://huggingface.co/datasets/DanielYamChen/DiffPhysCam_Data Simulation video: https://youtu.be/gQwSMrdmHJI

Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation

模型是否共享安全表示？面向安全视觉生成的跨模型引导

Tobia Poppi, Silvia Cappelletti, Sara Sarto, Florian Schiffers, Garin Kessler, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

机构 * University of Modena and Reggio Emilia（摩德纳和雷吉奥艾米利亚大学） ； University of Pisa（比萨大学） ； Amazon Prime Video（亚马逊prime视频） 纠错

专题命中 文生图 ：text-to-image(abstract)；分类 cs.CV、cs.MM

AI总结 本文提出首个跨模型安全引导框架，通过源语言模型估计安全方向并迁移至目标生成器，无需目标侧不安全数据即可实现安全控制，且不牺牲生成质量。

Comments Project page: https://aimagelab.github.io/cross-model-safety-representations/