图像生成 - arXivDaily 专题

2410.14749 2024-10-22 cs.LG cs.CV 57%

CFTS-GAN: Continual Few-Shot Teacher Student for Generative Adversarial Networks

Munsif Ali, Leonardo Rossi, Massimo Bertozzi

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

2410.08534 2024-10-22 cs.CV eess.IV 57%

Quality Prediction of AI Generated Images and Videos: Emerging Trends and Opportunities

Abhijay Ghildyal, Yuanhan Chen, Saman Zadtootaghaj, Nabajeet Barman, Alan C. Bovik

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

Comments "The abstract field cannot be longer than 1,920 characters", the abstract appearing here is slightly shorter than that in the PDF file

2212.09977 2024-10-15 eess.IV cs.CV 57%

Unified Framework for Histopathology Image Augmentation and Classification via Generative Models

Meng Li, Chaoyi Li, Can Peng, Brian C. Lovell

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

2410.02613 2024-10-04 cs.CV cs.AI cs.CL 57%

NL-Eye: Abductive NLI for Images

Mor Ventura, Michael Toker, Nitay Calderon, Zorik Gekhman, Yonatan Bitton, Roi Reichart

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

2410.00905 2024-10-02 cs.CV 57%

Removing Distributional Discrepancies in Captions Improves Image-Text Alignment

Yuheng Li, Haotian Liu, Mu Cai, Yijun Li, Eli Shechtman, Zhe Lin, Yong Jae Lee, Krishna Kumar Singh

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

2404.13788 2024-10-01 cs.CV cs.AI 57%

AnyPattern: Towards In-context Image Copy Detection

Wenhao Wang, Yifan Sun, Zhentao Tan, Yi Yang

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

Comments The project is publicly available at https://anypattern.github.io

2409.15781 2024-09-25 cs.CV 57%

Training Data Attribution: Was Your Model Secretly Trained On Data Created By Mine?

Likun Zhang, Hao Wu, Lingcui Zhang, Fengyuan Xu, Jin Cao, Fenghua Li, Ben Niu

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

2409.12244 2024-09-20 cs.CV cs.AI cs.LG 57%

Sparks of Artificial General Intelligence(AGI) in Semiconductor Material Science: Early Explorations into the Next Frontier of Generative AI-Assisted Electron Micrograph Analysis

Sakhinana Sagar Srinivas, Geethan Sannidhi, Sreeja Gangasani, Chidaksh Ravuru, Venkataramana Runkana

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

Comments Published at Deployable AI (DAI) Workshop at AAAI-2024

2409.11923 2024-09-19 cs.CV 57%

Agglomerative Token Clustering

Joakim Bruslund Haurum, Sergio Escalera, Graham W. Taylor, Thomas B. Moeslund

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

Comments ECCV 2024. Project webpage at https://vap.aau.dk/atc/

2404.02530 2024-09-18 cs.CV cs.AI 57%

Manipulating and Mitigating Generative Model Biases without Retraining

Jordan Vice, Naveed Akhtar, Richard Hartley, Ajmal Mian

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

Comments Accepted to ECCV 2024 WS: Workshop on critical evaluation of generative models and their impact on society (CEGIS)

2409.09361 2024-09-17 cs.LG cs.CV stat.ML 57%

Beta-Sigma VAE: Separating beta and decoder variance in Gaussian variational autoencoder

Seunghwan Kim, Seungkyu Lee

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

Comments Accepted for ICPR 2024

2409.01936 2024-09-04 cs.CV cs.LG 57%

Optimizing CLIP Models for Image Retrieval with Maintained Joint-Embedding Alignment

Konstantin Schall, Kai Uwe Barthel, Nico Hezel, Klaus Jung

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

2404.05783 2024-09-04 cs.CY cs.AI cs.CL cs.CV 57%

A Survey on Responsible Generative AI: What to Generate and What Not

Jindong Gu

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

Comments 77 pages, 10 figures

2408.13906 2024-08-27 cs.CV cs.AI cs.LG 57%

ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models

Yeji Park, Deokyeong Lee, Junsuk Choe, Buru Chang

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

Comments First two authors contributed equally. Source code is available at https://github.com/yejipark-m/ConVis

2008.07588 2024-08-19 eess.IV cs.CV cs.LG stat.ML 57%

Uncertainty Quantification using Variational Inference for Biomedical Image Segmentation

Abhinav Sagar

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

2310.08541 2024-08-15 cs.CV 57%

Idea2Img: Iterative Self-Refinement with GPT-4V(ision) for Automatic Image Design and Generation

Zhengyuan Yang, Jianfeng Wang, Linjie Li, Kevin Lin, Chung-Ching Lin, Zicheng Liu, Lijuan Wang

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

Comments ECCV 2024; Project page at https://idea2img.github.io/

2312.07315 2024-08-13 cs.CV 57%

NVS-Adapter: Plug-and-Play Novel View Synthesis from a Single Image

Yoonwoo Jeong, Jinwoo Lee, Chiheon Kim, Minsu Cho, Doyup Lee

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

Comments [ECCV2024] Project Page: https://postech-cvlab.github.io/nvsadapter/

2408.02231 2024-08-06 cs.CV 57%

REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language Models

Agneet Chatterjee, Yiran Luo, Tejas Gokhale, Yezhou Yang, Chitta Baral

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

Comments Accepted to ECCV 2024. Project Page : https://agneetchatterjee.com/revision/

2408.00352 2024-08-02 cs.CV 57%

Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion

Honglei Miao, Fan Ma, Ruijie Quan, Kun Zhan, Yi Yang

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

2407.20268 2024-07-31 cs.CV cs.LG eess.IV 57%

Utilizing Generative Adversarial Networks for Image Data Augmentation and Classification of Semiconductor Wafer Dicing Induced Defects

Zhining Hu, Tobias Schlosser, Michael Friedrich, André Luiz Vieira e Silva, Frederik Beuth, Danny Kowerko

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

Comments Accepted for: 2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA)

2403.15992 2024-07-19 cs.CV cs.CL 57%

BIMCV-R: A Landmark Dataset for 3D CT Text-Image Retrieval

Yinda Chen, Che Liu, Xiaoyu Liu, Rossella Arcucci, Zhiwei Xiong

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

2402.14000 2024-07-19 cs.CV 57%

Real-time 3D-aware Portrait Editing from a Single Image

Qingyan Bai, Zifan Shi, Yinghao Xu, Hao Ouyang, Qiuyu Wang, Ceyuan Yang, Xuan Wang, Gordon Wetzstein, Yujun Shen, Qifeng Chen

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

Comments ECCV 2024 camera-ready version. Project page: https://github.com/EzioBy/3dpe

2402.01832 2024-07-19 cs.CV cs.AI cs.LG 57%

SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?

Hasan Abed Al Kader Hammoud, Hani Itani, Fabio Pizzati, Philip Torr, Adel Bibi, Bernard Ghanem

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

Comments Under review

2312.02192 2024-07-18 cs.CV 57%

DiverseDream: Diverse Text-to-3D Synthesis with Augmented Text Embedding

Uy Dieu Tran, Minh Luu, Phong Ha Nguyen, Khoi Nguyen, Binh-Son Hua

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

Comments Accepted to ECCV 2024. Project page: https://diversedream.github.io

2407.10413 2024-07-16 cs.CV cs.AI 57%

Melon Fruit Detection and Quality Assessment Using Generative AI-Based Image Data Augmentation

Seungri Yoon, Yunseong Cho, Tae In Ahn

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

Comments 8 pages, 7 figures

2407.10102 2024-07-16 cs.CV 57%

3DEgo: 3D Editing on the Go!

Umar Khalid, Hasan Iqbal, Azib Farooq, Jing Hua, Chen Chen

专题命中文生图：diffusion(abstract)；分类 cs.CV

Comments ECCV 2024 Accepted Paper

2310.12128 2024-07-16 cs.CV cs.AI cs.CL cs.LG 57%

DiagrammerGPT: Generating Open-Domain, Open-Platform Diagrams via LLM Planning

Abhay Zala, Han Lin, Jaemin Cho, Mohit Bansal

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

Comments COLM 2024; Project page: https://diagrammerGPT.github.io/

2407.08966 2024-07-15 cs.CV cs.AI cs.LG 57%

LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models

Yabin Zhang, Wenjie Zhu, Chenhang He, Lei Zhang

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

Comments ECCV2024; Codes and Supp. are available at: https://github.com/YBZh/LAPT

2407.08674 2024-07-12 cs.CV 57%

Still-Moving: Customized Video Generation without Customized Video Data

Hila Chefer, Shiran Zada, Roni Paiss, Ariel Ephrat, Omer Tov, Michael Rubinstein, Lior Wolf, Tali Dekel, Tomer Michaeli, Inbar Mosseri

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

Comments Webpage: https://still-moving.github.io/ | Video: https://www.youtube.com/watch?v=U7UuV_VIjnA

2407.05527 2024-07-09 cs.CV cs.LG eess.IV 57%

Rethinking Image Skip Connections in StyleGAN2

Seung Park, Yong-Goo Shin

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

1. 文生图 3480 篇

CFTS-GAN: Continual Few-Shot Teacher Student for Generative Adversarial Networks

Quality Prediction of AI Generated Images and Videos: Emerging Trends and Opportunities

Unified Framework for Histopathology Image Augmentation and Classification via Generative Models

NL-Eye: Abductive NLI for Images

Removing Distributional Discrepancies in Captions Improves Image-Text Alignment

AnyPattern: Towards In-context Image Copy Detection

Training Data Attribution: Was Your Model Secretly Trained On Data Created By Mine?

Sparks of Artificial General Intelligence(AGI) in Semiconductor Material Science: Early Explorations into the Next Frontier of Generative AI-Assisted Electron Micrograph Analysis

Agglomerative Token Clustering

Manipulating and Mitigating Generative Model Biases without Retraining

Beta-Sigma VAE: Separating beta and decoder variance in Gaussian variational autoencoder

Optimizing CLIP Models for Image Retrieval with Maintained Joint-Embedding Alignment

A Survey on Responsible Generative AI: What to Generate and What Not

ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models

Uncertainty Quantification using Variational Inference for Biomedical Image Segmentation

Idea2Img: Iterative Self-Refinement with GPT-4V(ision) for Automatic Image Design and Generation

NVS-Adapter: Plug-and-Play Novel View Synthesis from a Single Image

REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language Models

Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion

Utilizing Generative Adversarial Networks for Image Data Augmentation and Classification of Semiconductor Wafer Dicing Induced Defects

BIMCV-R: A Landmark Dataset for 3D CT Text-Image Retrieval

Real-time 3D-aware Portrait Editing from a Single Image

SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?

DiverseDream: Diverse Text-to-3D Synthesis with Augmented Text Embedding

Melon Fruit Detection and Quality Assessment Using Generative AI-Based Image Data Augmentation

3DEgo: 3D Editing on the Go!

DiagrammerGPT: Generating Open-Domain, Open-Platform Diagrams via LLM Planning

LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models

Still-Moving: Customized Video Generation without Customized Video Data

Rethinking Image Skip Connections in StyleGAN2