图像生成

Spanning the Visual Analogy Space with a Weight Basis of LoRAs

通过LoRAs的权重基来跨越视觉类比空间

Hila Manor, Rinon Gal, Haggai Maron, Tomer Michaeli, Gal Chechik

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

AI总结 本文提出LoRWeB，通过在单次推理中为每个类比任务专门化模型，动态组合学习的变换原语，以提升视觉类比学习的泛化能力。

Comments Accepted to ECCV 2026; Code and data are in https://research.nvidia.com/labs/par/lorweb

Echo-Memory: A Controlled Study of Memory in Action World Models

Echo-Memory：动作世界模型中记忆的受控研究

Wayne King, Zeyue Xue, Yuxuan Bian, Jie Huang, Haoran Li, Yaowei Li, Yaofeng Su, Yuming Li, Haoyu Wang, Shiyi Zhang, Songchun Zhang, Yuwei Niu, Sihan Xu, Junhao Zhuang, Haoyang Huang, Nan Duan

机构 * Joy Future Academy（京东探索研究院） 纠错

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

AI总结 提出Echo-Memory框架，通过控制变量法研究动作条件世界模型中的记忆机制，发现原始上下文容量和块状状态空间递归对开放域返回任务至关重要。

Comments 9 figures and 28 pages, Code at \href{https://github.com/Echo-Team-Joy-Future-Academy-JD/Echo-Memory}{this URL}

JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation

JavisDiT++：联合音频视频生成的统一建模与优化

Kai Liu, Yanhao Zheng, Kai Wang, Shengqiong Wu, Rongjunchen Zhang, Jiebo Luo, Dimitrios Hatzinakos, Ziwei Liu, Hao Fei, Tat-Seng Chua

机构 * Zhejiang University（浙江大学） ； National University of Singapore（新加坡国立大学） ； University of Toronto（多伦多大学） ； HiThink Research（HiThink研究） ； University of Rochester（罗切斯特大学） ； Nanyang Technological University（南洋理工大学） 纠错

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

AI总结 JavisDiT++通过统一建模与优化方法，在联合音频视频生成任务中实现高质量的同步与语义对齐。

Comments Accepted by ICLR 2026. Homepage: https://JavisVerse.github.io/JavisDiT2-page

VIVAT: Virtuous Improving VAE Training through Artifact Mitigation

VIVAT: 通过抑制伪影改进VAE训练

Lev Novitskiy, Viacheslav Vasilev, Maria Kovaleva, Vladimir Arkhipkin, Denis Dimitrov

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

AI总结 VIVAT通过抑制VAE训练中的常见伪影，提升图像重建和生成质量，实现更优的PSNR、SSIM和CLIP分数表现。

Co-Reinforcement Learning for Unified Multimodal Understanding and Generation

协同强化学习用于统一多模态理解和生成

Jingjing Jiang, Chongjie Si, Jun Luo, Hanwang Zhang, Chao Ma

机构 * Shanghai Jiao Tong University（上海交通大学） ； Nanyang Technological University（南洋理工大学） 纠错

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

AI总结 本文提出CoRL框架，通过协同强化学习提升多模态大语言模型在生成与理解任务上的性能。

Comments NeurIPS 2025

Enhancing Multimodal Misinformation Detection by Replaying the Whole Story from Image Modality Perspective

Bing Wang, Ximing Li, Yanjun Wang, Changchun Li, Lin Yuanbo Wu, Buyu Wang, Shengsheng Wang

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

Comments Accepted by AAAI 2026. 13 pages, 6 figures. Code: https://github.com/wangbing1416/RETSIMD

T2IW: Joint Text to Image & Watermark Generation

An-An Liu, Guokai Zhang, Yuting Su, Ning Xu, Yongdong Zhang, Lanjun Wang

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

Journal ref Machine Intelligence Research, 2025

PartComposer: Learning and Composing Part-Level Concepts from Single-Image Examples

Junyu Liu, R. Kenny Jones, Daniel Ritchie

机构 * Brown University（布朗大学） ； Stanford University（斯坦福大学） 纠错

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

BloomScene: Lightweight Structured 3D Gaussian Splatting for Crossmodal Scene Generation

Xiaolu Hou, Mingcheng Li, Dingkang Yang, Jiawei Chen, Ziyun Qian, Xiao Zhao, Yue Jiang, Jinjie Wei, Qingyao Xu, Lihua Zhang

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

Comments Accepted by AAAI 2025. Code: https://github.com/SparklingH/BloomScene

One Framework to Rule Them All: Unifying Multimodal Tasks with LLM Neural-Tuning

Hao Sun, Yu Song, Jiaqing Liu, Jihong Hu, Yen-Wei Chen, Lanfen Lin

机构 * College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院） ； College of Information Science and Engineering, Ritsumeikan University（立命馆大学信息科学与工程学院） 纠错

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

Learning Latent Representations for Image Translation using Frequency Distributed CycleGAN

Shivangi Nigam, Adarsh Prasad Behera, Shekhar Verma, P. Nagabhushan

机构 * Department of Information Technology, Indian Institute of Information Technology, Allahabad, U.P.（信息科技系，印度信息技术研究所，阿勒普尔，乌塔兰邦） ； KTH Royal Institute of Technology（皇家理工学院） ； Department of Computer Science and Engineering, Vignan University, Guntur, Andhra Pradesh（计算机科学与工程系，维加恩大学，古特尔，安得拉邦） 纠错

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

Comments This paper is currently under review for publication in an IEEE Transactions. If accepted, the copyright will be transferred to IEEE

MatSwap: Light-aware material transfers in images

Ivan Lopes, Valentin Deschaintre, Yannick Hold-Geoffroy, Raoul de Charette

机构 * Inria（法国国家信息与自动化技术研究所） ； Adobe Research（Adobe研究院） 纠错

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

Comments Accepted to EGSR, journal track to appear in Computer Graphics Forum

Towards Explainable Partial-AIGC Image Quality Assessment

Jiaying Qian, Ziheng Jia, Zicheng Zhang, Zeyu Zhang, Guangtao Zhai, Xiongkuo Min

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

Images that Sound: Composing Images and Sounds on a Single Canvas

Ziyang Chen, Daniel Geng, Andrew Owens

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

Comments Accepted to NeurIPS 2024. Project site: https://ificl.github.io/images-that-sound/

Natural Language Induced Adversarial Images

Xiaopei Zhu, Peiyang Xu, Guanning Zeng, Yingpeng Dong, Xiaolin Hu

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

Comments Carmera-ready version. To appear in ACM MM 2024

HoloDreamer: Holistic 3D Panoramic World Generation from Text Descriptions

Haiyang Zhou, Xinhua Cheng, Wangbo Yu, Yonghong Tian, Li Yuan

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

Comments Homepage: https://zhouhyocean.github.io/holodreamer

GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs

Gege Gao, Weiyang Liu, Anpei Chen, Andreas Geiger, Bernhard Schölkopf

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

Comments CVPR 2024 (18 pages, 11 figures, https://graphdreamer.github.io/)

Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images

Roberto Amoroso, Davide Morelli, Marcella Cornia, Lorenzo Baraldi, Alberto Del Bimbo, Rita Cucchiara

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

Comments ACM Transactions on Multimedia Computing, Communications and Applications (2024)

Language Models as Black-Box Optimizers for Vision-Language Models

Shihong Liu, Zhiqiu Lin, Samuel Yu, Ryan Lee, Tiffany Ling, Deepak Pathak, Deva Ramanan

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

Comments Published at CVPR 2024. Project site: https://llm-can-optimize-vlm.github.io/

Break-A-Scene: Extracting Multiple Concepts from a Single Image

Omri Avrahami, Kfir Aberman, Ohad Fried, Daniel Cohen-Or, Dani Lischinski

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

Comments SIGGRAPH Asia 2023. Project page: at: https://omriavrahami.com/break-a-scene/ Video: https://www.youtube.com/watch?v=-9EA-BhizgM

Unrolling Virtual Worlds for Immersive Experiences

Alexey Tikhonov, Anton Repushko

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

Comments Accepted for NeurIPS 2023 Workshop on Machine Learning for Creativity and Design

Breathing New Life into 3D Assets with Generative Repainting

Tianfu Wang, Menelaos Kanakis, Konrad Schindler, Luc Van Gool, Anton Obukhov

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

TeCH: Text-guided Reconstruction of Lifelike Clothed Humans

Yangyi Huang, Hongwei Yi, Yuliang Xiu, Tingting Liao, Jiaxiang Tang, Deng Cai, Justus Thies

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

Comments Project: https://huangyangyi.github.io/TeCH, Code: https://github.com/huangyangyi/TeCH

DiffSynth: Latent In-Iteration Deflickering for Realistic Video Synthesis

Zhongjie Duan, Lizhou You, Chengyu Wang, Cen Chen, Ziheng Wu, Weining Qian, Jun Huang

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

Comments 9 pages, 6 figures

Image Vectorization: a Review

Maria Dziuba, Ivan Jarsky, Valeria Efimova, Andrey Filchenkov

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

IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers

Ronghuan Wu, Wanchao Su, Kede Ma, Jing Liao

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

Comments Project Page: https://icon-shop.github.io/

Vision + Language Applications: A Survey

Yutong Zhou, Nobutaka Shimada

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

Comments Accepted by GCV @CVPR2023

IIITD-20K: Dense captioning for Text-Image ReID

A V Subramanyam, Niranjan Sundararajan, Vibhu Dubey, Brejesh Lall

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

ELODIN: Naming Concepts in Embedding Spaces

Rodrigo Mello, Filipe Calegario, Geber Ramalho

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

Comments Added quantitative data, fixed formatting issues

Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions

Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency

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