视觉与机器人

图像生成

图像生成、文生图、图像编辑、扩散模型和可控生成。

2025-10-22 至 2025-10-22 共收录 74 篇信号源：cs.CV, cs.GR, cs.MM

1. 扩散模型 60 篇

2510.09464 2025-10-22 cs.SI 50%

Cross-Platform Narrative Prediction: Leveraging Platform-Invariant Discourse Networks

Patrick Gerard, Luca Luceri, Leonardo Blas, Emilio Ferrara

专题命中扩散模型：diffusion(abstract)

Comments 13 pages, 4 figures

2. 可控生成 4 篇

2510.18716 2025-10-22 cs.CV 79%

SSD: Spatial-Semantic Head Decoupling for Efficient Autoregressive Image Generation

Siyong Jian, Huan Wang

机构 * Westlake University（西湖大学）

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

2510.18053 2025-10-22 cs.LG cs.AI 67%

Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models

Jiajun Fan, Tong Wei, Chaoran Cheng, Yuxin Chen, Ge Liu

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

专题命中可控生成：image generation(abstract)；text-to-image(abstract)

Comments 30 pages

2510.18345 2025-10-22 cs.CV 57%

GPTFace: Generative Pre-training of Facial-Linguistic Transformer by Span Masking and Weakly Correlated Text-image Data

Yudong Li, Hao Li, Xianxu Hou, Linlin Shen

机构 * Shenzhen University（深圳大学）

专题命中可控生成：inpainting(abstract)；分类 cs.CV

Comments This work was initially drafted in November 2022

2510.18366 2025-10-22 cond-mat.mtrl-sci 50%

Aqueous Preparation of CsPbBr3 Perovskite Nanocrystals Under Ambient Conditio

Zhaoyi Du, Jiewen Wei, Ding Ding, Martina Rimmele, Yueyao Dong, Weitao Qian, Davide Nodari, Francesco Furlan, Edoardo Angela, George Morgan, Peter Akinshin, William Rodriguez Kazeem, Gwilherm Kerherve, Adam V. Marsh, Martin Heeney, Thomas J. Macdonald, Saif A. Haque, Nicola Gasparini, David J. Payne, Martyn A. McLachlan

专题命中可控生成：diffusion(abstract)

3. 图像修复 3 篇

2510.18851 2025-10-22 cs.CV cs.AI 70%

DP$^2$O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution

Rongyuan Wu, Lingchen Sun, Zhengqiang Zhang, Shihao Wang, Tianhe Wu, Qiaosi Yi, Shuai Li, Lei Zhang

机构 * The Hong Kong Polytechnic University（香港理工大学）； OPPO Research Institute（OPPO研究院）； City University of Hong Kong（香港城市大学）

专题命中图像修复：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments Accept by NeurIPS 2025

2510.18773 2025-10-22 cs.CV 57%

Detection and Simulation of Urban Heat Islands Using a Fine-Tuned Geospatial Foundation Model for Microclimate Impact Prediction

Jannis Fleckenstein, David Kreismann, Tamara Rosemary Govindasamy, Thomas Brunschwiler, Etienne Vos, Mattia Rigotti

机构 * IBM Research – Europe（IBM欧洲研究院）； IBM Research – Africa（IBM非洲研究院）

专题命中图像修复：inpainting(abstract)；分类 cs.CV

Comments 10 pages, 9 figures. Accepted at the NeurIPS 2025 Workshop on Tackling Climate Change with Machine Learning

2505.14460 2025-10-22 cs.CV 57%

VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank

Tianhe Wu, Jian Zou, Jie Liang, Lei Zhang, Kede Ma

机构 * City University of Hong Kong（香港城市大学）； OPPO Research Institute（OPPO研究院）； The Hong Kong Polytechnic University（香港理工大学）

专题命中图像修复：image generation(abstract)；分类 cs.CV

4. 个性化与一致性 1 篇

2411.15277 2025-10-22 cs.CV 57%

Foundation Cures Personalization: Improving Personalized Models' Prompt Consistency via Hidden Foundation Knowledge

Yiyang Cai, Zhengkai Jiang, Yulong Liu, Chunyang Jiang, Wei Xue, Yike Guo, Wenhan Luo

机构 * Hong Kong University of Science and Technology (HKUST)（香港科技大学）； Tencent Hunyuan（腾讯文元）

专题命中个性化与一致性：diffusion(abstract)；分类 cs.CV

Comments Accepted to NeurIPS 2025

5. 图像生成评测 1 篇

2510.17626 2025-10-22 cs.CV cs.AI 57%

CaMiT: A Time-Aware Car Model Dataset for Classification and Generation

Frédéric LIN, Biruk Abere Ambaw, Adrian Popescu, Hejer Ammar, Romaric Audigier, Hervé Le Borgne

机构 * Université Paris-Saclay, CEA, List（巴黎-萨克雷大学，CEA，List）

专题命中图像生成评测：image generation(abstract)；分类 cs.CV

Comments To be published in NeurIPS 2025 Track on Datasets and Benchmarks

6. 效率与蒸馏 3 篇

2503.10103 2025-10-22 cs.CV cs.LG 79%

Improving Diffusion-based Inverse Algorithms under Few-Step Constraint via Learnable Linear Extrapolation

Jiawei Zhang, Ziyuan Liu, Leon Yan, Gen Li, Yuantao Gu

机构 * Tsinghua University（清华大学）； CUHK（香港中文大学）

专题命中效率与蒸馏：diffusion(title,abstract)；分类 cs.CV

Comments Accepted by NeurIPS 2025

2505.02048 2025-10-22 eess.IV cs.AI cs.CV 70%

Regression is all you need for medical image translation

Sebastian Rassmann, David Kügler, Christian Ewert, Martin Reuter

机构 * German Center for Neurodegenerative Diseases (DZNE)（德国神经退行性疾病研究中心）

专题命中效率与蒸馏：diffusion(abstract)；image synthesis(abstract)；分类 cs.CV

2509.02106 2025-10-22 cs.DB 50%

GeoLayer: Towards Low-Latency and Cost-Efficient Geo-Distributed Graph Stores with Layered Graph

Feng Yao, Xiaokang Yang, Shufeng Gong, Song Yu, Yanfeng Zhang, Ge Yu

专题命中效率与蒸馏：diffusion(abstract)

7. 其他图像生成 1 篇

2510.17869 2025-10-22 cs.CV 57%

GAN-based Content-Conditioned Generation of Handwritten Musical Symbols

Gerard Asbert, Pau Torras, Lei Kang, Alicia Fornés, Josep Lladós

机构 * Computer Vision Center（计算机视觉中心）； Universitat Autònoma de Barcelona（巴塞罗那自治大学）

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

Comments 15 pages, 5 figures, Accepted at ICDAR workshop GREC 2025