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。

2025-09-10 至 2025-09-10 共收录 40 篇信号源：cs.CV, cs.GR, cs.MM

1. 扩散模型 29 篇

2509.07124 2025-09-10 astro-ph.GA 50%

Unveiling the Impact of Cosmic Rays on the Disc Sizes and Outflows from Dwarf Scales to Galaxy Groups

Rebekka Bieri, Rüdiger Pakmor, Freeke van de Voort, Rosie Y. Talbot, Maria Werhahn, Christoph Pfrommer, Volker Springel

专题命中扩散模型：diffusion(abstract)

2505.13791 2025-09-10 cs.LG physics.chem-ph 50%

Scalable Autoregressive 3D Molecule Generation

Austin H. Cheng, Chong Sun, Alán Aspuru-Guzik

机构 * Department of Chemistry, University of Toronto, Toronto, ON, Canada ； Department of Computer Science, University of Toronto, Toronto, ON, Canada ； Vector Institute for Artificial Intelligence, Toronto, ON, Canada ； Department of Chemistry ； Chemical Biology, Rutgers University, Piscataway, NJ, USA ； Department of Materials Science \& Engineering, University of Toronto, Toronto, ON, Canada ； Department of Chemical Engineering \& Applied Chemistry, University of Toronto, Toronto, ON, Canada ； Senior Fellow, Canadian Institute for Advanced Research (CIFAR), Toronto, ON, Canada ； NVIDIA

专题命中扩散模型：diffusion(abstract)

Comments Added link to code; corrected results on disabling data augmentation in Appendix Table 4; logit prediction uses Lin, not MLP

2509.07017 2025-09-10 cs.AI cs.CL cs.LG 50%

From Eigenmodes to Proofs: Integrating Graph Spectral Operators with Symbolic Interpretable Reasoning

Andrew Kiruluta, Priscilla Burity

机构 * Andrew Kiruluta and Priscilla Burity（独立研究者）

专题命中扩散模型：diffusion(abstract)

2. 可控生成 2 篇

2509.07809 2025-09-10 cs.CV 79%

SplatFill: 3D Scene Inpainting via Depth-Guided Gaussian Splatting

Mahtab Dahaghin, Milind G. Padalkar, Matteo Toso, Alessio Del Bue

机构 * Pattern Analysis and Computer Vision (PAVIS)（模式分析与计算机视觉（PAVIS））； Istituto Italiano di Tecnologia (IIT)（意大利技术研究所（IIT））

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

2509.07647 2025-09-10 cs.CV 57%

Semantic Watermarking Reinvented: Enhancing Robustness and Generation Quality with Fourier Integrity

Sung Ju Lee, Nam Ik Cho

机构 * Dept. of ECE & INMC, Seoul National University, Korea（电子工程系及智能纳米材料中心，首尔国立大学）

专题命中可控生成：diffusion(abstract)；分类 cs.CV

Comments Accepted to the IEEE/CVF International Conference on Computer Vision (ICCV) 2025. Project page: https://thomas11809.github.io/SFWMark/ Code: https://github.com/thomas11809/SFWMark

3. 图像修复 1 篇

2410.02423 2025-09-10 cs.CV cs.LG 57%

PnP-Flow: Plug-and-Play Image Restoration with Flow Matching

Ségolène Martin, Anne Gagneux, Paul Hagemann, Gabriele Steidl

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

4. 个性化与一致性 1 篇

2504.12574 2025-09-10 cs.CV 70%

ForgetMe: Evaluating Selective Forgetting in Generative Models

Zhenyu Yu, Mohd Yamani Inda Idris, Pei Wang

机构 * Universiti Malaya（马来亚大学）； Kunming University of Science and Technology（昆明理工大学）

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

5. 图像生成评测 1 篇

2509.07050 2025-09-10 cs.CV cs.AI cs.CY 70%

Automated Evaluation of Gender Bias Across 13 Large Multimodal Models

Juan Manuel Contreras

机构 * Aymara

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

6. 效率与蒸馏 1 篇

2506.18463 2025-09-10 cs.CV 57%

DIP: Unsupervised Dense In-Context Post-training of Visual Representations

Sophia Sirko-Galouchenko, Spyros Gidaris, Antonin Vobecky, Andrei Bursuc, Nicolas Thome

机构 * Sorbonne Université, CNRS, ISIR（索邦大学、国家科学研究中心、ISIR）； FEE CTU（捷克技术大学电子工程系）； CIIRC CTU Prague（捷克技术大学普拉格研究所）； Institut universitaire de France (IUF)（法国国家科学院）

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

Comments Accepted to ICCV 2025

7. 其他图像生成 1 篇

2509.07595 2025-09-10 cs.DC 50%

AgentX: Towards Orchestrating Robust Agentic Workflow Patterns with FaaS-hosted MCP Services

Shiva Sai Krishna Anand Tokal, Vaibhav Jha, Anand Eswaran, Praveen Jayachandran, Yogesh Simmhan

专题命中其他图像生成：image generation(abstract)