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。

2025-10-27 至 2025-10-27 共收录 70 篇信号源：cs.CV, cs.GR, cs.MM

1. 可控生成 4 篇

2505.21491 2025-10-27 cs.CV 57%

Frame In-N-Out: Unbounded Controllable Image-to-Video Generation

Boyang Wang, Xuweiyi Chen, Matheus Gadelha, Zezhou Cheng

机构 * University of Virginia（弗吉尼亚大学）； Adobe Research（Adobe研究）

专题命中可控生成：diffusion(abstract)；分类 cs.CV

2. 图像修复 1 篇

2510.03317 2025-10-27 cs.CV cs.AI 79%

Photorealistic Inpainting for Perturbation-based Explanations in Ecological Monitoring

Günel Aghakishiyeva, Jiayi Zhou, Saagar Arya, Julian Dale, James David Poling, Holly R. Houliston, Jamie N. Womble, Gregory D. Larsen, David W. Johnston, Brinnae Bent

机构 * Duke University（杜克大学）； University of Agder（阿格德大学）； University of Cambridge（剑桥大学）； U.S. National Park Service Department of Interior（美国国家公园管理局）； Alaska Spatial Science（阿拉斯加空间科学）

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

Comments NeurIPS 2025 Imageomics Workshop

3. 个性化与一致性 2 篇

2510.20887 2025-10-27 cs.CV cs.AI 70%

Preventing Shortcuts in Adapter Training via Providing the Shortcuts

Anujraaj Argo Goyal, Guocheng Gordon Qian, Huseyin Coskun, Aarush Gupta, Himmy Tam, Daniil Ostashev, Ju Hu, Dhritiman Sagar, Sergey Tulyakov, Kfir Aberman, Kuan-Chieh Jackson Wang

机构 * Snap Inc.

专题命中个性化与一致性：text-to-image(abstract)；image synthesis(abstract)；分类 cs.CV

Comments Accepted to NeurIPS 2025, webpage: https://snap-research.github.io/shortcut-rerouting/

2510.21696 2025-10-27 cs.CV 57%

BachVid: Training-Free Video Generation with Consistent Background and Character

Han Yan, Xibin Song, Yifu Wang, Hongdong Li, Pan Ji, Chao Ma

机构 * MoE Key Lab of Artificial, AI Institute, Shanghai Jiao Tong University（人工智能研究院，上海交通大学）； Vertex Lab（Vertex实验室）； Australian National University（澳大利亚国立大学）

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

Comments Project page: https://wolfball.github.io/bachvid

4. 图像生成评测 3 篇

2510.21120 2025-10-27 cs.CV 79%

SafetyPairs: Isolating Safety Critical Image Features with Counterfactual Image Generation

Alec Helbling, Shruti Palaskar, Kundan Krishna, Polo Chau, Leon Gatys, Joseph Yitan Cheng

机构 * Georgia Tech（佐治亚理工学院）； Apple（苹果公司）

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

2510.21542 2025-10-27 stat.ML cs.LG 50%

HollowFlow: Efficient Sample Likelihood Evaluation using Hollow Message Passing

Johann Flemming Gloy, Simon Olsson

机构 * Department of Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg（计算机科学与工程系，查尔姆斯理工大学和戈尔德堡大学）

专题命中图像生成评测：diffusion(abstract)

Comments Accepted to NeurIPS 2025

2503.02943 2025-10-27 cs.LG cs.SY eess.SY 50%

Robust time series generation via Schrödinger Bridge: a comprehensive evaluation

Alexandre Alouadi, Baptiste Barreau, Laurent Carlier, Huyên Pham

机构 * École Polytechnique & BNP PARIBAS CIB, Global Markets（巴黎高等理工学院 & 巴克莱银行CIB，全球市场部）

专题命中图像生成评测：image generation(abstract)

Comments 9 pages

5. 效率与蒸馏 3 篇

2412.17153 2025-10-27 cs.CV cs.LG 70%

Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching

Enshu Liu, Xuefei Ning, Yu Wang, Zinan Lin

专题命中效率与蒸馏：image generation(abstract)；text-to-image(abstract)；分类 cs.CV

2509.20753 2025-10-27 stat.ML cs.LG 50%

RAPTOR-GEN: RApid PosTeriOR GENerator for Bayesian Learning in Biomanufacturing

Wandi Xu, Wei Xie

机构 * Department of Mechanical and Industrial Engineering, Northeastern University（机械与工业工程系，东北大学）

专题命中效率与蒸馏：diffusion(abstract)

Comments 72 pages, 6 figures

2506.07254 2025-10-27 cs.LG 50%

A Stable Whitening Optimizer for Efficient Neural Network Training

Kevin Frans, Sergey Levine, Pieter Abbeel

机构 * UC Berkeley（伯克利大学）

专题命中效率与蒸馏：diffusion(abstract)