图像生成

BoostDream: Efficient Refining for High-Quality Text-to-3D Generation from Multi-View Diffusion

BoostDream: 高效细化用于多视角扩散模型生成高质量文本到3D生成

Yonghao Yu, Shunan Zhu, Huai Qin, Haorui Li

机构 * Waseda University（早稻田大学） ； Southeast University（东南大学） 纠错

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

AI总结 BoostDream通过高效细化方法，结合多视角SDS损失和法线图指导，实现快速生成高质量的3D资产，提升生成效率和质量。

From Structure to Detail: Hierarchical Distillation for Efficient Diffusion Model

Hanbo Cheng, Peng Wang, Kaixiang Lei, Qi Li, Zhen Zou, Pengfei Hu, Jun Du

机构 * University of Science and Technology of China（中国科学技术大学） ； ByteDance China（字节跳动中国） 纠错

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

DetailFlow: 1D Coarse-to-Fine Autoregressive Image Generation via Next-Detail Prediction

Yiheng Liu, Liao Qu, Huichao Zhang, Xu Wang, Yi Jiang, Yiming Gao, Hu Ye, Xian Li, Shuai Wang, Daniel K. Du, Fangmin Chen, Zehuan Yuan, Xinglong Wu

机构 * ByteDance Inc.（字节跳动公司） 纠错

专题命中 效率与蒸馏 ：image generation(title,abstract)；image synthesis(abstract)；分类 cs.CV

DiffusionX: Efficient Edge-Cloud Collaborative Image Generation with Multi-Round Prompt Evolution

Yi Wei, Shunpu Tang, Liang Zhao, Qiangian Yang

机构 * College of Information Science（信息科学学院） ； Electronic Engineering, Zhejiang University, Hangzhou, China（电子工程，浙江大学，杭州，中国） 纠错

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

CLQ: Cross-Layer Guided Orthogonal-based Quantization for Diffusion Transformers

Kai Liu, Shaoqiu Zhang, Linghe Kong, Yulun Zhang

机构 * Shanghai Jiao Tong University（上海交通大学） 纠错

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

Comments 10 pages, 5 figures. Code is released at https://github.com/Kai-Liu001/CLQ

Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling

Huangjie Zheng, Zhendong Wang, Jianbo Yuan, Guanghan Ning, Pengcheng He, Quanzeng You, Hongxia Yang, Mingyuan Zhou

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校） ； ByteDance Inc.（字节跳动公司） ； Microsoft Azure AI（微软Azure人工智能） 纠错

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

UltraVSR: Achieving Ultra-Realistic Video Super-Resolution with Efficient One-Step Diffusion Space

Yong Liu, Jinshan Pan, Yinchuan Li, Qingji Dong, Chao Zhu, Yu Guo, Fei Wang

机构 * Xi'an Jiaotong University（西安交通大学） ； Nanjing University of Science and Technology（南京理工大学） ； Huawei Noah's Ark Lab（华为诺亚实验室） 纠错

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

Comments ACM Multimedia 2025

Frequency-Aware Autoregressive Modeling for Efficient High-Resolution Image Synthesis

Zhuokun Chen, Jugang Fan, Zhuowei Yu, Bohan Zhuang, Mingkui Tan

机构 * South China University of Technology（华南理工大学） ； Pazhou Lab（帕乔实验室） ； University of California, Davis（加州大学戴维斯分校） ； Zhejiang University（浙江大学） 纠错

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

Parameter-Efficient Fine-Tuning of 3D DDPM for MRI Image Generation Using Tensor Networks

Binghua Li, Ziqing Chang, Tong Liang, Chao Li, Toshihisa Tanaka, Shigeki Aoki, Qibin Zhao, Zhe Sun

机构 * Tokyo University of Agriculture（东京农业大学） ； Technology（技术） ； Juntendo University（立命馆大学） ； RIKEN Center for Advanced Intelligence Project（理化学研究所先进情报项目中心） 纠错

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

QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning

Haoxuan Wang, Yuzhang Shang, Zhihang Yuan, Junyi Wu, Junchi Yan, Yan Yan

机构 * University of Illinois Chicago（伊利诺伊大学芝加哥分校） ； University of Central Florida（中央佛罗里达大学） ； Shanghai Jiao Tong University（上海交通大学） ； Houmo AI 纠错

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

Comments ICCV 2025. Code is available at https://github.com/hatchetProject/QuEST

Temporal Feature Matters: A Framework for Diffusion Model Quantization

Yushi Huang, Ruihao Gong, Xianglong Liu, Jing Liu, Yuhang Li, Jiwen Lu, Dacheng Tao

机构 * Department of Electrical and Computer Engineering, the Hong Kong University of Science and Technology（香港科技大学电子与计算机工程系） ； State Key Laboratory of Complex & Critical Software Environment, Beihang University（北京航空航天大学复杂与关键软件环境国家重点实验室） ； Department of Information Technology, Monash University（墨尔本大学信息科技系） ； Department of Electrical Engineering, Yale University（耶鲁大学电子工程系） 纠错

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

Comments Accepted by TPAMI 2025. arXiv admin note: substantial text overlap with arXiv:2311.16503

PQCAD-DM: Progressive Quantization and Calibration-Assisted Distillation for Extremely Efficient Diffusion Model

Beomseok Ko, Hyeryung Jang

机构 * Department of Computer Science & Artificial Intelligence, Dongguk University（计算机科学与人工智能系，东国大学） 纠错

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

Comments 10 pages, 6 figures

Flexiffusion: Training-Free Segment-Wise Neural Architecture Search for Efficient Diffusion Models

Hongtao Huang, Xiaojun Chang, Lina Yao

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

Comments This paper was intended to be a v2 version of my previous paper (arXiv:2409.17566), but it was submitted as a new paper by mistake

Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferences

Weijian Luo

机构 * Peking University（北京大学） 纠错

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

Comments Revision: The paper was accepted by Transactions of Machine Learning Research (TMLR)

TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution

Linwei Dong, Qingnan Fan, Yihong Guo, Zhonghao Wang, Qi Zhang, Jinwei Chen, Yawei Luo, Changqing Zou

机构 * Zhejiang University（浙江大学） ； Vivo Mobile Communication Co. Ltd（Vivo移动通信有限公司） ； University of Chinese Academy of Sciences（中国科学院大学） ； Zhejiang Lab（浙江实验室） 纠错

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

Diffusion Sampling Path Tells More: An Efficient Plug-and-Play Strategy for Sample Filtering

Sixian Wang, Zhiwei Tang, Tsung-Hui Chang

机构 * School of Science and Engineering（科学与工程学院） ； The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； DAMO Academy, Alibaba Group（阿里达摩院） ； School of Artificial Intelligence（人工智能学院） 纠错

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

Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers

Weilun Feng, Chuanguang Yang, Haotong Qin, Xiangqi Li, Yu Wang, Zhulin An, Libo Huang, Boyu Diao, Zixiang Zhao, Yongjun Xu, Michele Magno

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

Comments Accepted to ICML2025

Mean-Shift Distillation for Diffusion Mode Seeking

Vikas Thamizharasan, Nikitas Chatzis, Iliyan Georgiev, Matthew Fisher, Evangelos Kalogerakis, Difan Liu, Nanxuan Zhao, Michal Lukac

专题命中 效率与蒸馏 ：diffusion(title,abstract)；text-to-image(abstract)；分类 cs.GR

Comments 15 pages, 9 figures

Taming Diffusion for Dataset Distillation with High Representativeness

Lin Zhao, Yushu Wu, Xinru Jiang, Jianyang Gu, Yanzhi Wang, Xiaolin Xu, Pu Zhao, Xue Lin

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

Comments The paper is accepted by ICML 2025

Few-Step Diffusion via Score identity Distillation

Mingyuan Zhou, Yi Gu, Zhendong Wang

机构 * UT Austin（德克萨斯大学奥斯汀分校） ； Google（谷歌） ； Google DeepMind（谷歌DeepMind） ； Microsoft（微软） 纠错

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

Diffusion Model Quantization: A Review

Qian Zeng, Chenggong Hu, Mingli Song, Jie Song

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

Comments 40 pages, 8 figures

Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data

Asad Aali, Giannis Daras, Brett Levac, Sidharth Kumar, Alexandros G. Dimakis, Jonathan I. Tamir

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

Journal ref ICLR, 2025

DMM: Building a Versatile Image Generation Model via Distillation-Based Model Merging

Tianhui Song, Weixin Feng, Shuai Wang, Xubin Li, Tiezheng Ge, Bo Zheng, Limin Wang

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

Autoregressive Distillation of Diffusion Transformers

Yeongmin Kim, Sotiris Anagnostidis, Yuming Du, Edgar Schönfeld, Jonas Kohler, Markos Georgopoulos, Albert Pumarola, Ali Thabet, Artsiom Sanakoyeu

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

Comments CVPR 2025 Oral

Training-free Diffusion Acceleration with Bottleneck Sampling

Ye Tian, Xin Xia, Yuxi Ren, Shanchuan Lin, Xing Wang, Xuefeng Xiao, Yunhai Tong, Ling Yang, Bin Cui

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

Comments Project Page: https://tyfeld.github.io/BottleneckSampling.github.io/

LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization

Xianfeng Wu, Yajing Bai, Haoze Zheng, Harold Haodong Chen, Yexin Liu, Zihao Wang, Xuran Ma, Wen-Jie Shu, Xianzu Wu, Harry Yang, Ser-Nam Lim

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

Comments Code: https://github.com/XianfengWu01/LightGen

TR-DQ: Time-Rotation Diffusion Quantization

Yihua Shao, Deyang Lin, Fanhu Zeng, Minxi Yan, Muyang Zhang, Siyu Chen, Yuxuan Fan, Ziyang Yan, Haozhe Wang, Jingcai Guo, Yan Wang, Haotong Qin, Hao Tang

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

PostEdit: Posterior Sampling for Efficient Zero-Shot Image Editing

Feng Tian, Yixuan Li, Yichao Yan, Shanyan Guan, Yanhao Ge, Xiaokang Yang

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

Comments 31 pages

Journal ref ICLR 2025

Q&C: When Quantization Meets Cache in Efficient Image Generation

Xin Ding, Xin Li, Haotong Qin, Zhibo Chen

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

Comments 11 pages

FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Sampling

Zhengqiang Zhang, Ruihuang Li, Lei Zhang

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