图像生成 - arXivDaily 专题

2410.05116 2025-03-14 cs.LG cs.AI cs.CV cs.HC 83%

HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning

Ayano Hiranaka, Shang-Fu Chen, Chieh-Hsin Lai, Dongjun Kim, Naoki Murata, Takashi Shibuya, Wei-Hsiang Liao, Shao-Hua Sun, Yuki Mitsufuji

专题命中扩散模型：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

Comments Published in International Conference on Learning Representations (ICLR) 2025

2503.09491 2025-03-13 cs.CV eess.IV 83%

DAMM-Diffusion: Learning Divergence-Aware Multi-Modal Diffusion Model for Nanoparticles Distribution Prediction

Junjie Zhou, Shouju Wang, Yuxia Tang, Qi Zhu, Daoqiang Zhang, Wei Shao

专题命中扩散模型：diffusion(title,abstract)；image synthesis(abstract)；分类 cs.CV

Comments Accepted by CVPR 2025

2502.16965 2025-03-13 cs.CV 83%

Autoregressive Image Generation with Vision Full-view Prompt

Miaomiao Cai, Guanjie Wang, Wei Li, Zhijun Tu, Hanting Chen, Shaohui Lin, Jie Hu

专题命中扩散模型：image generation(title,abstract)；diffusion(abstract)；分类 cs.CV

2503.08729 2025-03-13 cs.CV cs.AI cs.LG 83%

Preserving Product Fidelity in Large Scale Image Recontextualization with Diffusion Models

Ishaan Malhi, Praneet Dutta, Ellie Talius, Sally Ma, Brendan Driscoll, Krista Holden, Garima Pruthi, Arunachalam Narayanaswamy

专题命中扩散模型：diffusion(title,abstract)；text-to-image(abstract)；分类 cs.CV

2503.08339 2025-03-12 cs.CV 83%

Diffusion Transformer Meets Random Masks: An Advanced PET Reconstruction Framework

Bin Huang, Binzhong He, Yanhan Chen, Zhili Liu, Xinyue Wang, Binxuan Li, Qiegen Liu

专题命中扩散模型：diffusion(title,abstract)；inpainting(abstract)；分类 cs.CV

2503.08253 2025-03-12 cs.CV 83%

SARA: Structural and Adversarial Representation Alignment for Training-efficient Diffusion Models

Hesen Chen, Junyan Wang, Zhiyu Tan, Hao Li

专题命中扩散模型：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

Comments Technical report

2501.12382 2025-03-12 cs.CV 83%

DiffDoctor: Diagnosing Image Diffusion Models Before Treating

Yiyang Wang, Xi Chen, Xiaogang Xu, Sihui Ji, Yu Liu, Yujun Shen, Hengshuang Zhao

专题命中扩散模型：diffusion(title,abstract)；text-to-image(abstract)；分类 cs.CV

Comments 8 pages of main body

2411.17017 2025-03-12 cs.CV 83%

TED-VITON: Transformer-Empowered Diffusion Models for Virtual Try-On

Zhenchen Wan, Yanwu Xu, Zhaoqing Wang, Feng Liu, Tongliang Liu, Mingming Gong

专题命中扩散模型：diffusion(title,abstract)；text-to-image(abstract)；分类 cs.CV

Comments Project page: https://github.com/ZhenchenWan/TED-VITON

2410.21826 2025-03-12 cs.CV 83%

Volumetric Conditioning Module to Control Pretrained Diffusion Models for 3D Medical Images

Suhyun Ahn, Wonjung Park, Jihoon Cho, Seunghyuck Park, Jinah Park

专题命中扩散模型：diffusion(title,abstract)；image synthesis(abstract)；分类 cs.CV

Comments 17 pages, 18 figures, accepted @ WACV 2025

Journal ref Proceedings of the Winter Conference on Applications of Computer Vision (WACV), pp. 85-95, Feb. 2025

2410.07659 2025-03-12 cs.CV 83%

MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion

Onkar Susladkar, Jishu Sen Gupta, Chirag Sehgal, Sparsh Mittal, Rekha Singhal

专题命中扩散模型：diffusion(title,abstract)；inpainting(abstract)；分类 cs.CV

Comments Accepted in ICLR 2025 (spotlight paper)

2503.06746 2025-03-11 cs.CV 83%

Color Alignment in Diffusion

Ka Chun Shum, Binh-Son Hua, Duc Thanh Nguyen, Sai-Kit Yeung

专题命中扩散模型：diffusion(title,abstract)；image synthesis(abstract)；分类 cs.CV

Comments CVPR 2025

2412.21044 2025-03-11 cs.CV 83%

E2ED^2:Direct Mapping from Noise to Data for Enhanced Diffusion Models

Zhiyu Tan, WenXu Qian, Hesen Chen, Mengping Yang, Lei Chen, Hao Li

专题命中扩散模型：diffusion(title,abstract)；image synthesis(abstract)；分类 cs.CV

Comments Technical report

2408.09151 2025-03-11 cs.CV eess.IV 83%

Timestep-Aware Diffusion Model for Extreme Image Rescaling

Ce Wang, Zhenyu Hu, Wanjie Sun, Zhenzhong Chen

专题命中扩散模型：diffusion(title,abstract)；text-to-image(abstract)；分类 cs.CV

2503.05595 2025-03-10 cs.CV 83%

Anti-Diffusion: Preventing Abuse of Modifications of Diffusion-Based Models

Zheng Li, Liangbin Xie, Jiantao Zhou, Xintao Wang, Haiwei Wu, Jinyu Tian

专题命中扩散模型：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

2503.04871 2025-03-10 cs.CV cs.LG eess.IV 83%

Toward Lightweight and Fast Decoders for Diffusion Models in Image and Video Generation

Alexey Buzovkin, Evgeny Shilov

专题命中扩散模型：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

Comments 11 pages, 8 figures, 3 tables

2412.00156 2025-03-10 cs.CV cs.AI cs.LG stat.ML 83%

VISION-XL: High Definition Video Inverse Problem Solver using Latent Image Diffusion Models

Taesung Kwon, Jong Chul Ye

专题命中扩散模型：diffusion(title,abstract)；inpainting(abstract)；分类 cs.CV

Comments Project page: https://vision-xl.github.io/

2503.03944 2025-03-07 cs.CV 83%

GuardDoor: Safeguarding Against Malicious Diffusion Editing via Protective Backdoors

Yaopei Zeng, Yuanpu Cao, Lu Lin

专题命中扩散模型：diffusion(title,abstract)；image editing(abstract)；分类 cs.CV

2503.03090 2025-03-06 cs.GR 83%

From Architectural Sketch to Conceptual Representation: Using Structure-Aware Diffusion Model to Generate Renderings of School Buildings

Zhengyang Wang, Hao Jin, Xusheng Du, Yuxiao Ren, Ye Zhang, Haoran Xie

专题命中扩散模型：diffusion(title,abstract)；image generation(abstract)；分类 cs.GR

Comments 10 pages, 5 figures, in Proceedings of CAADRIA 2025

2503.02577 2025-03-05 cs.CV 83%

SPG: Improving Motion Diffusion by Smooth Perturbation Guidance

Boseong Jeon

专题命中扩散模型：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

2502.19754 2025-03-05 cs.CV 83%

Finding Local Diffusion Schrödinger Bridge using Kolmogorov-Arnold Network

Xingyu Qiu, Mengying Yang, Xinghua Ma, Fanding Li, Dong Liang, Gongning Luo, Wei Wang, Kuanquan Wang, Shuo Li

专题命中扩散模型：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

Comments 16 pages, 10 figures, accepted by CVPR 2025

2501.08180 2025-03-05 cs.CV cs.LG 83%

D$^2$-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models

Qian Zeng, Jie Song, Han Zheng, Hao Jiang, Mingli Song

专题命中扩散模型：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

Comments 9 pages, 4 figures, acceptted by AAAI2025, the code is available at https://github.com/taylorjocelyn/d2-dpm

2410.05591 2025-03-05 cs.CV 83%

TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation

Gihyun Kwon, Jong Chul Ye

专题命中扩散模型：diffusion(title,abstract)；text-to-image(abstract)；分类 cs.CV

Comments Github Page: https://github.com/KwonGihyun/TweedieMix

2311.14028 2025-03-05 cs.LG cs.AI cs.CV 83%

Continual Learning of Diffusion Models with Generative Distillation

Sergi Masip, Pau Rodriguez, Tinne Tuytelaars, Gido M. van de Ven

专题命中扩散模型：diffusion(title,abstract)；image synthesis(abstract)；分类 cs.CV

Comments To appear in the Proceedings of the Third Conference on Lifelong Learning Agents (CoLLAs), 2024

Journal ref Proceedings of The 3rd Conference on Lifelong Learning Agents, PMLR 274: 431-456, 2025

2503.01323 2025-03-04 cs.CV cs.AI 83%

CacheQuant: Comprehensively Accelerated Diffusion Models

Xuewen Liu, Zhikai Li, Qingyi Gu

专题命中扩散模型：diffusion(title,abstract)；image synthesis(abstract)；分类 cs.CV

Comments CVPR 2025

2410.03190 2025-03-04 cs.CV 83%

Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization

Zichen Miao, Zhengyuan Yang, Kevin Lin, Ze Wang, Zicheng Liu, Lijuan Wang, Qiang Qiu

专题命中扩散模型：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

2409.11219 2025-03-04 cs.CV cs.LG 83%

Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models

Tianqi Chen, Shujian Zhang, Mingyuan Zhou

专题命中扩散模型：diffusion(title,abstract)；text-to-image(abstract)；分类 cs.CV

Comments ICLR 2025

2503.00266 2025-03-04 cs.CV eess.IV 83%

Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Quality

Milad Yazdani, Yasamin Medghalchi, Pooria Ashrafian, Ilker Hacihaliloglu, Dena Shahriari

专题命中扩散模型：image synthesis(title)；image generation(abstract)；diffusion(abstract)；分类 cs.CV

2501.15878 2025-03-04 cs.CV cs.LG 83%

Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation

Adil Kaan Akan, Yucel Yemez

专题命中扩散模型：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

Comments Accepted to ICLR2025. Project page: https://kaanakan.github.io/SlotAdapt/

2409.20164 2025-03-04 cs.CV 83%

Erase, then Redraw: A Novel Data Augmentation Approach for Free Space Detection Using Diffusion Model

Fulong Ma, Weiqing Qi, Guoyang Zhao, Ming Liu, Jun Ma

专题命中扩散模型：diffusion(title,abstract)；text-to-image(abstract)；分类 cs.CV

2502.20679 2025-03-03 cs.CV 83%

Diffusion Restoration Adapter for Real-World Image Restoration

Hanbang Liang, Zhen Wang, Weihui Deng

专题命中扩散模型：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

1. 扩散模型 69989 篇

HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning

DAMM-Diffusion: Learning Divergence-Aware Multi-Modal Diffusion Model for Nanoparticles Distribution Prediction

Autoregressive Image Generation with Vision Full-view Prompt

Preserving Product Fidelity in Large Scale Image Recontextualization with Diffusion Models

Diffusion Transformer Meets Random Masks: An Advanced PET Reconstruction Framework

SARA: Structural and Adversarial Representation Alignment for Training-efficient Diffusion Models

DiffDoctor: Diagnosing Image Diffusion Models Before Treating

TED-VITON: Transformer-Empowered Diffusion Models for Virtual Try-On

Volumetric Conditioning Module to Control Pretrained Diffusion Models for 3D Medical Images

MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion

Color Alignment in Diffusion

E2ED^2:Direct Mapping from Noise to Data for Enhanced Diffusion Models

Timestep-Aware Diffusion Model for Extreme Image Rescaling

Anti-Diffusion: Preventing Abuse of Modifications of Diffusion-Based Models

Toward Lightweight and Fast Decoders for Diffusion Models in Image and Video Generation

VISION-XL: High Definition Video Inverse Problem Solver using Latent Image Diffusion Models

GuardDoor: Safeguarding Against Malicious Diffusion Editing via Protective Backdoors

From Architectural Sketch to Conceptual Representation: Using Structure-Aware Diffusion Model to Generate Renderings of School Buildings

SPG: Improving Motion Diffusion by Smooth Perturbation Guidance

Finding Local Diffusion Schrödinger Bridge using Kolmogorov-Arnold Network

D$^2$-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models

TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation

Continual Learning of Diffusion Models with Generative Distillation

CacheQuant: Comprehensively Accelerated Diffusion Models

Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization

Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models

Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Quality

Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation

Erase, then Redraw: A Novel Data Augmentation Approach for Free Space Detection Using Diffusion Model

Diffusion Restoration Adapter for Real-World Image Restoration