图像生成 - arXivDaily 专题

2404.04478 2024-04-09 cs.CV 83%

Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models

Zhengcong Fei, Mingyuan Fan, Changqian Yu, Debang Li, Junshi Huang

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

2404.04356 2024-04-09 cs.LG cs.CV 83%

Pixel-wise RL on Diffusion Models: Reinforcement Learning from Rich Feedback

Mo Kordzanganeh, Danial Keshvary, Nariman Arian

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

Comments 6 pages, 7 figures

2310.20092 2024-04-08 cs.LG cs.CV 83%

The Missing U for Efficient Diffusion Models

Sergio Calvo-Ordonez, Chun-Wun Cheng, Jiahao Huang, Lipei Zhang, Guang Yang, Carola-Bibiane Schonlieb, Angelica I Aviles-Rivero

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

Comments 23 pages, 14 figures, Accepted at Transactions of Machine Learning Research (04/2024)

2311.18832 2024-04-04 cs.CV 83%

Exploiting Diffusion Prior for Generalizable Dense Prediction

Hsin-Ying Lee, Hung-Yu Tseng, Hsin-Ying Lee, Ming-Hsuan Yang

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

Comments To appear in CVPR 2024. Project page: https://shinying.github.io/dmp

2311.17919 2024-04-04 cs.CV 83%

Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models

Daniel Geng, Inbum Park, Andrew Owens

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

Comments CVPR 2024 camera ready

2404.01424 2024-04-03 cs.CV 83%

DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery

Yixuan Zhu, Ao Li, Yansong Tang, Wenliang Zhao, Jie Zhou, Jiwen Lu

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

Comments Accepted by IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024

2404.01292 2024-04-02 cs.CV cs.LG 83%

Measuring Style Similarity in Diffusion Models

Gowthami Somepalli, Anubhav Gupta, Kamal Gupta, Shramay Palta, Micah Goldblum, Jonas Geiping, Abhinav Shrivastava, Tom Goldstein

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

2404.01051 2024-04-02 cs.CV 83%

Action Detection via an Image Diffusion Process

Lin Geng Foo, Tianjiao Li, Hossein Rahmani, Jun Liu

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

Comments Accepted to CVPR 2024

2212.00210 2024-04-02 cs.CV cs.AI cs.LG 83%

Shape-Guided Diffusion with Inside-Outside Attention

Dong Huk Park, Grace Luo, Clayton Toste, Samaneh Azadi, Xihui Liu, Maka Karalashvili, Anna Rohrbach, Trevor Darrell

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

Comments WACV 2024

2403.20249 2024-04-01 cs.CV 83%

Relation Rectification in Diffusion Model

Yinwei Wu, Xingyi Yang, Xinchao Wang

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

2403.19164 2024-03-29 cs.CV 83%

RecDiffusion: Rectangling for Image Stitching with Diffusion Models

Tianhao Zhou, Haipeng Li, Ziyi Wang, Ao Luo, Chen-Lin Zhang, Jiajun Li, Bing Zeng, Shuaicheng Liu

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

2403.18471 2024-03-28 cs.CV 83%

DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery Analysis

Zhongxi Chen, Ke Sun, Ziyin Zhou, Xianming Lin, Xiaoshuai Sun, Liujuan Cao, Rongrong Ji

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

2401.17879 2024-03-28 cs.CV 83%

AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error

Jonas Ricker, Denis Lukovnikov, Asja Fischer

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

Comments Accepted to CVPR 2024

2303.05656 2024-03-26 cs.LG cs.CV 83%

EHRDiff: Exploring Realistic EHR Synthesis with Diffusion Models

Hongyi Yuan, Songchi Zhou, Sheng Yu

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

Comments Accepted by TMLR, preprint of camera-ready version

2403.14440 2024-03-25 eess.IV cs.AI cs.CV cs.LG 83%

Analysing Diffusion Segmentation for Medical Images

Mathias Öttl, Siyuan Mei, Frauke Wilm, Jana Steenpass, Matthias Rübner, Arndt Hartmann, Matthias Beckmann, Peter Fasching, Andreas Maier, Ramona Erber, Katharina Breininger

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

2403.13408 2024-03-25 cs.CV cs.AI 83%

S2DM: Sector-Shaped Diffusion Models for Video Generation

Haoran Lang, Yuxuan Ge, Zheng Tian

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

Comments 17 pages, 6 figures

2308.13712 2024-03-25 cs.CV cs.LG 83%

Residual Denoising Diffusion Models

Jiawei Liu, Qiang Wang, Huijie Fan, Yinong Wang, Yandong Tang, Liangqiong Qu

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

Comments Accepted to CVPR2024

2403.14429 2024-03-22 cs.CV cs.AI cs.LG 83%

Style-Extracting Diffusion Models for Semi-Supervised Histopathology Segmentation

Mathias Öttl, Frauke Wilm, Jana Steenpass, Jingna Qiu, Matthias Rübner, Arndt Hartmann, Matthias Beckmann, Peter Fasching, Andreas Maier, Ramona Erber, Bernhard Kainz, Katharina Breininger

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

2403.14070 2024-03-22 eess.IV cs.CV physics.med-ph 83%

QSMDiff: Unsupervised 3D Diffusion Models for Quantitative Susceptibility Mapping

Zhuang Xiong, Wei Jiang, Yang Gao, Feng Liu, Hongfu Sun

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

2311.15980 2024-03-22 cs.CV 83%

Direct2.5: Diverse Text-to-3D Generation via Multi-view 2.5D Diffusion

Yuanxun Lu, Jingyang Zhang, Shiwei Li, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan, Xun Cao, Yao Yao

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

Comments CVPR 2024 camera ready, including more evaluations and discussions. Project webpage: https://nju-3dv.github.io/projects/direct25

2312.02696 2024-03-21 cs.CV cs.AI cs.LG cs.NE stat.ML 83%

Analyzing and Improving the Training Dynamics of Diffusion Models

Tero Karras, Miika Aittala, Jaakko Lehtinen, Janne Hellsten, Timo Aila, Samuli Laine

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

2403.11697 2024-03-20 cs.CV 83%

Urban Scene Diffusion through Semantic Occupancy Map

Junge Zhang, Qihang Zhang, Li Zhang, Ramana Rao Kompella, Gaowen Liu, Bolei Zhou

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

Comments The project website is https://metadriverse.github.io/urbandiff/

2403.11667 2024-03-19 cs.CV eess.IV 83%

Binary Noise for Binary Tasks: Masked Bernoulli Diffusion for Unsupervised Anomaly Detection

Julia Wolleb, Florentin Bieder, Paul Friedrich, Peter Zhang, Alicia Durrer, Philippe C. Cattin

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

2403.11162 2024-03-19 cs.CV cs.AI cs.CR cs.CY cs.LG 83%

CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion

Xiaoyu Wu, Yang Hua, Chumeng Liang, Jiaru Zhang, Hao Wang, Tao Song, Haibing Guan

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

Comments Accepted by CVPR 2024

2403.07773 2024-03-19 cs.CV 83%

SemCity: Semantic Scene Generation with Triplane Diffusion

Jumin Lee, Sebin Lee, Changho Jo, Woobin Im, Juhyeong Seon, Sung-Eui Yoon

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

Comments Accepted to CVPR 2024

2401.06637 2024-03-19 cs.CV cs.CR 83%

Adversarial Examples are Misaligned in Diffusion Model Manifolds

Peter Lorenz, Ricard Durall, Janis Keuper

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

Comments accepted at IJCNN

2403.10044 2024-03-18 cs.CV 83%

SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion Model

Tao Wu, Xuewei Li, Zhongang Qi, Di Hu, Xintao Wang, Ying Shan, Xi Li

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

Comments Accepted by AAAI2024

2403.09355 2024-03-15 eess.IV cs.CV 83%

Mitigating Data Consistency Induced Discrepancy in Cascaded Diffusion Models for Sparse-view CT Reconstruction

Hanyu Chen, Zhixiu Hao, Lin Guo, Liying Xiao

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

2403.08764 2024-03-14 cs.CV 83%

VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis

Enric Corona, Andrei Zanfir, Eduard Gabriel Bazavan, Nikos Kolotouros, Thiemo Alldieck, Cristian Sminchisescu

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

Comments Project web: https://enriccorona.github.io/vlogger/

2403.07142 2024-03-13 cs.CV cs.CL cs.LG 83%

One Category One Prompt: Dataset Distillation using Diffusion Models

Ali Abbasi, Ashkan Shahbazi, Hamed Pirsiavash, Soheil Kolouri

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

1. 扩散模型 70015 篇

Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models

Pixel-wise RL on Diffusion Models: Reinforcement Learning from Rich Feedback

The Missing U for Efficient Diffusion Models

Exploiting Diffusion Prior for Generalizable Dense Prediction

Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models

DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery

Measuring Style Similarity in Diffusion Models

Action Detection via an Image Diffusion Process

Shape-Guided Diffusion with Inside-Outside Attention

Relation Rectification in Diffusion Model

RecDiffusion: Rectangling for Image Stitching with Diffusion Models

DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery Analysis

AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error

EHRDiff: Exploring Realistic EHR Synthesis with Diffusion Models

Analysing Diffusion Segmentation for Medical Images

S2DM: Sector-Shaped Diffusion Models for Video Generation

Residual Denoising Diffusion Models

Style-Extracting Diffusion Models for Semi-Supervised Histopathology Segmentation

QSMDiff: Unsupervised 3D Diffusion Models for Quantitative Susceptibility Mapping

Direct2.5: Diverse Text-to-3D Generation via Multi-view 2.5D Diffusion

Analyzing and Improving the Training Dynamics of Diffusion Models

Urban Scene Diffusion through Semantic Occupancy Map

Binary Noise for Binary Tasks: Masked Bernoulli Diffusion for Unsupervised Anomaly Detection

CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion

SemCity: Semantic Scene Generation with Triplane Diffusion

Adversarial Examples are Misaligned in Diffusion Model Manifolds

SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion Model

Mitigating Data Consistency Induced Discrepancy in Cascaded Diffusion Models for Sparse-view CT Reconstruction

VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis

One Category One Prompt: Dataset Distillation using Diffusion Models