图像生成 - arXivDaily 专题

2404.03159 2024-04-05 cs.CV 79%

HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloud

Wencan Cheng, Hao Tang, Luc Van Gool, Jong Hwan Ko

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

Comments Accepted as a conference paper to the Conference on Computer Vision and Pattern Recognition (2024)

2312.02145 2024-04-04 cs.CV 79%

Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

Bingxin Ke, Anton Obukhov, Shengyu Huang, Nando Metzger, Rodrigo Caye Daudt, Konrad Schindler

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

Comments CVPR 2024 camera ready

2404.00132 2024-04-02 eess.IV cs.CV 79%

FetalDiffusion: Pose-Controllable 3D Fetal MRI Synthesis with Conditional Diffusion Model

Molin Zhang, Polina Golland, Patricia Ellen Grant, Elfar Adalsteinsson

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

Comments 8 pages, 3 figures, 2 tables, submitted to MICCAI 2024, code available if accepted

2403.07234 2024-03-22 cs.CV 79%

It's All About Your Sketch: Democratising Sketch Control in Diffusion Models

Subhadeep Koley, Ayan Kumar Bhunia, Deeptanshu Sekhri, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song

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

Comments Accepted in CVPR 2024. Project page available at https://subhadeepkoley.github.io/StableSketching

2403.05056 2024-03-11 cs.CV 79%

Stealing Stable Diffusion Prior for Robust Monocular Depth Estimation

Yifan Mao, Jian Liu, Xianming Liu

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

2306.00964 2024-03-01 cs.CV cs.LG 79%

Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation

Minghui Hu, Jianbin Zheng, Daqing Liu, Chuanxia Zheng, Chaoyue Wang, Dacheng Tao, Tat-Jen Cham

专题命中可控生成：image generation(title)；diffusion(abstract)；分类 cs.CV

Comments Project Page: https://mhh0318.github.io/cocktail/

2402.17101 2024-02-28 cs.CV cs.AI 79%

T-HITL Effectively Addresses Problematic Associations in Image Generation and Maintains Overall Visual Quality

Susan Epstein, Li Chen, Alessandro Vecchiato, Ankit Jain

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

Comments 11 pages, 8 figures

2402.14395 2024-02-23 cs.CV 79%

Semantic Image Synthesis with Unconditional Generator

Jungwoo Chae, Hyunin Cho, Sooyeon Go, Kyungmook Choi, Youngjung Uh

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

Comments NeurIPS 2023, Project Page: https://hhyunn2.github.io/SIS_UncondG/

2402.10855 2024-02-19 cs.CV 79%

Control Color: Multimodal Diffusion-based Interactive Image Colorization

Zhexin Liang, Zhaochen Li, Shangchen Zhou, Chongyi Li, Chen Change Loy

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

Comments Project Page: https://zhexinliang.github.io/Control_Color/; Demo Video: https://youtu.be/tSCwA-srl8Q

2402.10334 2024-02-19 cs.CV cs.AI cs.LG 79%

HI-GAN: Hierarchical Inpainting GAN with Auxiliary Inputs for Combined RGB and Depth Inpainting

Ankan Dash, Jingyi Gu, Guiling Wang

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

2301.10551 2024-01-23 cs.CV 79%

Variation-Aware Semantic Image Synthesis

Mingle Xu, Jaehwan Lee, Sook Yoon, Hyongsuk Kim, Dong Sun Park

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

Comments 12 pages, 3 figures, 5 tables

2401.09836 2024-01-19 cs.CV 79%

Exploring Latent Cross-Channel Embedding for Accurate 3D Human Pose Reconstruction in a Diffusion Framework

Junkun Jiang, Jie Chen

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

2401.08815 2024-01-18 cs.CV cs.AI cs.LG 79%

Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive

Yumeng Li, Margret Keuper, Dan Zhang, Anna Khoreva

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

Comments Accepted at ICLR 2024. Project page: https://yumengli007.github.io/ALDM/ and code: https://github.com/boschresearch/ALDM

2306.09086 2024-01-12 cs.CV 79%

Relation-Aware Diffusion Model for Controllable Poster Layout Generation

Fengheng Li, An Liu, Wei Feng, Honghe Zhu, Yaoyu Li, Zheng Zhang, Jingjing Lv, Xin Zhu, Junjie Shen, Zhangang Lin, Jingping Shao

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

Comments accepted by CIKM 2023

2401.03914 2024-01-09 cs.CV 79%

D3PRefiner: A Diffusion-based Denoise Method for 3D Human Pose Refinement

Danqi Yan, Qing Gao, Yuepeng Qian, Xinxing Chen, Chenglong Fu, Yuquan Leng

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

2401.03476 2024-01-09 cs.MM cs.AI cs.HC cs.SD eess.AS 79%

Freetalker: Controllable Speech and Text-Driven Gesture Generation Based on Diffusion Models for Enhanced Speaker Naturalness

Sicheng Yang, Zunnan Xu, Haiwei Xue, Yongkang Cheng, Shaoli Huang, Mingming Gong, Zhiyong Wu

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

Comments 6 pages, 3 figures, ICASSP 2024

2312.14611 2023-12-25 cs.CV 79%

Tuning-Free Inversion-Enhanced Control for Consistent Image Editing

Xiaoyue Duan, Shuhao Cui, Guoliang Kang, Baochang Zhang, Zhengcong Fei, Mingyuan Fan, Junshi Huang

专题命中可控生成：image editing(title)；diffusion(abstract)；分类 cs.CV

2312.12471 2023-12-21 cs.CV 79%

Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion

Fan Zhang, Shaodi You, Yu Li, Ying Fu

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

Comments 10 pages

2312.08256 2023-12-14 cs.CV 79%

A Compact and Semantic Latent Space for Disentangled and Controllable Image Editing

Gwilherm Lesné, Yann Gousseau, Saïd Ladjal, Alasdair Newson

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

2312.05798 2023-12-12 cs.CV 79%

Disentangled Representation Learning for Controllable Person Image Generation

Wenju Xu, Chengjiang Long, Yongwei Nie, Guanghui Wang

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

2312.01850 2023-12-05 cs.CV cs.LG 79%

Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentation

Joshua Niemeijer, Manuel Schwonberg, Jan-Aike Termöhlen, Nico M. Schmidt, Tim Fingscheidt

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

Comments Accepted to WACV 2024

2311.18830 2023-12-01 cs.CV 79%

MotionEditor: Editing Video Motion via Content-Aware Diffusion

Shuyuan Tu, Qi Dai, Zhi-Qi Cheng, Han Hu, Xintong Han, Zuxuan Wu, Yu-Gang Jiang

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

Comments 18 pages, 15 figures. Project page at https://francis-rings.github.io/MotionEditor/

2311.16882 2023-11-29 cs.CV cs.CL cs.LG 79%

Optimisation-Based Multi-Modal Semantic Image Editing

Bowen Li, Yongxin Yang, Steven McDonagh, Shifeng Zhang, Petru-Daniel Tudosiu, Sarah Parisot

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

2311.08217 2023-11-15 cs.CV 79%

Peer is Your Pillar: A Data-unbalanced Conditional GANs for Few-shot Image Generation

Ziqiang Li, Chaoyue Wang, Xue Rui, Chao Xue, Jiaxu Leng, Bin Li

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

Comments Under Review

2310.18986 2023-11-07 cs.CV 79%

Controllable Group Choreography using Contrastive Diffusion

Nhat Le, Tuong Do, Khoa Do, Hien Nguyen, Erman Tjiputra, Quang D. Tran, Anh Nguyen

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

2311.01015 2023-11-03 cs.CV 79%

Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs

Peng Jin, Yang Wu, Yanbo Fan, Zhongqian Sun, Yang Wei, Li Yuan

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

Comments Accepted by NeurIPS 2023

2310.16305 2023-10-26 cs.CV cs.LG 79%

Dolfin: Diffusion Layout Transformers without Autoencoder

Yilin Wang, Zeyuan Chen, Liangjun Zhong, Zheng Ding, Zhizhou Sha, Zhuowen Tu

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

2302.08357 2023-10-19 cs.CV 79%

Boundary Guided Learning-Free Semantic Control with Diffusion Models

Ye Zhu, Yu Wu, Zhiwei Deng, Olga Russakovsky, Yan Yan

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

Comments NeurIPS 2023. 27 pages including appendices, code at https://github.com/L-YeZhu/BoundaryDiffusion

2309.16812 2023-10-02 cs.CV eess.IV 79%

SatDM: Synthesizing Realistic Satellite Image with Semantic Layout Conditioning using Diffusion Models

Orkhan Baghirli, Hamid Askarov, Imran Ibrahimli, Ismat Bakhishov, Nabi Nabiyev

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

Comments 14 pages, 4 figures

2306.00914 2023-09-29 cs.CV 79%

Conditioning Diffusion Models via Attributes and Semantic Masks for Face Generation

Nico Giambi, Giuseppe Lisanti

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

Comments The paper is under consideration at Computer Vision and Image Understanding

1. 可控生成 4201 篇

HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloud

Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

FetalDiffusion: Pose-Controllable 3D Fetal MRI Synthesis with Conditional Diffusion Model

It's All About Your Sketch: Democratising Sketch Control in Diffusion Models

Stealing Stable Diffusion Prior for Robust Monocular Depth Estimation

Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation

T-HITL Effectively Addresses Problematic Associations in Image Generation and Maintains Overall Visual Quality

Semantic Image Synthesis with Unconditional Generator

Control Color: Multimodal Diffusion-based Interactive Image Colorization

HI-GAN: Hierarchical Inpainting GAN with Auxiliary Inputs for Combined RGB and Depth Inpainting

Variation-Aware Semantic Image Synthesis

Exploring Latent Cross-Channel Embedding for Accurate 3D Human Pose Reconstruction in a Diffusion Framework

Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive

Relation-Aware Diffusion Model for Controllable Poster Layout Generation

D3PRefiner: A Diffusion-based Denoise Method for 3D Human Pose Refinement

Freetalker: Controllable Speech and Text-Driven Gesture Generation Based on Diffusion Models for Enhanced Speaker Naturalness

Tuning-Free Inversion-Enhanced Control for Consistent Image Editing

Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion

A Compact and Semantic Latent Space for Disentangled and Controllable Image Editing

Disentangled Representation Learning for Controllable Person Image Generation

Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentation

MotionEditor: Editing Video Motion via Content-Aware Diffusion

Optimisation-Based Multi-Modal Semantic Image Editing

Peer is Your Pillar: A Data-unbalanced Conditional GANs for Few-shot Image Generation

Controllable Group Choreography using Contrastive Diffusion

Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs

Dolfin: Diffusion Layout Transformers without Autoencoder

Boundary Guided Learning-Free Semantic Control with Diffusion Models

SatDM: Synthesizing Realistic Satellite Image with Semantic Layout Conditioning using Diffusion Models

Conditioning Diffusion Models via Attributes and Semantic Masks for Face Generation