Awesome-Generative-Image-Composition
Image compositor
A curated collection of resources and tools for composing images by inserting objects into backgrounds.
A curated list of papers, code, and resources pertaining to generative image composition or object insertion.
82 stars
8 watching
6 forks
Language: Python
last commit: 14 days ago diffusion-modelimage-compositionobject-insertion
Awesome Generative Image Composition / Evaluation Metrics | |||
| Composite-Image-Evaluation | 20 | 9 months ago | |
Awesome Generative Image Composition / Test Set | |||
| COCOEE | 1,109 | 12 months ago | (within-domain, single-ref): 500 background images from MSCOCO validation set. Each background image has a bounding box and a foreground image from MSCOCO training set |
| TF-ICON test benchmark | 795 | 10 months ago | (cross-domain, single-ref): 332 samples. Each sample consists of a background image, a foreground image, a user mask, and a text prompt |
| FOSCom | 145 | about 2 months ago | (within-domain, single-ref): 640 background images from Internet. Each background image has a manually annotated bounding box and a foreground image from MSCOCO training set |
| DreamEditBench | (within-domain, multi-ref): 220 background images and 30 unique foreground objects from 15 categories | ||
| MureCom | 18 | 6 months ago | (within-domain, multi-ref): 640 background images and 96 unique foreground objects from 32 categories |
Awesome Generative Image Composition / Leaderboard / Evaluating Your Results | |||
| requirements.txt | Begin by installing the dependencies listed in | ||
| Segment Anything | 47,627 | 2 months ago | Additionally, install |
Awesome Generative Image Composition / Leaderboard / Evaluating Your Results / Download the following pretrained models into the folder: | |||
| openai/clip-vit-base-patch32 | : Used for CLIP score and FID score calculations | ||
| ViT-H SAM model | 47,627 | 2 months ago | : Utilized to estimate foreground masks for reference images and generated composites |
| facebook/dino-vits16 | : Employed in DINO score computation | ||
| coco2017_gmm_k20 | 1,109 | 12 months ago | : Utilized to compute the overall quality score |
Awesome Generative Image Composition / Leaderboard / Evaluating Your Results / : | |||
| COCOEE benchmark | 1,109 | 12 months ago | Prepare the alongside your generated composite results. Ensure that your composite images have filenames corresponding to the background images of the COCOEE dataset, as illustrated below: |
Awesome Generative Image Composition / Papers | |||
| [arXiv] | Shaoan Xie, Yang Zhao, Zhisheng Xiao, Kelvin C.K. Chan, Yandong Li, Yanwu Xu, Kun Zhang, Tingbo Hou: " " arXiv preprint arXiv:2312.03771 (2023) | ||
| [arXiv] | Yulin Pan, Chaojie Mao, Zeyinzi Jiang, Zhen Han, Jingfeng Zhang: " " arXiv preprint arXiv:2403.19534 (2024) | ||
| [arXiv] | Zitian Zhang, Frederic Fortier-Chouinard, Mathieu Garon, Anand Bhattad, Jean-Francois Lalonde: " " arXiv preprint arXiv:2410.08168 (2024) | ||
| [arXiv] | Thinking Outside the BBox: Unconstrained Generative Object Compositing：" " arXiv preprint arXiv:2409.04559 (2024) | ||
| [arXiv] | Weijing Tao, Xiaofeng Yang, Biwen Lei, Miaomiao Cui, Xuansong Xie, Guosheng Lin: " " arXiv preprint arXiv:2409.10090 (2024). [ | ||
| [arXiv] | Yizhi Song, Zhifei Zhang, Zhe Lin, Scott Cohen, Brian Price, Jianming Zhang, Soo Ye Kim, He Zhang, Wei Xiong, Daniel Aliaga: " " CVPR (2024) | ||
| [arXiv] | Xi Chen, Lianghua Huang, Yu Liu, Yujun Shen, Deli Zhao, Hengshuang Zhao: " " CVPR (2024) | ||
| [pdf] | Vishnu Sarukkai, Linden Li, Arden Ma, Christopher Re, Kayvon Fatahalian: " " WACV (2024) | ||
| [arXiv] | Ziyang Yuan, Mingdeng Cao, Xintao Wang, Zhongang Qi, Chun Yuan, Ying Shan: " " ACM MM (2024) | ||
| [arXiv] | Bo Zhang, Yuxuan Duan, Jun Lan, Yan Hong, Huijia Zhu, Weiqiang Wang, Li Niu: " " arXiv preprint arXiv:2308.10040 (2023) | ||
| [arXiv] | Xin Zhang, Jiaxian Guo, Paul Yoo, Yutaka Matsuo, Yusuke Iwasawa: " " arXiv preprint arXiv:2306.07596 (2023) | ||
| [arXiv] | Roy Hachnochi, Mingrui Zhao, Nadav Orzech, Rinon Gal, Ali Mahdavi-Amiri, Daniel Cohen-Or, Amit Haim Bermano: " " arXiv preprint arXiv:2302.10167 (2023) | ||
| [pdf] | Shilin Lu, Yanzhu Liu, Adams Wai-Kin Kong: " " ICCV (2023) | ||
| [arXiv] | Binxin Yang, Shuyang Gu, Bo Zhang, Ting Zhang, Xuejin Chen, Xiaoyan Sun, Dong Chen, Fang Wen: " " CVPR (2023) | ||
| [arXiv] | Yizhi Song, Zhifei Zhang, Zhe Lin, Scott Cohen, Brian Price, Jianming Zhang, Soo Ye Kim, Daniel Aliaga: " " CVPR (2023) | ||
| [paper] | Sumith Kulal, Tim Brooks, Alex Aiken, Jiajun Wu, Jimei Yang, Jingwan Lu, Alexei A. Efros, Krishna Kumar Singh: " " CVPR (2023) | ||
Awesome Generative Image Composition / Related Topics | |||
| [arXiv] | Jinghao Zhou, Tomas Jakab, Philip Torr, Christian Rupprecht: " " arXiv preprint arXiv:2312.12419 (2023) | ||
| [arXiv] | Mohamad Shahbazi, Liesbeth Claessens, Michael Niemeyer, Edo Collins, Alessio Tonioni, Luc Van Gool, Federico Tombari: " " arXiv preprint arXiv:2401.05335 (2024) | ||
| [arXiv] | Rahul Goel, Dhawal Sirikonda, Saurabh Saini, PJ Narayanan: " " CVPR (2023) | ||
| [arXiv] | Rahul Goel, Dhawal Sirikonda, Rajvi Shah, PJ Narayanan: " " CVPR Workshop (2023) | ||
| [arXiv] | Verica Lazova, Vladimir Guzov, Kyle Olszewski, Sergey Tulyakov, Gerard Pons-Moll: " " WACV (2023) | ||
| [arXiv] | Jiaxiang Tang, Xiaokang Chen, Jingbo Wang, Gang Zeng: " " NIPS (2022) | ||
| [arXiv] | Bangbang Yang, Yinda Zhang, Yinghao Xu, Yijin Li, Han Zhou, Hujun Bao, Guofeng Zhang, Zhaopeng Cui: " " ICCV (2021) | ||
| [arXiv] | Boxiao Pan, Zhan Xu, Chun-Hao Paul Huang, Krishna Kumar Singh, Yang Zhou, Leonidas J. Guibas, Jimei Yang: " " arXiv preprint arXiv:2401.10822 (2024) | ||
Awesome Generative Image Composition / Other Resources | |||
| Awesome-Image-Composition | 1,178 | 11 days ago | |