| Autor: |
Soikat Hasan Ahmed, Chao Li, Xinbo Gao, Haoning Wu, A. N. Rajagopalan, Mengmeng Bai, Murari Mandal, Chu Tak Li, Cai Yiyang, Andrés Romero, Jimei Yang, Taeoh Kim, Shilei Wen, Pranjal Singh Chauhan, Maitreya Suin, Eli Shechtman, Fu Li, Jianming Zhang, Hae Woong Jang, Evangelos Ntavelis, Pratik Narang, Daniel P. K. Lun, Zhi-Song Liu, Li-Wen Wang, Zheng Hui, Haopeng Ni, Chenghua Li, Dongliang He, Yu Zeng, Hanbin Son, Yong Ju Jung, Yu Han, Sangyoun Lee, Jungmin Yoon, Uddin S.M. Nadim, Zhe Lin, Siavash Arjomand Bigdeli, Kuldeep Purohit, Xiumei Wang, Wan-Chi Siu, Errui Ding, Shuchen Li, Dejia Xu, Chajin Shin, Huchuan Lu, Radu Timofte, Weijian Zeng |
| Rok vydání: |
2020 |
| Předmět: |
|
| Zdroj: |
Computer Vision – ECCV 2020 Workshops ISBN: 9783030670696
ECCV Workshops (3) |
| DOI: |
10.1007/978-3-030-67070-2_43 |
| Popis: |
This paper reviews the AIM 2020 challenge on extreme image inpainting. This report focuses on proposed solutions and results for two different tracks on extreme image inpainting: classical image inpainting and semantically guided image inpainting. The goal of track 1 is to inpaint large part of the image with no supervision. Similarly, the goal of track 2 is to inpaint the image by having access to the entire semantic segmentation map of the input. The challenge had 88 and 74 participants, respectively. 11 and 6 teams competed in the final phase of the challenge, respectively. This report gauges current solutions and set a benchmark for future extreme image inpainting methods. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
