The first branch learns spatio-temporal features by tokenizing the input frames along the spatial and temporal dimensions using a ConvNext-based encoder and processing these abstract tokens using a bottleneck mixer.
In this work, we propose RePaint: A Denoising Diffusion Probabilistic Model (DDPM) based inpainting approach that is applicable to even extreme masks.
Super-resolution is an ill-posed problem, where a ground-truth high-resolution image represents only one possibility in the space of plausible solutions.
More specifically, HCFlow learns a bijective mapping between HR and LR image pairs by modelling the distribution of the LR image and the rest high-frequency component simultaneously.
We propose DeFlow, a method for learning stochastic image degradations from unpaired data.
SRFlow therefore directly accounts for the ill-posed nature of the problem, and learns to predict diverse photo-realistic high-resolution images.
Ranked #4 on Image Super-Resolution on DIV2K val - 4x upscaling (using extra training data)
5 code implementations • 5 May 2020 • Andreas Lugmayr, Martin Danelljan, Radu Timofte, Namhyuk Ahn, Dongwoon Bai, Jie Cai, Yun Cao, Junyang Chen, Kaihua Cheng, SeYoung Chun, Wei Deng, Mostafa El-Khamy, Chiu Man Ho, Xiaozhong Ji, Amin Kheradmand, Gwantae Kim, Hanseok Ko, Kanghyu Lee, Jungwon Lee, Hao Li, Ziluan Liu, Zhi-Song Liu, Shuai Liu, Yunhua Lu, Zibo Meng, Pablo Navarrete Michelini, Christian Micheloni, Kalpesh Prajapati, Haoyu Ren, Yong Hyeok Seo, Wan-Chi Siu, Kyung-Ah Sohn, Ying Tai, Rao Muhammad Umer, Shuangquan Wang, Huibing Wang, Timothy Haoning Wu, Hao-Ning Wu, Biao Yang, Fuzhi Yang, Jaejun Yoo, Tongtong Zhao, Yuanbo Zhou, Haijie Zhuo, Ziyao Zong, Xueyi Zou
This paper reviews the NTIRE 2020 challenge on real world super-resolution.
1 code implementation • 18 Nov 2019 • Andreas Lugmayr, Martin Danelljan, Radu Timofte, Manuel Fritsche, Shuhang Gu, Kuldeep Purohit, Praveen Kandula, Maitreya Suin, A. N. Rajagopalan, Nam Hyung Joon, Yu Seung Won, Guisik Kim, Dokyeong Kwon, Chih-Chung Hsu, Chia-Hsiang Lin, Yuanfei Huang, Xiaopeng Sun, Wen Lu, Jie Li, Xinbo Gao, Sefi Bell-Kligler
For training, only one set of source input images is therefore provided in the challenge.
Instead of directly addressing this problem, most works employ the popular bicubic downsampling strategy to artificially generate a corresponding low resolution image.