Abstract | ||
---|---|---|
With advancement in deep neural network (DNN), recent state-of-the-art (SOTA) image superresolution (SR) methods have achieved impressive performance using deep residual network with dense skip connections. While these models perform well on benchmark dataset where low-resolution (LR) images are constructed from high-resolution (HR) references with known blur kernel, real image SR is more challenging when both images in the LR-HR pair are collected from real cameras. Based on existing dense residual networks, a Gaussian process based neural architecture search (GP-NAS) scheme is utilized to find candidate network architectures using a large search space by varying the number of dense residual blocks, the block size and the number of features. A suite of heterogeneous models with diverse network structure and hyperparameter are selected for model-ensemble to achieve outstanding performance in real image SR. The proposed method won the first place in all three tracks of the AIM 2020 Real Image Super-Resolution Challenge. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1007/978-3-030-67070-2_25 | ECCV Workshops |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhihong Pan | 1 | 3 | 2.80 |
Baopu Li | 2 | 348 | 30.88 |
Teng Xi | 3 | 1 | 0.73 |
Yanwen Fan | 4 | 1 | 1.41 |
Gang Zhang | 5 | 2 | 3.58 |
jingtuo liu | 6 | 47 | 9.43 |
Junyu Han | 7 | 85 | 11.12 |
Er-rui Ding | 8 | 142 | 29.31 |