.png){kind=icon}
返回
Fine-grained scale space learning for single image super-resolution
.png){kind=icon}
PRE
AI
DOI：10.1007/s00371-022-02551-w.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recent deep convolutional neural networks have achieved great reconstruction accuracy for single image super-resolution (SISR). Most of them, however, need to train a specific set of parameters for a single scaling factor or a particular group of scaling factors. This means, multiple sets of model parameters have to be used for different scaling factors, each of which can be already very large. In this paper, we study a new problem of fine-grained scale space learning of SISR, which uses one set of parameters while achieving varying scales. Specifically, we aim to use an arbitrary base SISR x 2 model to realize high-quality SISR for a continuous-integer spectrum of scaling factors, e.g., 2 similar to 8. To this end, first for the base scaling factor 2, we propose low-resolution reconstruction, blind kernel estimation and recursive error compensation, to generate three loss functions, helping to boost the training quality of the base model. Then, we cascade the boosted SISR x2 model and extend the low-resolution reconstruction to incorporate multiple LR loss functions covering {3, 4, ..., 2(n)} scales. By this way, the SISR x2 model can be effectively tuned to work well for continuous-integer scaling factors, with exactly the same set of parameters. Extensive experiments verify the capability of our approach to enable state-of-the-art methods to realize fine-grained scale space learning of SISR, with higher accuracy and much less parameters.
Keyword:
Single-image super-resolution
Fine-grained scale space
Base model
Boosting and cascading
期刊
IF:
2.9
论文数:
4.6K
被引数:
6.5K
机构
引用论文
The Cytoplasmic Tail of FPC Antagonizes the Full-Length Protein in the Regulation of mTOR Pathway.png)
PLoS ONE
OAAI
PLoS ONEIF0
OAAI分享收藏In vivo DTI of the healthy and injured cat spinal cord at high spatial and angular resolution高空间和角度分辨率下健康和受伤的猫脊髓的体内DTINeuroImage
NeuroImageIF0
PREAI
分享收藏Red, green, and blue electrochromism in ambipolar poly(amine–amide–imide)s based on electroactive tetraphenyl‐p‐phenylenediamine units基于电活性四苯基 p-苯二胺单元的双极性聚 (胺-酰胺-酰亚胺) 中的红色，绿色和蓝色电致变色
PREAI
分享收藏Effects of Nautical Traffic and Noise on Foraging Patterns of Mediterranean Damselfish (Chromis chromis)海上交通和噪声对地中海豚 (Chromis chromis) 觅食方式的影响PLoS ONE
OAAI
PLoS ONEIF0
OAAI分享收藏N-Doped Graphene-Supported PtRu Direct Methanol Fuel Cell Electrocatalysts氮掺杂石墨烯负载PtRu直接甲醇燃料电池电催化剂OAAI
OAAI分享收藏
查看更多内容