RealSR:通过内核估计和噪声注入实现真实世界的超分辨率-源码

上传者: 42160278 | 上传时间: 2021-05-29 23:07:33 | 文件大小: 14.67MB | 文件类型: ZIP
RealSR 通过内核估计和噪声注入实现真实世界的超分辨率 纪小中,曹云,泰英,王成杰,李吉林和黄飞跃 腾讯优途实验室 我们的解决方案在两个赛道上均获得了CVPR NTIRE 2020真实世界超高分辨率挑战赛的冠军。 (官方PyTorch实施) 更新-2020年9月2日 培训代码可从 更新-2020年5月26日 添加模型。 提供了基于。在Windows / Linux / macos上测试您自己的图像。有关更多详细信息,请参见 用法./realsr-ncnn-vulkan -i in.jpg -o out.png -x使用合奏 -g 0选择GPU ID。 介绍 不管模糊和噪点如何,最新的最新超分辨率方法在理想数据集上均实现了令人印象深刻的性能。但是,这些方法在现实世界中的图像超分辨率中始终会失败,因为它们大多数都从高质量图像中采用简单的三次三次向下采样来构造低分辨率(LR)和高分辨率(

文件下载

资源详情

[{"title":"( 57 个子文件 14.67MB ) RealSR:通过内核估计和噪声注入实现真实世界的超分辨率-源码","children":[{"title":"RealSR-master","children":[{"title":".gitignore <span style='color:#111;'> 1.84KB </span>","children":null,"spread":false},{"title":"codes","children":[{"title":"data","children":[{"title":"__init__.py <span style='color:#111;'> 1.72KB </span>","children":null,"spread":false},{"title":"GT_dataset.py <span style='color:#111;'> 5.79KB </span>","children":null,"spread":false},{"title":"LR_dataset.py <span style='color:#111;'> 1.20KB </span>","children":null,"spread":false},{"title":"LRHR_seg_bg_dataset.py <span style='color:#111;'> 5.81KB </span>","children":null,"spread":false},{"title":"data_loader.py <span style='color:#111;'> 1.71KB </span>","children":null,"spread":false},{"title":"util.py <span style='color:#111;'> 16.49KB </span>","children":null,"spread":false},{"title":"data_sampler.py <span style='color:#111;'> 2.24KB </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"options","children":[{"title":"dped","children":[{"title":"test_dped.yml <span style='color:#111;'> 575B </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"options.py <span style='color:#111;'> 4.47KB </span>","children":null,"spread":false},{"title":"df2k","children":[{"title":"test_df2k.yml <span style='color:#111;'> 511B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"models","children":[{"title":"__init__.py <span style='color:#111;'> 606B </span>","children":null,"spread":false},{"title":"SRGAN_model.py <span style='color:#111;'> 15.67KB </span>","children":null,"spread":false},{"title":"SR_model.py <span style='color:#111;'> 6.62KB </span>","children":null,"spread":false},{"title":"lr_scheduler.py <span style='color:#111;'> 5.48KB </span>","children":null,"spread":false},{"title":"SFTGAN_ACD_model.py <span style='color:#111;'> 11.36KB </span>","children":null,"spread":false},{"title":"networks.py <span style='color:#111;'> 3.80KB </span>","children":null,"spread":false},{"title":"modules","children":[{"title":"module_util.py <span style='color:#111;'> 2.56KB </span>","children":null,"spread":false},{"title":"discriminator_vgg_arch.py <span style='color:#111;'> 10.95KB </span>","children":null,"spread":false},{"title":"RRDBNet_arch.py <span style='color:#111;'> 2.68KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"seg_arch.py <span style='color:#111;'> 2.52KB </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"loss.cpython-36.pyc <span style='color:#111;'> 3.05KB </span>","children":null,"spread":false},{"title":"module_util.cpython-36.pyc <span style='color:#111;'> 2.82KB </span>","children":null,"spread":false},{"title":"discriminator_vgg_arch.cpython-36.pyc <span style='color:#111;'> 3.05KB </span>","children":null,"spread":false},{"title":"__init__.cpython-36.pyc <span style='color:#111;'> 153B </span>","children":null,"spread":false},{"title":"SRResNet_arch.cpython-36.pyc <span style='color:#111;'> 1.88KB </span>","children":null,"spread":false},{"title":"RRDBNet_arch.cpython-36.pyc <span style='color:#111;'> 3.06KB </span>","children":null,"spread":false}],"spread":false},{"title":"SRResNet_arch.py <span style='color:#111;'> 2.05KB </span>","children":null,"spread":false},{"title":"loss.py <span style='color:#111;'> 2.60KB </span>","children":null,"spread":false},{"title":"sft_arch.py <span style='color:#111;'> 7.02KB </span>","children":null,"spread":false}],"spread":true},{"title":"base_model.py <span style='color:#111;'> 4.53KB </span>","children":null,"spread":false}],"spread":true},{"title":"utils","children":[{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"util.py <span style='color:#111;'> 7.51KB </span>","children":null,"spread":false}],"spread":true},{"title":"scripts","children":[{"title":"create_lmdb.py <span style='color:#111;'> 2.73KB </span>","children":null,"spread":false},{"title":"extract_subimgs_single.py <span style='color:#111;'> 2.92KB </span>","children":null,"spread":false},{"title":"generate_mod_LR_bic.m <span style='color:#111;'> 2.25KB </span>","children":null,"spread":false},{"title":"color2gray.py <span style='color:#111;'> 2.11KB </span>","children":null,"spread":false},{"title":"generate_mod_LR_bic.py <span style='color:#111;'> 2.46KB </span>","children":null,"spread":false},{"title":"transfer_params_sft.py <span style='color:#111;'> 1.84KB </span>","children":null,"spread":false},{"title":"transfer_params_MSRResNet.py <span style='color:#111;'> 1.10KB </span>","children":null,"spread":false},{"title":"back_projection","children":[{"title":"main_bp.m <span style='color:#111;'> 616B </span>","children":null,"spread":false},{"title":"main_reverse_filter.m <span style='color:#111;'> 716B </span>","children":null,"spread":false},{"title":"backprojection.m <span style='color:#111;'> 588B </span>","children":null,"spread":false}],"spread":false}],"spread":true},{"title":"test.py <span style='color:#111;'> 5.46KB </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 10.09KB </span>","children":null,"spread":false}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 11.09KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 6.31KB </span>","children":null,"spread":false},{"title":"figures","children":[{"title":"dped.png <span style='color:#111;'> 1.76MB </span>","children":null,"spread":false},{"title":"track1.png <span style='color:#111;'> 324.46KB </span>","children":null,"spread":false},{"title":"df2k.png <span style='color:#111;'> 3.11MB </span>","children":null,"spread":false},{"title":"track2.png <span style='color:#111;'> 272.94KB </span>","children":null,"spread":false},{"title":"arch.png <span style='color:#111;'> 271.78KB </span>","children":null,"spread":false},{"title":"0913.png <span style='color:#111;'> 4.27MB </span>","children":null,"spread":false},{"title":"0935.png <span style='color:#111;'> 4.65MB </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明