LPTN:论文'High-Resolution Photorealistic Image Translation in Real-Time'的官方实现

上传者: 42116705 | 上传时间: 2024-01-12 16:22:31 | 文件大小: 269KB | 文件类型: ZIP
LPTN | | 实时高分辨率真实感图像翻译:拉普拉斯金字塔翻译网络梁洁*、曾慧*、。 在 CVPR 2021 中。 抽象的 现有的图像到图像转换 (I2IT) 方法要么受限于低分辨率图像,要么由于对高分辨率特征图卷积的计算负担过重而导致推理时间长。 在本文中,我们专注于加速基于封闭形式拉普拉斯金字塔分解和重建的高分辨率逼真 I2IT 任务。 具体来说,我们揭示了属性变换,如光照和颜色处理,更多地与低频分量相关,而内容细节可以在高频分量上自适应地细化。 因此,我们提出了一个拉普拉斯金字塔翻译网络 (LPTN) 来同时执行这两项任务,我们设计了一个轻量级网络,用于翻译分辨率降低的低频分量和渐进式掩蔽策略,以有效地改进高频分量。 我们的模型避免了处理高分辨率特征图所消耗的大部分繁重计算,并忠实地保留了图像细节。 在各种任务上的大量实验结果表明,所提出的方法可以使用一个普通 GPU 实时转换 4

文件下载

资源详情

[{"title":"( 47 个子文件 269KB ) LPTN:论文'High-Resolution Photorealistic Image Translation in Real-Time'的官方实现","children":[{"title":"LPTN-main","children":[{"title":"Figs","children":[{"title":"LPTN_pipeline.jpg <span style='color:#111;'> 223.82KB </span>","children":null,"spread":false}],"spread":true},{"title":"experiments","children":[{"title":"pretrained_models","children":[{"title":"put_models_here <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"scripts","children":[{"title":"download_gdrive.py <span style='color:#111;'> 370B </span>","children":null,"spread":false},{"title":"data_preparation","children":[{"title":"download_datasets.py <span style='color:#111;'> 1.94KB </span>","children":null,"spread":false},{"title":"create_lmdb.py <span style='color:#111;'> 1.33KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"requirement.txt <span style='color:#111;'> 124B </span>","children":null,"spread":false},{"title":"options","children":[{"title":"train","children":[{"title":"LPTN","children":[{"title":"train_FiveK.yml <span style='color:#111;'> 2.39KB </span>","children":null,"spread":false},{"title":"train_FiveK_paper.yml <span style='color:#111;'> 2.40KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"test","children":[{"title":"LPTN","children":[{"title":"test_speed_FiveK.yml <span style='color:#111;'> 855B </span>","children":null,"spread":false},{"title":"test_FiveK.yml <span style='color:#111;'> 927B </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true},{"title":"README.md <span style='color:#111;'> 4.56KB </span>","children":null,"spread":false},{"title":"codes","children":[{"title":"train.py <span style='color:#111;'> 9.46KB </span>","children":null,"spread":false},{"title":"utils","children":[{"title":"misc.py <span style='color:#111;'> 4.38KB </span>","children":null,"spread":false},{"title":"options.py <span style='color:#111;'> 3.67KB </span>","children":null,"spread":false},{"title":"file_client.py <span style='color:#111;'> 6.14KB </span>","children":null,"spread":false},{"title":"flow_util.py <span style='color:#111;'> 6.19KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 806B </span>","children":null,"spread":false},{"title":"download_util.py <span style='color:#111;'> 2.07KB </span>","children":null,"spread":false},{"title":"lmdb_util.py <span style='color:#111;'> 7.11KB </span>","children":null,"spread":false},{"title":"logger.py <span style='color:#111;'> 4.97KB </span>","children":null,"spread":false},{"title":"dist_util.py <span style='color:#111;'> 2.55KB </span>","children":null,"spread":false},{"title":"img_util.py <span style='color:#111;'> 7.29KB </span>","children":null,"spread":false}],"spread":true},{"title":"models","children":[{"title":"archs","children":[{"title":"LPTN_paper_arch.py <span style='color:#111;'> 6.82KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 1.20KB </span>","children":null,"spread":false},{"title":"arch_util.py <span style='color:#111;'> 8.27KB </span>","children":null,"spread":false},{"title":"LPTN_arch.py <span style='color:#111;'> 6.85KB </span>","children":null,"spread":false},{"title":"discriminator_arch.py <span style='color:#111;'> 4.10KB </span>","children":null,"spread":false}],"spread":true},{"title":"lptn_test_model.py <span style='color:#111;'> 6.06KB </span>","children":null,"spread":false},{"title":"losses","children":[{"title":"loss_util.py <span style='color:#111;'> 2.83KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 367B </span>","children":null,"spread":false},{"title":"losses.py <span style='color:#111;'> 15.21KB </span>","children":null,"spread":false}],"spread":true},{"title":"lptn_model.py <span style='color:#111;'> 9.72KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 1.11KB </span>","children":null,"spread":false},{"title":"lr_scheduler.py <span style='color:#111;'> 4.22KB </span>","children":null,"spread":false},{"title":"base_model.py <span style='color:#111;'> 9.94KB </span>","children":null,"spread":false}],"spread":true},{"title":"metrics","children":[{"title":"__init__.py <span style='color:#111;'> 102B </span>","children":null,"spread":false},{"title":"psnr_ssim.py <span style='color:#111;'> 4.62KB </span>","children":null,"spread":false},{"title":"metric_util.py <span style='color:#111;'> 1.28KB </span>","children":null,"spread":false}],"spread":true},{"title":"test.py <span style='color:#111;'> 1.70KB </span>","children":null,"spread":false},{"title":"test_speed.py <span style='color:#111;'> 1.68KB </span>","children":null,"spread":false},{"title":"data","children":[{"title":"unpair_image_dataset.py <span style='color:#111;'> 3.25KB </span>","children":null,"spread":false},{"title":"paired_image_dataset.py <span style='color:#111;'> 3.26KB </span>","children":null,"spread":false},{"title":"data_util.py <span style='color:#111;'> 5.03KB </span>","children":null,"spread":false},{"title":"data_sampler.py <span style='color:#111;'> 1.61KB </span>","children":null,"spread":false},{"title":"prefetch_dataloader.py <span style='color:#111;'> 3.08KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 4.51KB </span>","children":null,"spread":false},{"title":"transforms.py <span style='color:#111;'> 6.63KB </span>","children":null,"spread":false}],"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