DiscoFaceGAN:通过3D模仿-对比学习进行纠缠和可控的面部图像生成（CVPR 2020口头）
DiscoFaceGAN：派息纠缠和Co通过3D模仿，对比学习ntrollable人脸图像生成
这是以下论文的tensorflow实现：
通过3D模仿-对比学习，CVPR 2020进行纠缠和可控的面部图像生成。 （口头）
邓登，杨娇龙，陈东，方文和辛彤
论文： :
摘要：本文提出DiscoFaceGAN，人脸图像生成的虚拟人与DIS纠结了不存在的人，表情，姿势和照明的身份，precisely- CO ntrollable潜表示的方法。我们将3D先验嵌入到对抗性学习中，并训练网络以模仿3D人脸分析和渲染过程的图像形成。为了处理由真实和渲染的面部之间的域间隙引起的生成自由度，我们进一步引入对比学习以通过比较生成的图像对来促进解缠结。实验表明，通过我们的模仿对比学习，可以很好地消除因素变化，并且可以精确控制生成的脸部的特性。我们还分析了学习到的潜在空间，并提出了支持因子解缠结的几个有意义的性
文件下载
资源详情
[{"title":"（ 81 个子文件 30.14MB ） DiscoFaceGAN:通过3D模仿-对比学习进行纠缠和可控的面部图像生成（CVPR 2020口头）","children":[{"title":"DiscoFaceGAN-master","children":[{"title":"generate_images.py <span style='color:#111;'> 8.83KB </span>","children":null,"spread":false},{"title":"preprocess","children":[{"title":"preprocess_utils.py <span style='color:#111;'> 6.39KB </span>","children":null,"spread":false},{"title":"similarity_Lm3D_all.mat <span style='color:#111;'> 994B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 72B </span>","children":null,"spread":false}],"spread":true},{"title":"train.py <span style='color:#111;'> 6.86KB </span>","children":null,"spread":false},{"title":"config.py <span style='color:#111;'> 713B </span>","children":null,"spread":false},{"title":"dataset_tool.py <span style='color:#111;'> 29.71KB </span>","children":null,"spread":false},{"title":"metrics","children":[{"title":"perceptual_path_length.py <span style='color:#111;'> 5.10KB </span>","children":null,"spread":false},{"title":"linear_separability.py <span style='color:#111;'> 10.07KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 350B </span>","children":null,"spread":false},{"title":"metric_base.py <span style='color:#111;'> 6.33KB </span>","children":null,"spread":false},{"title":"frechet_inception_distance.py <span style='color:#111;'> 5.42KB </span>","children":null,"spread":false}],"spread":true},{"title":"images","children":[{"title":"disentangled.png <span style='color:#111;'> 1.73MB </span>","children":null,"spread":false},{"title":"teaser.gif <span style='color:#111;'> 11.67MB </span>","children":null,"spread":false},{"title":"expression.png <span style='color:#111;'> 643.99KB </span>","children":null,"spread":false},{"title":"reference.png <span style='color:#111;'> 945.72KB </span>","children":null,"spread":false},{"title":"pose.png <span style='color:#111;'> 825.65KB </span>","children":null,"spread":false},{"title":"light.png <span style='color:#111;'> 603.61KB </span>","children":null,"spread":false}],"spread":true},{"title":"dnnlib","children":[{"title":"util.py <span style='color:#111;'> 13.43KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 799B </span>","children":null,"spread":false},{"title":"submission","children":[{"title":"_internal","children":[{"title":"run.py <span style='color:#111;'> 1.51KB </span>","children":null,"spread":false}],"spread":true},{"title":"run_context.py <span style='color:#111;'> 4.25KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 392B </span>","children":null,"spread":false},{"title":"submit.py <span style='color:#111;'> 10.92KB </span>","children":null,"spread":false}],"spread":true},{"title":"tflib","children":[{"title":"__init__.py <span style='color:#111;'> 524B </span>","children":null,"spread":false},{"title":"optimizer.py <span style='color:#111;'> 9.75KB </span>","children":null,"spread":false},{"title":"network.py <span style='color:#111;'> 29.42KB </span>","children":null,"spread":false},{"title":"autosummary.py <span style='color:#111;'> 7.36KB </span>","children":null,"spread":false},{"title":"tfutil.py <span style='color:#111;'> 9.05KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 1.13KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 9.93KB </span>","children":null,"spread":false},{"title":"vae","children":[{"title":"util.py <span style='color:#111;'> 7.68KB </span>","children":null,"spread":false},{"title":"weights","children":[{"title":"rot","children":[{"title":"stage1_epoch_395.ckpt.index <span style='color:#111;'> 2.04KB </span>","children":null,"spread":false},{"title":"stage1_epoch_395.ckpt.data-00000-of-00001 <span style='color:#111;'> 56.00KB </span>","children":null,"spread":false},{"title":"stage1_epoch_395.ckpt.meta <span style='color:#111;'> 182.08KB </span>","children":null,"spread":false}],"spread":false},{"title":"exp","children":[{"title":"stage1_epoch_395.ckpt.index <span style='color:#111;'> 2.19KB </span>","children":null,"spread":false},{"title":"stage1_epoch_395.ckpt.data-00000-of-00001 <span style='color:#111;'> 3.68MB </span>","children":null,"spread":false},{"title":"stage1_epoch_395.ckpt.meta <span style='color:#111;'> 187.67KB </span>","children":null,"spread":false}],"spread":false},{"title":"id","children":[{"title":"stage1_epoch_395.ckpt.index <span style='color:#111;'> 2.21KB </span>","children":null,"spread":false},{"title":"stage1_epoch_395.ckpt.data-00000-of-00001 <span style='color:#111;'> 16.16MB </span>","children":null,"spread":false},{"title":"stage1_epoch_395.ckpt.meta <span style='color:#111;'> 183.67KB </span>","children":null,"spread":false}],"spread":false},{"title":"gamma","children":[{"title":"stage1_epoch_395.ckpt.index <span style='color:#111;'> 2.16KB </span>","children":null,"spread":false},{"title":"stage1_epoch_395.ckpt.data-00000-of-00001 <span style='color:#111;'> 930.71KB </span>","children":null,"spread":false},{"title":"stage1_epoch_395.ckpt.meta <span style='color:#111;'> 214.39KB </span>","children":null,"spread":false}],"spread":false}],"spread":true},{"title":"two_stage_vae_model.py <span style='color:#111;'> 4.57KB </span>","children":null,"spread":false},{"title":"demo.py <span style='color:#111;'> 3.61KB </span>","children":null,"spread":false},{"title":"data_loader.py <span style='color:#111;'> 2.75KB </span>","children":null,"spread":false}],"spread":true},{"title":"SECURITY.md <span style='color:#111;'> 2.75KB </span>","children":null,"spread":false},{"title":"NOTICE <span style='color:#111;'> 30.66KB </span>","children":null,"spread":false},{"title":"training","children":[{"title":"networks_recon.py <span style='color:#111;'> 2.36KB </span>","children":null,"spread":false},{"title":"misc.py <span style='color:#111;'> 9.76KB </span>","children":null,"spread":false},{"title":"pretrained_weights","children":[{"title":"parsing_net","children":[{"title":"xx.mat <span style='color:#111;'> 1.00MB </span>","children":null,"spread":false},{"title":"yy.mat <span style='color:#111;'> 1.00MB </span>","children":null,"spread":false}],"spread":false}],"spread":false},{"title":"inception_resnet_v1.py <span style='color:#111;'> 11.49KB </span>","children":null,"spread":false},{"title":"training_utils.py <span style='color:#111;'> 12.24KB </span>","children":null,"spread":false},{"title":"parser_utils.py <span style='color:#111;'> 5.37KB </span>","children":null,"spread":false},{"title":"resnet_block.py <span style='color:#111;'> 6.65KB </span>","children":null,"spread":false},{"title":"loss.py <span style='color:#111;'> 10.40KB </span>","children":null,"spread":false},{"title":"networks_parser.py <span style='color:#111;'> 4.16KB </span>","children":null,"spread":false},{"title":"dataset.py <span style='color:#111;'> 11.93KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 350B </span>","children":null,"spread":false},{"title":"networks_stylegan.py <span style='color:#111;'> 34.10KB </span>","children":null,"spread":false},{"title":"training_loop.py <span style='color:#111;'> 16.11KB </span>","children":null,"spread":false},{"title":"loss_control.py <span style='color:#111;'> 8.01KB </span>","children":null,"spread":false},{"title":"networks_id.py <span style='color:#111;'> 1.20KB </span>","children":null,"spread":false}],"spread":false},{"title":"CODE_OF_CONDUCT.md <span style='color:#111;'> 453B </span>","children":null,"spread":false},{"title":"renderer","children":[{"title":"__init__.py <span style='color:#111;'> 2B </span>","children":null,"spread":false},{"title":"camera_utils.py <span style='color:#111;'> 5.49KB </span>","children":null,"spread":false},{"title":"BFM face model","children":[{"title":"gan_mask.mat <span style='color:#111;'> 33.16KB </span>","children":null,"spread":false},{"title":"select_vertex_id.mat <span style='color:#111;'> 60.84KB </span>","children":null,"spread":false},{"title":"facemodel_info.mat <span style='color:#111;'> 721.54KB </span>","children":null,"spread":false},{"title":"similarity_Lm3D_all.mat <span style='color:#111;'> 994B </span>","children":null,"spread":false},{"title":"BFM_front_idx.mat <span style='color:#111;'> 43.83KB </span>","children":null,"spread":false},{"title":"std_exp.txt <span style='color:#111;'> 615B </span>","children":null,"spread":false},{"title":"BFM_exp_idx.mat <span style='color:#111;'> 89.78KB </span>","children":null,"spread":false},{"title":"gan_tl.mat <span style='color:#111;'> 643.12KB </span>","children":null,"spread":false}],"spread":false},{"title":"rasterize_triangles.py <span style='color:#111;'> 8.53KB </span>","children":null,"spread":false},{"title":"mesh_renderer.py <span style='color:#111;'> 19.60KB </span>","children":null,"spread":false},{"title":"face_decoder.py <span style='color:#111;'> 13.85KB </span>","children":null,"spread":false}],"spread":false},{"title":".gitignore <span style='color:#111;'> 1.76KB </span>","children":null,"spread":false},{"title":"preprocess_data.py <span style='color:#111;'> 4.13KB </span>","children":null,"spread":false}],"spread":false}],"spread":true}]
评论信息
其他资源
- Kinect Wrapper Unity Package
- oh_my_zsh_20210210离线安装包.zip
- OpenCV的CvvImage类下载，CvvImage.cpp和CvvImage.h打包
- HDR原理与实现
- 飞塔fortiexplorer设置软件
- 数学建模优秀论文合集
- 基于PV模型、电导增量+积分调节器MPPT算法的三相光伏并网仿真模型
- 分割txt超大文件
- Java数据结构和算法(第二版)+随书源代码+applet小程序
- 小型跑酷游戏
- 面向多源知识融合的扩展主题图相似性算法
- 2020担保品管理服务年度报告-.pdf
- 顶力DSK3.1H.zip
- Serene-Conky：干净利落的conky主题，使用lua和cairo制成-源码
- Access解密工具
- Android-快手抢红包是一款开源Android抢红包插件
- (齿轮生成器)GearTrax_2015_23_0_151绿色汉化版V0.2
- 数字电子课程设计——循环彩灯控制器
- apktool2.3.4
- 步进电机S型曲线算法模型
- 对bitmap的压缩设置32k以内，随意设置
- 基于安卓前端j2ee后端的民宿管理系统
- C++ 基础教程Beta 版
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
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