谷歌浏览器插件
订阅小程序
在清言上使用

What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs

Computer Vision and Pattern Recognition(2024)

引用 0|浏览61
暂无评分
关键词
Generative Adversarial Networks,3D Generative Adversarial Networks,Computational Cost,Image Quality,Super-resolution,Sampling Density,2D Images,Fewer Samples,3D Geometry,Surface Geometry,Generative Adversarial Networks Training,Volume Rendering,Random Number,Standard Samples,Diffusion Model,Discrete Distribution,3D Representation,3D Scene,Proposal Network,2D Data,Fréchet Inception Distance,Robust Sample,Grid Features,Sampling-based Methods,View Synthesis,High-resolution Details,Laplace Distribution,Generative Adversarial Network Framework,Geometry Features
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要