We generate a 3D SDF and a texture field via two latent codes. We utilize DMTet to extract a 3D surface mesh from the SDF, and query the texture field at surface points to get colors. We train with adversarial losses defined on 2D images. In particular, we use a rasterization-based differentiable renderer to obtain RGB images and silhouettes. We utilize two 2D discriminators, each on RGB image, and silhouette, respectively, to classify whether the inputs are real or fake. The whole model is end-to-end trainable.
数据统计
数据评估
本站Xcron提供的NVIDIA都来源于网络,不保证外部链接的准确性和完整性,同时,对于该外部链接的指向,不由Xcron实际控制,在2024年4月15日 下午12:32收录时,该网页上的内容,都属于合规合法,后期网页的内容如出现违规,可以直接联系网站管理员进行删除,Xcron不承担任何责任。
相关导航

BLACKBOX AI is the Best AI Model for Code. Millions of developers use Blackbox Code Chat to answer coding questions and assist them while writing code faster. Whether you are fixing a bug, building a new feature or refactoring your code, ask BLACKBOX to help. BLACKBOX has real-time knowledge of the world, making it able to answer questions about recent events, technological breakthroughs, product releases, API documentations & more BLACKBOX integrates directly with VSCode to automatically suggests the next lines of code based on your repo context.