in-n-out-3d.github.io - In-N-Out

home > domains > in-n-out-3d.github.io

Description: Our work focuses on OOD inversion based on 3D GAN.

editing (3319) gan inversion (1) out-of-distribution data (1)

Example domain paragraphs

Font Awesome fontawesome.com --> arXiv Code (coming soon!) Abstract 3D-aware GANs offer new capabilities for creative content editing, such as view synthesis, while preserving the editing capability of their 2D counterparts. Using GAN inversion, these methods can reconstruct an image or a video by optimizing/predicting a latent code and achieve semantic editing by manipulating the latent code. However, a model pre-trained on a face dataset (e.g., FFHQ) often has difficulty handling faces with out-of-distrib

Our method can be applied to diverse videos from the Internet. We show reconstruction results below.

We can edit it with available semantic editing methods, e.g., InterfaceGAN, StyleCLIP.

Links to in-n-out-3d.github.io (4)

• jbhuang0604.github.io Jia-Bin Huang
• zhixinshu.github.io Zhixin Shu
• twizwei.github.io Yiran Xu
• jiabinhuang.com 琼中坑猎物流有限公司