Could I synthesize novel view images without generating mesh?

vt-vl-lab / 3d-photo-inpainting

[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting

https://shihmengli.github.io/3D-Photo-Inpainting/

Other

6.91k stars 1.11k forks source link

Could I synthesize novel view images without generating mesh? #75

Closed gaojie2244 closed 4 years ago

gaojie2244 commented 4 years ago

Hi,I find it takes a long time to create the mesh when I run the code, although I set "save_ply: False". How could I synthesize novel view images without generating mesh?Is it necessary to generate mesh? Or other ways to reduce running time? Thanks a lot!