ashawkey / nerf2mesh

[ICCV2023] Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement
https://me.kiui.moe/nerf2mesh/
MIT License
879 stars 87 forks source link

Inference #95

Open kim-sehun opened 8 months ago

kim-sehun commented 8 months ago

After training, is it possible to infer other images using checkpoint values?

AI should make inferences using trained models, but as it stands now, it feels like you have to train to construct an image into a 3D model, and you have to do this “every time.” I would appreciate it if you could let me know if my thinking is wrong.