search

CompVis / geometry-free-view-synthesis

Is a geometric model required to synthesize novel views from a single image?
https://arxiv.org/abs/2104.07652
MIT License
376 stars 35 forks source link

[Question] Multiple Image Input #4

Closed chris-aeviator closed 3 years ago

chris-aeviator commented 3 years ago

How can I include multiple input images into the synth? When starting braindance.py path-to-my-imagefolder, a filemanager opens that just let's me select a single image.

I'd like to re-create a whole room by including the info's of multiple images.

pesser commented 3 years ago

This work specifically focused on the synthesis of novel views from a single input image. Currently it cannot take into account multiple images, but that's a very interesting direction for future works!

If you have many views available, you might be interested in Stable View Synthesis.