Label assignment after source and destination frame ids are selected?

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

Label assignment after source and destination frame ids are selected? #11

Open DRealArun opened 3 years ago

DRealArun commented 3 years ago

I am trying to understand the code and had one query about the dataloading in acid and real estate 10k dataset. I will try explaining it using the acid dataset case. The label assignment for large/small, forward/backward movement is done before actually sampling the source and destination frame ids. According to my understanding, this should be done after the frame id selection is done. Can you please let me know if I am missing something?

DRealArun commented 3 years ago

Another query, is a spare 3d model of the scene always necessary to train the models proposed in this project?