You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I had an idea of trying something in the realm of PixelNeRF which is a Neural Radiance Fields model from One or Few Images.
The essence of my idea involves training a NeRF for a rather specific purpose, say, the rendering of different types of buckets. The objective is to put in rigorous efforts in training and save the trained model. Here's where it gets interesting: my vision entails that once the network is primed and ready, if presented with only one or two images of a different bucket, yet remarkably similar to those used during training, it should be capable of rendering the appearance of that new bucket.
All of this would be without background so it does not interfere with the training process.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hello,
I had an idea of trying something in the realm of PixelNeRF which is a Neural Radiance Fields model from One or Few Images.
The essence of my idea involves training a NeRF for a rather specific purpose, say, the rendering of different types of buckets. The objective is to put in rigorous efforts in training and save the trained model. Here's where it gets interesting: my vision entails that once the network is primed and ready, if presented with only one or two images of a different bucket, yet remarkably similar to those used during training, it should be capable of rendering the appearance of that new bucket.
All of this would be without background so it does not interfere with the training process.
Is this idea possible inside of nerfstudio?
Kind regards,
Rob
Beta Was this translation helpful? Give feedback.
All reactions