Zero-1-to-3: Zero-shot One Image to 3D Object

Re:Zero-1-to-3: Zero-shot One Image to 3D Object by GaggiX on Tuesday March 21, 2023 @10:21AM (#35246540)

If you have a few examples you can use an already trained encoder (like CLIP image encoder) and train a SVM on the embeddings, no need to train a neural network.

[ Parent | on HN ]

There are no comments on this comment yet.