If you have a few examples you can use an already trained encoder (like CLIP ima...

GaggiX on March 21, 2023 | parent | context | favorite | on: Zero-1-to-3: Zero-shot One Image to 3D Object

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.