Once the subject is embedded in the output domain of the model, the unique identifier can then be used to synthesize fully-novel photorealistic images of the subject contextualized in different scenes.
We explore a data-driven approach for learning to optimize neural networks.
We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet.
Although a series of successful portrait image toonification models built upon the powerful StyleGAN have been proposed, these image-oriented methods have obvious limitations when applied to videos, such as the fixed frame size, the requirement of face alignment, missing non-facial details and temporal inconsistency.
Our method, Dream Fields, can generate the geometry and color of a wide range of objects without 3D supervision.
Compared to other models on the leaderboard, DINO significantly reduces its model size and pre-training data size while achieving better results.
Ranked #1 on Object Detection on COCO minival (using extra training data)
We interpret the data points as electrical charges on the $z=0$ hyperplane in a space augmented with an additional dimension $z$, generating a high-dimensional electric field (the gradient of the solution to Poisson equation).
Ranked #18 on Image Generation on CIFAR-10