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.
Ranked #30 on Speech Recognition on LibriSpeech test-clean
Our method, Dream Fields, can generate the geometry and color of a wide range of objects without 3D supervision.
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.
In this work, we present the Textless Vision-Language Transformer (TVLT), where homogeneous transformer blocks take raw visual and audio inputs for vision-and-language representation learning with minimal modality-specific design, and do not use text-specific modules such as tokenization or automatic speech recognition (ASR).
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)
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond.