We show that a text-conditioned diffusion model trained on pixel representations of images can be used to generate SVG-exportable vector graphics.
Using this loss in a DeepDream-like procedure, we optimize a randomly-initialized 3D model (a Neural Radiance Field, or NeRF) via gradient descent such that its 2D renderings from random angles achieve a low loss.
Ranked #5 on Text to 3D on T$^3$Bench
Autoregressive generative models can estimate complex continuous data distributions, like trajectory rollouts in an RL environment, image intensities, and audio.
Our method, Dream Fields, can generate the geometry and color of a wide range of objects without 3D supervision.
Recent work learns contextual representations of source code by reconstructing tokens from their context.
Ranked #1 on Method name prediction on CodeSearchNet
For tasks such as image completion, these models are unable to use much of the observed context.
Ranked #1 on Image Generation on MNIST
We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics.
Ranked #2 on Image Generation on LSUN Bedroom
To operate effectively in the real world, agents should be able to act from high-dimensional raw sensory input such as images and achieve diverse goals across long time-horizons.
Particularly difficult is the prediction of human behavior.
We formalize the problem of trading-off DNN training time and memory requirements as the tensor rematerialization optimization problem, a generalization of prior checkpointing strategies.
In a typical deep learning approach to a computer vision task, Convolutional Neural Networks (CNNs) are used to extract features at varying levels of abstraction from an image and compress a high dimensional input into a lower dimensional decision space through a series of transformations.
Current trends in Machine Learning~(ML) inference on hardware accelerated devices (e. g., GPUs, TPUs) point to alarmingly low utilization.