Posts
OpenAI Releases Point-E, an AI For 3D Modeling (engadget.com)11
OpenAI, the Elon Musk-founded artificial intelligence startup behind popular DALL-E text-to-image generator, announced (PDF) on Tuesday the release of its newest picture-making machine POINT-E, which can produce 3D point clouds directly from text prompts. Engadget reports:Whereas existing systems like Google's DreamFusion typically require multiple hours -- and GPUs to generate their images, Point-E only needs one GPU and a minute or two. Point-E, unlike similar systems, "leverages a large corpus of (text, image) pairs, allowing it to follow diverse and complex prompts, while our image-to-3D model is trained on a smaller dataset of (image, 3D) pairs," the OpenAI research team led by Alex Nichol wrote in Point-E: A System for Generating 3D Point Clouds from Complex Prompts, published last week. "To produce a 3D object from a text prompt, we first sample an image using the text-to-image model, and then sample a 3D object conditioned on the sampled image. Both of these steps can be performed in a number of seconds, and do not require expensive optimization procedures."
If you were to input a text prompt, say, "A cat eating a burrito," Point-E will first generate a synthetic view 3D rendering of said burrito-eating cat. It will then run that generated image through a series of diffusion models to create the 3D, RGB point cloud of the initial image -- first producing a coarse 1,024-point cloud model, then a finer 4,096-point. "In practice, we assume that the image contains the relevant information from the text, and do not explicitly condition the point clouds on the text," the research team points out. These diffusion models were each trained on "millions" of 3d models, all converted into a standardized format. "While our method performs worse on this evaluation than state-of-the-art techniques," the team concedes, "it produces samples in a small fraction of the time."OpenAI has posted the projects open-source code on Github.
If you were to input a text prompt, say, "A cat eating a burrito," Point-E will first generate a synthetic view 3D rendering of said burrito-eating cat. It will then run that generated image through a series of diffusion models to create the 3D, RGB point cloud of the initial image -- first producing a coarse 1,024-point cloud model, then a finer 4,096-point. "In practice, we assume that the image contains the relevant information from the text, and do not explicitly condition the point clouds on the text," the research team points out. These diffusion models were each trained on "millions" of 3d models, all converted into a standardized format. "While our method performs worse on this evaluation than state-of-the-art techniques," the team concedes, "it produces samples in a small fraction of the time."OpenAI has posted the projects open-source code on Github.
