Generative AI can help produce things like poetry, images and music that previously required human effort to create. These systems use NVIDIA GPUs and AI software to train deep learning models on massive data sets to create an AI-generated output with intrinsic value.
Beyond conversational text, generative AI can help people create computer code, audio, music, illustrations, video, 3D wireframe models and characters.
Generative AI requires massively parallel systems for both training and inference. ChatGPT was trained on 10,000 NVIDIA GPUs for several weeks, but the large language models behind these types of applications are doubling in size and complexity every few months. Applying generative AI to business will require the world’s data centers to become AI factories.
With “Instant Neural Graphics Primitives” (Instant-NGP), the NVIDIA research group demonstrate near-instant training of neural graphics primitives on a single GPU for multiple tasks — gigapixel images, 3D objects, and NeRFs.
In gigapixel image we represent an image by a neural network. SDF learns a signed distance function in 3D space whose zero level-set represents a 2D surface. NeRF uses 2D images and their camera poses to reconstruct a volumetric radiance-and-density field that is visualized using ray marching. Lastly, neural volume learns a denoised radiance and density field directly from a volumetric path tracer.
Approximating an RGB image of resolution 20,000 x 23,466 (469M RGB pixels) with our multiresolution has encoding' with different table sizes. The painting is 'Girl With a Pearl Earring' renovation by Koorosh Orooj
Outpainting with DALLᐧE
