Nvidia Corporation

Other

Huan Ling

Sanja Fidler

Karsten Julian Kreis

Antonio Torralba Barriuso

Wenzheng Chen

Seung Wook Kim

Jun Gao

Amlan Kar

David Jesus Acuna Marrero

Daiqing Li

Yuxuan Zhang

Kangxue Yin

Sameh Khamis

Tim Dockhorn

Masha Shugrina

David Acuna Marrero

Robin Rombach

Andreas Blattmann

Approaches are presented for training an inverse graphics network. An image synthesis network can generate training data for an inverse graphics network. In turn, the inverse graphics network can teach the synthesis network about the physical three-dimensional (3D) controls. Such an approach can provide for accurate 3D reconstruction of objects from 2D images using the trained inverse graphics network, while requiring little annotation of the provided training data. Such an approach can extract and disentangle 3D knowledge learned by generative models by utilizing differentiable renderers, enabling a disentangled generative model to function as a controllable 3D 'neural renderer,' complementing traditional graphics renderers.

Neural rendering for inverse graphics generation

In various examples, systems and methods are disclosed relating to generating a response from image and/or video input for image/video-based artificial intelligence (AI) systems and applications. Systems and methods are disclosed for a first model (e.g., a teacher model) distilling its knowledge to a second model (a student model). The second model receives a downstream image in a downstream task and generates at least one feature. The first model generates first features corresponding to an image which can be a real image or a synthetic image. The second model generates second features using the image as an input to the second model. Loss with respect to first features is determined. The second model is updated using the loss.

Unsupervised pre-training of neural networks using generative models

Apparatuses, systems, and techniques to generate complete depictions of objects based on a partial depiction of the object. In at least one embodiment, an image of a complete object is generated by one or more neural networks, based on an image of a portion of the object, using an encoder of the one or more neural networks trained using training data generated from output of a decoder of the one or more neural networks.

Object image completion

Generation of three-dimensional (3D) object models may be challenging for users without a sufficient skill set for content creation and may also be resource intensive. One or more style transfer networks may be combined with a generative network to generate objects based on parameters associated with a textual input. An input including a 3D mesh and texture may be provided to a trained system along with a textual input that includes parameters for object generation. Features of the input object may be identified and then tuned in accordance with the textual input to generate a modified 3D object that includes a new texture along with one or more geometric adjustments.

Text-driven 3D object stylization using neural networks

In various examples, high-precision semantic image editing for machine learning systems and applications are described. For example, a generative adversarial network (GAN) may be used to jointly model images and their semantic segmentations based on a same underlying latent code. Image editing may be achieved by using segmentation mask modifications (e.g., provided by a user, or otherwise) to optimize the latent code to be consistent with the updated segmentation, thus effectively changing the original, e.g., RGB image. To improve efficiency of the system, and to not require optimizations for each edit on each image, editing vectors may be learned in latent space that realize the edits, and that can be directly applied on other images with or without additional optimizations. As a result, a GAN in combination with the optimization approaches described herein may simultaneously allow for high precision editing in real-time with straightforward compositionality of multiple edits.

High-precision semantic image editing using neural networks for synthetic data generation systems and applications

In various examples, systems and methods are disclosed relating to aligning images into frames of a first video using at least one first temporal attention layer of a neural network model. The first video has a first spatial resolution. A second video having a second spatial resolution is generated by up-sampling the first video using at least one second temporal attention layer of an up-sampler neural network model, wherein the second spatial resolution is higher than the first spatial resolution.

High-resolution video generation using image diffusion models

The present invention relates generally to object annotation, specifically to polygonal annotations of objects. Described are methods of annotating an object including steps of receiving an image depicting an object, generating a set of image features using a CNN encoder implemented on one or more computers, and producing a polygon object annotation via a recurrent decoder or a Graph Neural Network. The recurrent decoder may include a recurrent neural network, a graph neural network or a gated graph neural network. A system for annotating an object and a method of training an object annotation system are also described.

Systems and methods for polygon object annotation and a method of training an object annotation system

Systems and methods for polygon object annotation and a method of training and object annotation system

Growing community of inventors

Toronto, Canada

Huan Ling