公开(公告)号：US20250111588A1

公开(公告)日：2025-04-03

申请号：US18479261

申请日：2023-10-02

Applicant: Nvidia Corporation

Inventor： Karsten Julian Kreis ,  Maria Shugrina ,  Ming-Yu Liu ,  Or Perel ,  Sanja Fidler ,  Towaki Alan Takikawa ,  Tsung-Yi Lin ,  Xiaohui Zeng

IPC: G06T15/06 ,  G06T15/00

Abstract: Systems and methods of the present disclosure include interactive editing for generated three-dimensional (3D) models, such as those represented by neural radiance fields (NeRFs). A 3D model may be presented to a user in which the user may identify one or more localized regions for editing and/or modification. The localized regions may be selected and a corresponding 3D volume for that region may be provided to one or more generative networks, along with a prompt, to generate new content for the localized regions. Each of the original NeRF and the newly generated NeRF for the new content may then be combined into a single NeRF for a combined 3D representation with the original content and the localized modifications.

公开(公告)号：US20250166288A1

公开(公告)日：2025-05-22

申请号：US18513105

申请日：2023-11-17

Applicant: Nvidia Corporation

Inventor： Or Perel ,  Maria Shugrina ,  Yoni Kasten ,  Or Litany ,  Gal Chechik ,  Sanja Fidler

IPC: G06T15/08 ,  G06T15/20

Abstract: Systems and methods of the present disclosure include providing higher levels of detail (LODs) for generated three-dimensional (3D) models, such as those represented by neural radiance fields (NeRFs). A 3D model may be presented to a user in which the user may request additional LODs, such as to zoom into the image or to receive information about features within the image. A request to generate finer levels of detail may include using one or more diffusion models to generate images at higher resolutions and/or to hallucinate finer details based on information extracted from the original image or text prompts. Newly generated images may then be added to a set of images associated with the 3D models to enable later model generation to have finer details.

公开(公告)号：US20250029334A1

公开(公告)日：2025-01-23

申请号：US18356588

申请日：2023-07-21

Applicant: Nvidia Corporation

Inventor： Xingguang Yan ,  Or Perel ,  James Robert Lucas ,  Towaki Takikawa ,  Karsten Julian Kreis ,  Maria Shugrina ,  Sanja Fidler ,  Or Litany

IPC: G06T17/20 ,  G06T3/40

Abstract: Approaches presented herein provide systems and methods for generating three-dimensional (3D) objects using compressed data as an input. One or more models may learn from a hash table of latent features to map different features to a reconstruction domain, using a hash function as part of a learned process. A 3D shape for an object may be encoded to a multi-layered grid and represented by a series of embeddings, where given point within the grid may be interpolated based on the embeddings for a given layer of the multi-layered grid. A decoder may then be trained to use the embeddings to generate an output object.

公开(公告)号：US20250061153A1

公开(公告)日：2025-02-20

申请号：US18935222

申请日：2024-11-01

Applicant: Nvidia Corporation

Inventor： Hang Chu ,  Daiqing Li ,  David Jesus Acuna Marrero ,  Amlan Kar ,  Maria Shugrina ,  Ming-Yu Liu ,  Antonio Torralba Barriuso ,  Sanja Fidler

IPC: G06F16/901 ,  G06F30/13 ,  G06F30/27 ,  G06N3/044 ,  G06N3/045 ,  G06N3/047 ,  G06N3/08 ,  G06N3/084 ,  G06N5/04 ,  G06N20/10 ,  G06N20/20 ,  G06V10/764 ,  G06V10/82 ,  G06V10/84 ,  G06V20/10

Abstract: A generative model can be used for generation of spatial layouts and graphs. Such a model can progressively grow these layouts and graphs based on local statistics, where nodes can represent spatial control points of the layout, and edges can represent segments or paths between nodes, such as may correspond to road segments. A generative model can utilize an encoder-decoder architecture where the encoder is a recurrent neural network (RNN) that encodes local incoming paths into a node and the decoder is another RNN that generates outgoing nodes and edges connecting an existing node to the newly generated nodes. Generation is done iteratively, and can finish once all nodes are visited or another end condition is satisfied. Such a model can generate layouts by additionally conditioning on a set of attributes, giving control to a user in generating the layout.

公开(公告)号：US11928764B2

公开(公告)日：2024-03-12

申请号：US17021845

申请日：2020-09-15

Applicant: NVIDIA Corporation

Inventor： Tingwu Wang ,  Yun Rong Guo ,  Maria Shugrina ,  Sanja Fidler

IPC: G06T13/20 ,  G06F18/211 ,  G06F18/214 ,  G06N3/084 ,  G06N5/046 ,  G06T7/20

CPC classification number: G06T13/20 ,  G06F18/211 ,  G06F18/2148 ,  G06N3/084 ,  G06N5/046 ,  G06T7/20 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Apparatuses, systems, and techniques to animate objects in computer-generated graphics. In at least one embodiment, one or more neural networks are trained to identify one or more forces to be applied to one or more objects based, at least in part, on training data corresponding to two or more aspects of motion of the one or more objects.

公开(公告)号：US20220084272A1

公开(公告)日：2022-03-17

申请号：US17021845

申请日：2020-09-15

Applicant: NVIDIA Corporation

Inventor： Tingwu Wang ,  Yun Rong Guo ,  Maria Shugrina ,  Sanja Fidler

IPC: G06T13/20 ,  G06T7/20 ,  G06K9/62 ,  G06N3/08 ,  G06N5/04

Abstract: Apparatuses, systems, and techniques to animate objects in computer-generated graphics. In at least one embodiment, one or more neural networks are trained to identify one or more forces to be applied to one or more objects based, at least in part, on training data corresponding to two or more aspects of motion of the one or more objects.

公开(公告)号：US20200302250A1

公开(公告)日：2020-09-24

申请号：US16825199

申请日：2020-03-20

Applicant: Nvidia Corporation

Inventor： Hang Chu ,  Daiqing Li ,  David Jesus Acuna Marrero ,  Amlan Kar ,  Maria Shugrina ,  Ming-Yu Liu ,  Antonio Torralba Barriuso ,  Sanja Fidler

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06N5/04 ,  G06N20/10 ,  G06N20/20

Abstract: A generative model can be used for generation of spatial layouts and graphs. Such a model can progressively grow these layouts and graphs based on local statistics, where nodes can represent spatial control points of the layout, and edges can represent segments or paths between nodes, such as may correspond to road segments. A generative model can utilize an encoder-decoder architecture where the encoder is a recurrent neural network (RNN) that encodes local incoming paths into a node and the decoder is another RNN that generates outgoing nodes and edges connecting an existing node to the newly generated nodes. Generation is done iteratively, and can finish once all nodes are visited or another end condition is satisfied. Such a model can generate layouts by additionally conditioning on a set of attributes, giving control to a user in generating the layout.