-
公开(公告)号：US12266039B2
公开(公告)日：2025-04-01
申请号：US17985579
申请日：2022-11-11
Applicant: Adobe Inc.
Inventor： Valentin Deschaintre , Yiwei Hu , Paul Guerrero , Milos Hasan
Abstract: Certain aspects and features of this disclosure relate to rendering images using target-augmented material maps. In one example, a graphics imaging application is loaded with a scene and an input material map, as well as a file for a target image. A stored, material generation prior is accessed by the graphics imaging application. This prior, as an example, is based on a pre-trained, generative adversarial network (GAN). An input material appearance from the input material map is encoded to produce a projected latent vector. The value for the projected latent vector is optimized to produce the material map that is used to render the scene, producing a material map augmented by a realistic target material appearance.
-
公开(公告)号：US20250078387A1
公开(公告)日：2025-03-06
申请号：US18242764
申请日：2023-09-06
Applicant: Adobe Inc.
Inventor： Valentin Deschaintre , Yannick Hold-Geoffroy , Paul Guerrero
IPC: G06T15/04 , G06F16/535 , G06F16/583
Abstract: A material search computing system generates a joint feature comparison space by combining joint image-text features of surface material data objects. The joint feature comparison space is a consistent comparison space. The material search computing system extracts a query joint feature set from a query data object that includes text data or image data. In addition, the material search computing system compares the query joint feature set to the joint image-text features included in the joint feature comparison space. Based on the comparison, the material search computing system identifies a result joint feature set and associated result surface material data objects. The material search computing system generates material query result data describing the result surface material data objects, and provides the material query result data to an additional computing system.
-
公开(公告)号：US12277671B2
公开(公告)日：2025-04-15
申请号：US17454434
申请日：2021-11-10
Applicant: ADOBE INC.
Inventor： Shouchang Guo , Arthur Jules Martin Roullier , Tamy Boubekeur , Valentin Deschaintre , Jerome Derel , Paul Parneix
IPC: G06T3/4046 , G06T5/77 , G06T7/11 , G06T7/40
Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure include an image processing apparatus configured to efficiently perform texture synthesis (e.g., increase the size of, or extend, texture in an input image while preserving a natural appearance of the synthesized texture pattern in the modified output image). In some aspects, the image processing apparatus implements an attention mechanism with a multi-stage attention model where different stages (e.g., different transformer blocks) progressively refine image feature patch mapping at different scales, while utilizing repetitive patterns in texture images to enable network generalization. One or more embodiments of the disclosure include skip connections and convolutional layers (e.g., between transformer block stages) that combine high-frequency and low-frequency features from different transformer stages and unify attention to micro-structures, meso-structures and macro-structures. In some aspects, the skip connections enable information propagation in the transformer network.
-
公开(公告)号：US20240412444A1
公开(公告)日：2024-12-12
申请号：US18207923
申请日：2023-06-09
Applicant: Adobe Inc.
Inventor： Julien Philip , Valentin Deschaintre
Abstract: Methods and systems disclosed herein relate generally to radiance field gradient scaling for unbiased near-camera training. In a method, a processing device accesses an input image of a three-dimensional environment comprising a plurality of pixels, each pixel comprising a pixel color. The processing device determines a camera location based on the input image and a ray from the camera location in a direction of a pixel. The processing device integrates sampled information from a volumetric representation along the ray from the camera location to obtain an integrated color. The processing device trains a machine learning model configured to predict a density and a color, comprising minimizing a loss function using a scaling factor that is determined based on a distance between the camera location and a point along the ray. The processing device outputs the trained ML model for use in rendering an output image.
-
Patent Agency Ranking
5.发明申请公开(公告)号：US20250069373A1
公开(公告)日：2025-02-27
申请号：US18455023
申请日：2023-08-24
Applicant: Adobe Inc.
Inventor： Giuseppe Vecchio , Adrien Kaiser , Arthur Roullier , Romain Rouffet , Valentin Deschaintre , Rosalie Martin , Tamy Boubekeur
IPC: G06V10/774 , G06T5/00 , G06T5/50 , G06T11/60 , G06V10/82
Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate digital materials from digital images using a diffusion neural network. For instance, in one or more embodiments, the disclosed systems receive a digital image portraying a scene to be replicated as a digital material. The disclosed systems also generate, using a conditioning neural network, a spatial condition from the digital image. Using a controlled diffusion neural network and based on the spatial condition, the disclosed systems generate a plurality of material maps corresponding to the scene portrayed by the digital image.
-
公开(公告)号：US20240338888A1
公开(公告)日：2024-10-10
申请号：US18132714
申请日：2023-04-10
Applicant: Adobe Inc.
Inventor： Krishna Bhargava Mullia Lakshminarayana , Valentin Deschaintre , Nathan Carr , Milos Hasan , Bailey Miller
Abstract: Certain aspects and features of this disclosure relate to rendering images by training a neural material and applying the material map to a coarse geometry to provide high-fidelity asset encoding. For example, training can involve sampling for a set of lighting and camera configurations arranged to render an image of a target asset. A value for a loss function comparing the target asset with the neural material can be optimized to train the neural material to encode a high-fidelity model of the target asset. This technique restricts the application of the neural material to a specific predetermined geometry, resulting in a reproducible asset that can be used efficiently. Such an asset can be deployed, as examples, to mobile devices or to the web, where the computational budget is limited, and nevertheless produce highly detailed images.
-
公开(公告)号：US12125138B2
公开(公告)日：2024-10-22
申请号：US17864901
申请日：2022-07-14
Applicant: Adobe Inc.
Inventor： Valentin Deschaintre , Yiwei Hu , Paul Guerrero , Milos Hasan
Abstract: Embodiments are disclosed for optimizing a material graph for replicating a material of the target image. Embodiments include receiving a target image and a material graph to be optimized for replicating a material of the target image. Embodiments include identifying a non-differentiable node of the material graph, the non-differentiable node including a set of input parameters. Embodiments include selecting a differentiable proxy from a library of the selected differentiable proxy is trained to replicate an output of the identified non-differentiable node. Embodiments include generating an optimized input parameters for the identified non-differentiable node using the corresponding trained neural network and the target image. Embodiments include replacing the set of input parameters of the non-differentiable node of the material graph with the optimized input parameters. Embodiments include generating an output material by the material graph to represent the target image using the optimized input parameters for the non-differentiable node.
-
公开(公告)号：US20240161362A1
公开(公告)日：2024-05-16
申请号：US17985579
申请日：2022-11-11
Applicant: Adobe Inc.
Inventor： Valentin Deschaintre , Yiwei Hu , Paul Guerrero , Milos Hasan
CPC classification number: G06T11/60 , G06T3/40 , G06T9/00 , G06V10/761
Abstract: Certain aspects and features of this disclosure relate to rendering images using target-augmented material maps. In one example, a graphics imaging application is loaded with a scene and an input material map, as well as a file for a target image. A stored, material generation prior is accessed by the graphics imaging application. This prior, as an example, is based on a pre-trained, generative adversarial network (GAN). An input material appearance from the input material map is encoded to produce a projected latent vector. The value for the projected latent vector is optimized to produce the material map that is used to render the scene, producing a material map augmented by a realistic target material appearance.
-
公开(公告)号：US20230144637A1
公开(公告)日：2023-05-11
申请号：US17454434
申请日：2021-11-10
Applicant: ADOBE INC.
Inventor： Shouchang Guo , Arthur Jules Martin ROULLIER , Tamy Boubekeur , Valentin Deschaintre , Jerome Derel , Paul Parneix
CPC classification number: G06T3/4046 , G06T5/005 , G06T7/11 , G06T7/40
Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure include an image processing apparatus configured to efficiently perform texture synthesis (e.g., increase the size of, or extend, texture in an input image while preserving a natural appearance of the synthesized texture pattern in the modified output image). In some aspects, the image processing apparatus implements an attention mechanism with a multi-stage attention model where different stages (e.g., different transformer blocks) progressively refine image feature patch mapping at different scales, while utilizing repetitive patterns in texture images to enable network generalization. One or more embodiments of the disclosure include skip connections and convolutional layers (e.g., between transformer block stages) that combine high-frequency and low-frequency features from different transformer stages and unify attention to micro-structures, meso-structures and macro-structures. In some aspects, the skip connections enable information propagation in the transformer network.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.013 seconds)
