-
公开(公告)号:US20240135492A1
公开(公告)日:2024-04-25
申请号:US18379519
申请日:2023-10-12
Applicant: Google LLC
Inventor: Cristina Nader Vasconcelos , Ahmet Cengiz Oztireli , Andrea Tagliasacchi , Kevin Jordan Swersky , Mark Jeffrey Matthews , Milad Olia Hashemi
IPC: G06T3/40 , G06T5/20 , G06V10/771
CPC classification number: G06T3/4053 , G06T5/20 , G06V10/771 , G06T2207/10024 , G06T2207/20084
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing an input image using a super-resolution neural network to generate an up-sampled image that is a higher resolution version of the input image. In one aspect, a method comprises: processing the input image using an encoder subnetwork of the super-resolution neural network to generate a feature map; generating an updated feature map, comprising, for each spatial position in the updated feature map: applying a convolutional filter to the feature map to generate a plurality of features corresponding to the spatial position in the updated feature map, wherein the convolutional filter is parametrized by a set of convolutional filter parameters that are generated by processing data representing the spatial position using a hyper neural network; and processing the updated feature map using a projection subnetwork of the super-resolution neural network to generate the up-sampled image.
-
公开(公告)号:US20240119697A1
公开(公告)日:2024-04-11
申请号:US18012264
申请日:2022-10-10
Applicant: Google LLC
Inventor: Daniel Christopher Duckworth , Suhani Deepak-Ranu Vora , Noha Radwan , Klaus Greff , Henning Meyer , Kyle Adam Genova , Seyed Mohammad Mehdi Sajjadi , Etienne François Régis Pot , Andrea Tagliasacchi
CPC classification number: G06V10/26 , G06T7/143 , G06T15/08 , G06T2207/20076 , G06T2207/20081
Abstract: Example embodiments of the present disclosure provide an example computer-implemented method for constructing a three-dimensional semantic segmentation of a scene from two-dimensional inputs. The example method includes obtaining, by a computing system comprising one or more processors, an image set comprising one or more views of a subject scene. The example method includes generating, by the computing system and based at least in part on the image set, a scene representation describing the subject scene in three dimensions. The example method includes generating, by the computing system and using a machine-learned semantic segmentation model framework, a multidimensional field of probability distributions over semantic categories, the multidimensional field defined over the three dimensions of the subject scene. The example method includes outputting, by the computing system, classification data for at least one location in the subject scene.
-
公开(公告)号:US12106428B2
公开(公告)日:2024-10-01
申请号:US17686683
申请日:2022-03-04
Applicant: Google LLC
Inventor: Konstantinos Rematas , Thomas Allen Funkhouser , Vittorio Carlo Ferrari , Andrew Huaming Liu , Andrea Tagliasacchi , Pratul Preeti Srinivasan , Jonathan Tilton Barron
CPC classification number: G06T15/205 , G06N20/00 , G06T5/50 , G06T5/92 , G06T17/10
Abstract: Systems and methods for view synthesis and three-dimensional reconstruction can learn an environment by utilizing a plurality of images of an environment and depth data. The use of depth data can be helpful when the quantity of images and different angles may be limited. For example, large outdoor environments can be difficult to learn due to the size, the varying image exposures, and the limited variance in view direction changes. The systems and methods can leverage a plurality of panoramic images and corresponding lidar data to accurately learn a large outdoor environment to then generate view synthesis outputs and three-dimensional reconstruction outputs. Training may include the use of an exposure correction network to address lighting exposure differences between training images.
-
公开(公告)号:US11508167B2
公开(公告)日:2022-11-22
申请号:US16847009
申请日:2020-04-13
Applicant: Google LLC
Inventor: Boyang Deng , Kyle Genova , Soroosh Yazdani , Sofien Bouaziz , Geoffrey E. Hinton , Andrea Tagliasacchi
Abstract: Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for generating convex decomposition of objects using neural network models. One of the methods includes receiving an input that depicts an object. The input is processed using a neural network to generate an output that defines a convex representation of the object. The output includes, for each of a plurality of convex elements, respective parameters that define a position of the convex element in the convex representation of the object.
-
公开(公告)号:US20210319209A1
公开(公告)日:2021-10-14
申请号:US16847009
申请日:2020-04-13
Applicant: Google LLC
Inventor: Boyang Deng , Kyle Genova , Soroosh Yazdani , Sofien Bouaziz , Geoffrey E. Hinton , Andrea Tagliasacchi
Abstract: Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for generating convex decomposition of objects using neural network models. One of the methods includes receiving an input that depicts an object. The input is processed using a neural network to generate an output that defines a convex representation of the object. The output includes, for each of a plurality of convex elements, respective parameters that define a position of the convex element in the convex representation of the object.
-
6.
公开(公告)号:US20230281913A1
公开(公告)日:2023-09-07
申请号:US17686683
申请日:2022-03-04
Applicant: Google LLC
Inventor: Konstantinos Rematas , Thomas Allen Funkhouser , Vittorio Carlo Ferrari , Andrew Huaming Liu , Andrea Tagliasacchi , Pratul Preeti Srinivasan , Jonathan Tilton Barron
CPC classification number: G06T15/205 , G06T17/10 , G06N20/00 , G06T5/50 , G06T5/009
Abstract: Systems and methods for view synthesis and three-dimensional reconstruction can learn an environment by utilizing a plurality of images of an environment and depth data. The use of depth data can be helpful when the quantity of images and different angles may be limited. For example, large outdoor environments can be difficult to learn due to the size, the varying image exposures, and the limited variance in view direction changes. The systems and methods can leverage a plurality of panoramic images and corresponding lidar data to accurately learn a large outdoor environment to then generate view synthesis outputs and three-dimensional reconstruction outputs. Training may include the use of an exposure correction network to address lighting exposure differences between training images.
-
公开(公告)号:US20230078756A1
公开(公告)日:2023-03-16
申请号:US17990532
申请日:2022-11-18
Applicant: Google LLC
Inventor: Boyang Deng , Kyle Genova , Soroosh Yazdani , Sofien Bouaziz , Geoffrey E. Hinton , Andrea Tagliasacchi
Abstract: Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for generating convex decomposition of objects using neural network models. One of the methods includes receiving an input that depicts an object. The input is processed using a neural network to generate an output that defines a convex representation of the object. The output includes, for each of a plurality of convex elements, respective parameters that define a position of the convex element in the convex representation of the object.
-
公开(公告)号:US20200349772A1
公开(公告)日:2020-11-05
申请号:US16861530
申请日:2020-04-29
Applicant: Google LLC
Inventor: Anastasia Tkach , Ricardo Martin Brualla , Shahram Izadi , Shuoran Yang , Cem Keskin , Sean Ryan Francesco Fanello , Philip Davidson , Jonathan Taylor , Rohit Pandey , Andrea Tagliasacchi , Pavlo Pidlypenskyi
Abstract: A method includes receiving a first image including color data and depth data, determining a viewpoint associated with an augmented reality (AR) and/or virtual reality (VR) display displaying a second image, receiving at least one calibration image including an object in the first image, the object being in a different pose as compared to a pose of the object in the first image, and generating the second image based on the first image, the viewpoint and the at least one calibration image.
-
公开(公告)号:US11978268B2
公开(公告)日:2024-05-07
申请号:US17990532
申请日:2022-11-18
Applicant: Google LLC
Inventor: Boyang Deng , Kyle Genova , Soroosh Yazdani , Sofien Bouaziz , Geoffrey E. Hinton , Andrea Tagliasacchi
Abstract: Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for generating convex decomposition of objects using neural network models. One of the methods includes receiving an input that depicts an object. The input is processed using a neural network to generate an output that defines a convex representation of the object. The output includes, for each of a plurality of convex elements, respective parameters that define a position of the convex element in the convex representation of the object.
-
公开(公告)号:US20230154051A1
公开(公告)日:2023-05-18
申请号:US17919460
申请日:2020-04-17
Applicant: Google LLC
Inventor: Danhang Tang , Saurabh Singh , Cem Keskin , Phillip Andrew Chou , Christian Haene , Mingsong Dou , Sean Ryan Francesco Fanello , Jonathan Taylor , Andrea Tagliasacchi , Philip Lindsley Davidson , Yinda Zhang , Onur Gonen Guleryuz , Shahram Izadi , Sofien Bouaziz
IPC: G06T9/00
Abstract: Systems and methods are directed to encoding and/or decoding of the textures/geometry of a three-dimensional volumetric representation. An encoding computing system can obtain voxel blocks from a three-dimensional volumetric representation of an object. The encoding computing system can encode voxel blocks with a machine-learned voxel encoding model to obtain encoded voxel blocks. The encoding computing system can decode the encoded voxel blocks with a machine-learned voxel decoding model to obtain reconstructed voxel blocks. The encoding computing system can generate a reconstructed mesh representation of the object based at least in part on the one or more reconstructed voxel blocks. The encoding computing system can encode textures associated with the voxel blocks according to an encoding scheme and based at least in part on the reconstructed mesh representation of the object to obtain encoded textures.
-
-
-
-
-
-
-
-
-