-
公开(公告)号：US10311574B2
公开(公告)日：2019-06-04
申请号：US15853206
申请日：2017-12-22
Applicant: Adobe Inc.
Inventor： Xiaohui Shen , Zhe Lin , Yi-Hsuan Tsai , Kalyan K. Sunkavalli
Abstract: A digital medium environment includes an image processing application that performs object segmentation on an input image. An improved object segmentation method implemented by the image processing application comprises receiving an input image that includes an object region to be segmented by a segmentation process, processing the input image to provide a first segmentation that defines the object region, and processing the first segmentation to provide a second segmentation that provides pixel-wise label assignments for the object region. In some implementations, the image processing application performs improved sky segmentation on an input image containing a depiction of a sky.
-
公开(公告)号：US20240193850A1
公开(公告)日：2024-06-13
申请号：US18065456
申请日：2022-12-13
Applicant: Adobe Inc.
Inventor： Zhengfei Kuang , Fujun Luan , Sai Bi , Zhixin Shu , Kalyan K. Sunkavalli
CPC classification number: G06T15/08 , G06T15/06 , G06T15/503 , G06T15/80 , G06T19/20 , G06T2219/2012
Abstract: Embodiments of the present disclosure provide systems, methods, and computer storage media for generating editable synthesized views of scenes by inputting image rays into neural networks using neural basis decomposition. In embodiments, a set of input images of a scene depicting at least one object are collected and used to generate a plurality of rays of the scene. The rays each correspond to three-dimensional coordinates and viewing angles taken from the images. A volume density of the scene is determined by inputting the three-dimensional coordinates from the neural radiance fields into a first neural network to generate a 3D geometric representation of the object. An appearance decomposition is produced by inputting the three-dimensional coordinates and the viewing angles of the rays into a second neural network.
-
公开(公告)号：US10950037B2
公开(公告)日：2021-03-16
申请号：US16510586
申请日：2019-07-12
Applicant: ADOBE INC.
Inventor： Kalyan K. Sunkavalli , Zexiang Xu , Sunil Hadap
Abstract: Embodiments are generally directed to generating novel images of an object having a novel viewpoint and a novel lighting direction based on sparse images of the object. A neural network is trained with training images rendered from a 3D model. Utilizing the 3D model, training images, ground truth predictive images from particular viewpoint(s), and ground truth predictive depth maps of the ground truth predictive images, can be easily generated and fed back through the neural network for training. Once trained, the neural network can receive a sparse plurality of images of an object, a novel viewpoint, and a novel lighting direction. The neural network can generate a plane sweep volume based on the sparse plurality of images, and calculate depth probabilities for each pixel in the plane sweep volume. A predictive output image of the object, having the novel viewpoint and novel lighting direction, can be generated and output.
-
公开(公告)号：US20210073955A1
公开(公告)日：2021-03-11
申请号：US16564398
申请日：2019-09-09
Applicant: ADOBE INC.
Inventor： Jinsong Zhang , Kalyan K. Sunkavalli , Yannick Hold-Geoffroy , Sunil Hadap , Jonathan Eisenmann , Jean-Francois Lalonde
IPC: G06T5/00
Abstract: Methods and systems are provided for determining high-dynamic range lighting parameters for input low-dynamic range images. A neural network system can be trained to estimate high-dynamic range lighting parameters for input low-dynamic range images. The high-dynamic range lighting parameters can be based on sky color, sky turbidity, sun color, sun shape, and sun position. Such input low-dynamic range images can be low-dynamic range panorama images or low-dynamic range standard images. Such a neural network system can apply the estimates high-dynamic range lighting parameters to objects added to the low-dynamic range images.
-
公开(公告)号：US20210012561A1
公开(公告)日：2021-01-14
申请号：US16510586
申请日：2019-07-12
Applicant: ADOBE INC.
Inventor： Kalyan K. Sunkavalli , Zexiang Xu , Sunil Hadap
Abstract: Embodiments are generally directed to generating novel images of an object having a novel viewpoint and a novel lighting direction based on sparse images of the object. A neural network is trained with training images rendered from a 3D model. Utilizing the 3D model, training images, ground truth predictive images from particular viewpoint(s), and ground truth predictive depth maps of the ground truth predictive images, can be easily generated and fed back through the neural network for training. Once trained, the neural network can receive a sparse plurality of images of an object, a novel viewpoint, and a novel lighting direction. The neural network can generate a plane sweep volume based on the sparse plurality of images, and calculate depth probabilities for each pixel in the plane sweep volume. A predictive output image of the object, having the novel viewpoint and novel lighting direction, can be generated and output.
-
Patent Agency Ranking
公开(公告)号：US10964060B2
公开(公告)日：2021-03-30
申请号：US16675641
申请日：2019-11-06
Applicant: ADOBE INC.
Inventor： Kalyan K. Sunkavalli , Yannick Hold-Geoffroy , Sunil Hadap , Matthew David Fisher , Jonathan Eisenmann , Emiliano Gambaretto
Abstract: Embodiments of the present invention provide systems, methods, and computer storage media directed to generating training image data for a convolutional neural network, encoding parameters into a convolutional neural network, and employing a convolutional neural network that estimates camera calibration parameters of a camera responsible for capturing a given digital image. A plurality of different digital images can be extracted from a single panoramic image given a range of camera calibration parameters that correspond to a determined range of plausible camera calibration parameters. With each digital image in the plurality of extracted different digital images having a corresponding set of known camera calibration parameters, the digital images can be provided to the convolutional neural network to establish high-confidence correlations between detectable characteristics of a digital image and its corresponding set of camera calibration parameters. Once trained, the convolutional neural network can receive a new digital image, and based on detected image characteristics thereof, estimate a corresponding set of camera calibration parameters with a calculated level of confidence.
-
公开(公告)号：US10762608B2
公开(公告)日：2020-09-01
申请号：US16119709
申请日：2018-08-31
Applicant: Adobe Inc.
Inventor： Xiaohui Shen , Yi-Hsuan Tsai , Kalyan K. Sunkavalli , Zhe Lin
IPC: G06F3/0482 , G06F3/0484 , G06T11/00 , G06T5/00 , G06T7/90 , G06F16/583
Abstract: Embodiments of the present disclosure relate to a sky editing system and related processes for sky editing. The sky editing system includes a composition detector to determine the composition of a target image. A sky search engine in the sky editing system is configured to find a reference image with similar composition with the target image. Subsequently, a sky editor replaces content of the sky in the target image with content of the sky in the reference image. As such, the sky editing system transforms the target image into a new image with a preferred sky background.
-
公开(公告)号：US20200151509A1
公开(公告)日：2020-05-14
申请号：US16188130
申请日：2018-11-12
Applicant: ADOBE INC.
Inventor： Kalyan K. Sunkavalli , Sunil Hadap , Jonathan Eisenmann , Jinsong Zhang , Emiliano Gambaretto
Abstract: Methods and systems are provided for determining high-dynamic range lighting parameters for input low-dynamic range images. A neural network system can be trained to estimate lighting parameters for input images where the input images are synthetic and real low-dynamic range images. Such a neural network system can be trained using differences between a simple scene rendered using the estimated lighting parameters and the same simple scene rendered using known ground-truth lighting parameters. Such a neural network system can also be trained such that the synthetic and real low-dynamic range images are mapped in roughly the same distribution. Such a trained neural network system can be used to input a low-dynamic range image determine high-dynamic range lighting parameters.
-
公开(公告)号：US10607329B2
公开(公告)日：2020-03-31
申请号：US15457192
申请日：2017-03-13
Applicant: ADOBE INC.
Inventor： Kalyan K. Sunkavalli , Xiaohui Shen , Mehmet Ersin Yumer , Marc-André Gardner , Emiliano Gambaretto
Abstract: Methods and systems are provided for using a single image of an indoor scene to estimate illumination of an environment that includes the portion captured in the image. A neural network system may be trained to estimate illumination by generating recovery light masks indicating a probability of each pixel within the larger environment being a light source. Additionally, low-frequency RGB images may be generated that indicating low-frequency information for the environment. The neural network system may be trained using training input images that are extracted from known panoramic images. Once trained, the neural network system infers plausible illumination information from a single image to realistically illumination images and objects being manipulated in graphics applications, such as with image compositing, modeling, and reconstruction.
-
公开(公告)号：US10297045B2
公开(公告)日：2019-05-21
申请号：US14546934
申请日：2014-11-18
Applicant: Adobe Inc.
Inventor： Kalyan K. Sunkavalli
Abstract: Fast intrinsic images techniques are described. In one or more implementations, a combination of local constraints on shading and reflectance and non-local constraints on reflectance are applied to an image to generate a linear system of equations. The linear system of equations can be solved to generate a reflectance intrinsic image and a shading intrinsic image for the image. In one or more implementations, a multi-scale parallelized iterative solver is used to solve the linear system of equations to generate the reflectance intrinsic image and the shading intrinsic image.
-
-
-
-
-
-
-
-
-
Search Results
20
records
(took 0.015 seconds)
