-
1.发明公开公开(公告)号：US20240169760A1
公开(公告)日：2024-05-23
申请号：US17977041
申请日：2022-10-31
发明人： Xinqi FAN , Ali Raza SHAHID , Hong YAN
CPC分类号： G06V40/174 , G06T3/0093 , G06T7/20 , G06V10/82 , G06V40/161 , G06V40/171 , G06T2207/20084 , G06T2207/30201
摘要： A system for image processing, a method of facial expression detection and a method of reconstruction image generation. The system comprises a facial expression extraction module arranged to, upon receiving a source sequence of images representing a predetermined facial expression performed by a sample target, extract a motion of at least one key facial feature of the sample target associated with the predetermined facial expression, and to enhance the detection of the motion including at least one subtle movement of the at least one key facial feature; and a facial expression data analyser arranged to collect facial micro-expression data associated with the predetermined facial expression and the motion including subtle movements of all key facial features of the sample target performing the predetermined facial expression.
-
公开(公告)号：US20240163395A1
公开(公告)日：2024-05-16
申请号：US18388668
申请日：2023-11-10
CPC分类号： H04N7/0135 , G06T3/0093 , G06T3/40
摘要： A system includes a hardware processor, a memory storing software code, and a machine learning (ML) model-based video frame interpolator. The hardware processor executes the software code to provide first and second frames of a video sequence including a plurality of frames, respective binary masks for the first and second frames, and optionally an intermediate frame of the video sequence between the first and second frames and a binary mask for the intermediate frame, as interpolation inputs to the ML model-based video frame interpolator. The hardware processor further executes the software code to generate, using the ML model-based video frame interpolator and the interpolation inputs, an interpolated frame and an error map for the interpolated frame, wherein generating the interpolated frame and the error map includes a cross-backward warping of respective latent feature representations of each of the plurality of frames.
-
公开(公告)号：US11983848B2
公开(公告)日：2024-05-14
申请号：US18151104
申请日：2023-01-06
申请人： MEDIATEK INC.
发明人： Cheng-Lung Jen , Pei-Kuei Tsung , Chih-Wei Chen , Yao-Sheng Wang , Shih-Che Chen , Yu-Sheng Lin , Chih-Wen Goo , Shih-Chin Lin , Tsung-Shian Huang , Ying-Chieh Chen
CPC分类号： G06T5/002 , G06T3/0093 , G06T3/4053 , G06T5/50 , G06T7/254 , G06T2207/20084 , G06T2207/20224
摘要： Aspects of the disclosure provide a frame processor for processing frames with aliasing artifacts. For example, the frame processor can include a super-resolution (SR) and anti-aliasing (AA) engine and an attention reference frame generator coupled to the SR and AA engine. The SR and AA engine can be configured to enhance resolution and remove aliasing artifacts of a frame to generate a first high-resolution frame with aliasing artifacts and a second high-resolution frame with aliasing artifacts removed. The attention reference frame generator can be configured to generate an attention reference frame based on the first high-resolution frame and the second high-resolution frame.
-
公开(公告)号：US11978175B2
公开(公告)日：2024-05-07
申请号：US17652964
申请日：2022-03-01
申请人： MAGIC LEAP, INC.
CPC分类号： G06T3/0093 , G06F3/012 , G06T19/006
摘要： A computer implemented method for warping multi-field color virtual content for sequential projection includes obtaining first and second color fields having different first and second colors. The method also includes determining a first time for projection of a warped first color field. The method further includes determining a second time for projection of a warped second color field. Moreover, the method includes predicting a first pose at the first time and predicting a second pose at the second time. In addition, the method includes generating the warped first color field by warping the first color field based on the first pose. The method also includes generating the warped second color field by warping the second color field based on the second pose.
-
5.发明授权公开(公告)号：US11972780B2
公开(公告)日：2024-04-30
申请号：US17486476
申请日：2021-09-27
申请人： Intel Corporation
发明人： Gowri Somanath , Oscar Nestares
IPC分类号： G06T3/00 , G06T3/40 , G06T3/4007 , G06T3/4046 , G06T7/246 , G06T13/00 , G11B27/036 , G11B27/00
CPC分类号： G11B27/036 , G06T3/0093 , G06T3/4007 , G06T3/4046 , G06T7/246 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084 , G06T2207/20221
摘要： A mechanism is described for facilitating cinematic space-time view synthesis in computing environments according to one embodiment. A method of embodiments, as described herein, includes capturing, by one or more cameras, multiple images at multiple positions or multiple points in times, where the multiple images represent multiple views of an object or a scene, where the one or more cameras are coupled to one or more processors of a computing device. The method further includes synthesizing, by a neural network, the multiple images into a single image including a middle image of the multiple images and representing an intermediary view of the multiple views.
-
公开(公告)号：US20240135632A1
公开(公告)日：2024-04-25
申请号：US18332273
申请日：2023-06-09
发明人： Young Chun AHN , Nahyup KANG , Seokhwan JANG , Jiyeon KIM
CPC分类号： G06T15/08 , G06T3/0093 , G06T7/194 , G06T7/50 , G06T15/06 , G06T2207/20081 , G06T2207/20084 , G06T2207/30244
摘要： A method and apparatus for neural rendering based on view augmentation are provided. A method of training a neural scene representation (NSR) model includes: receiving original training images of a target scene, the original training images respectively corresponding to base views of the target scene; generating augmented images of the target scene by warping the original training images, the augmented images respectively corresponding to new views of the target scene; performing background-foreground segmentation on the original training images and the augmented images to generate segmentation masks; and training a neural scene representation (NSR) model to be configured for volume rendering of the target scene by using the original training images, the augmented images, and the segmentation masks.
-
公开(公告)号：US11963889B2
公开(公告)日：2024-04-23
申请号：US17658030
申请日：2022-04-05
申请人： 3DMorphic Pty Ltd
发明人： William C. H. Parr
CPC分类号： A61F2/5046 , A61F2/30942 , B29C64/393 , B33Y50/02 , G06T3/0093 , G06T17/20 , A61F2002/30952 , A61F2002/505 , G06T2210/41
摘要： Disclosed herein are a method and system for producing a digital model of a customised device, comprising the steps of: importing a first digital file of a base part; importing a second digital file of a target shape; determining a warping interpolation function based on source point positions associated with the base part and target point positions associated with the target shape; and applying the warping interpolation function to the points of said base part to generate a model of said customised device.
-
公开(公告)号：US20240129487A1
公开(公告)日：2024-04-18
申请号：US18484134
申请日：2023-10-10
发明人： Zhao WANG , Bolin CHEN , Yan YE , Shiqi WANG
IPC分类号： H04N19/154 , G06T3/00 , G06T3/20 , G06T3/60 , H04N19/169
CPC分类号： H04N19/154 , G06T3/0093 , G06T3/20 , G06T3/60 , H04N19/169
摘要： Methods and apparatuses are provided for compressing video data based on keypoint features. An exemplary video compression method includes: receiving a video sequence; encoding one or more pictures of the video sequence; and generating a bitstream; wherein the encoding includes: representing a first picture by a first set of keypoints and a second set of keypoints, the second set comprising less keypoints than the first set; and compressing the video sequence based on the first set and second set of keypoints.
-
9.发明公开公开(公告)号：US20240119672A1
公开(公告)日：2024-04-11
申请号：US18483813
申请日：2023-10-10
IPC分类号： G06T17/20 , G06T3/00 , G06T7/90 , G06V10/56 , G06V10/60 , H04N13/257 , H04N13/275
CPC分类号： G06T17/20 , G06T3/0093 , G06T7/90 , G06V10/56 , G06V10/60 , H04N13/257 , H04N13/275 , G06T2207/10024
摘要： In one embodiment, a method by a computing system comprising a color camera and two monochrome cameras respectively associated with two eyes of a user includes computing a point cloud corresponding to a visible environment based at least on two stereoscopic grayscale images respectively captured by the two monochrome cameras, generating a mesh corresponding to the visible environment based on the computed point cloud, and generating two stereoscopic colorized images to be respectively displayed to the two eyes of the user, where each of the two stereoscopic colorized images is generated using (1) the mesh, (2) luminance information from one of the two stereoscopic grayscale images that is associated with the eye to which the stereoscopic colorized image is to be displayed, and (3) color information from a color input image captured by the color camera.
-
公开(公告)号：US11954872B2
公开(公告)日：2024-04-09
申请号：US17071547
申请日：2020-10-15
申请人： NIKON CORPORATION
发明人： Mariko Hirokawa , Yasushi Tanabe
CPC分类号： G06T7/337 , A61B3/0025 , A61B3/1241 , G06T3/0093 , G06T7/0014 , G06T7/74 , G06T2207/20221 , G06T2207/30041 , G06T2207/30101
摘要： A first image is projective transformed into a reference image by using a projective transformation matrix on each pixel of the first image. A projective transformation matrix for transforming a tilted image n into a central image G0 is computed based on positions of combinations of twelve corresponding points indicated in a combination of the central image G0 with the tilted image n. The computed projective transformation matrix is then employed to perform a projective transformation of the tilted image n. A projective-transformed tilted image n1 is created thereby.
-
-
-
-
-
-
-
-
-
搜索结果
1197 条记录 (耗时 0.028 秒)
