-
公开(公告)号：US20240169496A1
公开(公告)日：2024-05-23
申请号：US17991594
申请日：2022-11-21
发明人： Mikko Ollila , Mikko Strandborg
摘要： A method includes obtaining 3D model of real-world environment; receiving image captured using camera, and pose information indicative of camera pose from which image is captured; utilising 3D model to generate reconstructed image from a perspective of camera pose; identifying group(s) of neighbouring pixels in image that is/are out of focus; determining point spread function for group(s) of neighbouring pixels, based on correlation between group(s) of neighbouring pixels and corresponding group of neighbouring pixels in reconstructed image; and applying extended depth-of-field correction to group(s) of neighbouring pixels in image, by using point spread function.
-
公开(公告)号：US20230245408A1
公开(公告)日：2023-08-03
申请号：US17591243
申请日：2022-02-02
发明人： Mikko Strandborg , Petteri Timonen
IPC分类号： G06T19/20 , G06V10/764 , G06T7/70 , G06T17/00
CPC分类号： G06T19/20 , G06V10/764 , G06T7/70 , G06T17/00
摘要： A system includes server(s) configured to: receive plurality of images of real-world environment captured by camera(s); process a number of images to detect plurality of objects present in a real-world environment and generate a three-dimensional environment model of the real-world environment; classify each of the objects as either a static or dynamic object; receive current image(s) of the real-world environment; process the current image(s) to detect object(s); determine whether or not the object(s) is/are from amongst the plurality of objects; determine whether the object(s) is a static object or dynamic object when it is determined that the object(s) is/are from amongst the plurality of objects; and for each dynamic object that is represented in the three-dimensional environment model but not in a current image(s), apply a first visual effect to a representation of the dynamic object in the three-dimensional environment model for indicating staleness of the representation.
-
公开(公告)号：US11568574B1
公开(公告)日：2023-01-31
申请号：US17405239
申请日：2021-08-18
摘要： An encoding method and a decoding method. The encoding method includes generating curved image by creating projection of visual scene onto inner surface of imaginary 3D geometric shape that is curved in at least one dimension; dividing curved image into input portion and plurality of input rings; encoding input portion and input rings into first planar image and second planar image, respectively, such that input portion is stored into first planar image, and input rings are packed into corresponding rows of second planar image; and communicating, to display apparatus, first and second planar images and information indicative of sizes of input portion and input rings.
-
公开(公告)号：US20220351411A1
公开(公告)日：2022-11-03
申请号：US17245823
申请日：2021-04-30
摘要： An AR system is arranged to display an image stream of an environment with one or more virtual objects, each virtual object being associated with a marker in the image stream. The AR system includes a tracking subsystem arranged to track a first pose of the marker in the image, and inform a frame rendering subsystem, which generates a rendering of the VR object and provides the rendering to the reprojecting subsystem together with information about the first pose of the marker and information identifying a set of pixels included in the VR image. The tracking subsystem further determines a second pose of the marker based on detected movement and informs the reprojecting subsystem about the second pose. The reprojecting subsystem renders an image frame including the image stream of the environment with the rendering of the VR object reprojected in dependence of the second pose.
-
公开(公告)号：US11307410B2
公开(公告)日：2022-04-19
申请号：US17155621
申请日：2021-01-22
摘要： A display apparatus including pose-tracking means; image renderer per eye; liquid-crystal device including liquid-crystal structure and control circuit; and processor. Processor is configured to: process pose-tracking data to determine user's head pose; detect if rate at which head pose is changing is below predefined threshold rate; if yes, switch on lock mode, select head pose for session of lock mode, and generate output image frames according to head pose during session; if no, generate output image frames according to corresponding head poses of user using pose-tracking data; and display output image frames, whilst shifting light emanating to from pixels of image renderer to multiple positions (P1-P9) in sequential and repeated manner, said shifting causes resolution of output image frames to appear higher than display resolution of image renderer.
-
公开(公告)号：US11170678B2
公开(公告)日：2021-11-09
申请号：US17162020
申请日：2021-01-29
发明人： Mikko Strandborg , Ville Miettinen
摘要： A display apparatus including gaze-tracking means, image renderers, liquid-crystal devices including liquid-crystal structure and control circuit, to shift light emanating from given pixel of image renderer to multiple positions, given pixel including colour component; and processor configured to: process gaze-tracking data to determine gaze direction of user's eye; determine gaze point; display first output image frame; detect if magnitude of difference between first output value and initial second output value of colour component of given pixel in first and second output image frames exceeds first threshold difference; when detected that magnitude of difference exceeds first threshold difference, update initial second output value to sum of first output value and product of distance factor and difference between initial second output and first output values; and display second output image frame.
-
7.发明申请公开(公告)号：US20210248969A1
公开(公告)日：2021-08-12
申请号：US17167233
申请日：2021-02-04
IPC分类号： G09G3/36
摘要： In a display apparatus, a liquid-crystal structure, arranged in front of an image renderer, is controlled to shift light of a given sub-pixel to target positions according to a shifting sequence in a repeated manner, while output image frames are displayed. To generate a given output image frame, a given target position to which the light is to be shifted is determined based on the shifting sequence. An input colour value of the given sub-pixel provided in a given input image frame is then adjusted to generate an output colour value of the given sub-pixel for the given output image frame, based on an output colour value of at least one other sub-pixel whose light overlaps with the given target position during display of a previous output image frame, and a retention coefficient between a colour of the at least one other sub-pixel and a colour of the given sub-pixel.
-
公开(公告)号：US20240362862A1
公开(公告)日：2024-10-31
申请号：US18306295
申请日：2023-04-25
发明人： Mikko Strandborg , Kimmo Roimela
CPC分类号： G06T17/005 , G06F3/013 , G06T7/90 , G06V10/25 , G06V10/761 , G06V10/82 , G06T2207/10024 , G06T2207/20081
摘要： A hierarchical data structure has sets of nodes representing a 3D space of an environment at different granularity levels. Sets of neural networks at different granularity levels are trained. For a portion of an output image, a granularity level at which the portion is to be reconstructed is determined. A corresponding node is identified; the node having sets of child nodes. A set of child nodes is selected at the granularity level at which the portion is to be reconstructed. For a child node, a cascade of neural networks is utilised to reconstruct the portion. Granularity level of N+1th neural network is higher than that of Nth neural network. Input of a neural network includes outputs of at least a predefined number of previous neural networks.
-
公开(公告)号：US20240282051A1
公开(公告)日：2024-08-22
申请号：US18111340
申请日：2023-02-17
发明人： Kimmo Roimela , Mikko Strandborg
CPC分类号： G06T17/00 , G06T7/11 , G06T7/70 , G06V10/25 , G06V10/761 , G06V10/82 , G06T2207/10024 , G06T2207/10028 , G06T2207/20081
摘要： A system and method for receiving colour images, depth images and viewpoint information; dividing 3D space occupied by real-world environment into 3D grid(s) of voxels; create 3D data structure(s) comprising nodes, each node representing corresponding voxel; dividing colour image and depth image into colour tiles and depth tiles, respectively; mapping colour tile to voxel(s) whose colour information is captured in colour tile; storing, in node representing voxel(s), viewpoint information indicative of viewpoint from which colour and depth images are captured, along with any of: colour tile that captures colour information of voxel(s) and corresponding depth tile that captured depth information, or reference information indicative of unique identification of colour tile and corresponding depth tile; and utilising 3D data structure(s) for training neural network(s), wherein input of neural network(s) comprises 3D position of point and output of neural network(s) comprises colour and opacity of point.
-
公开(公告)号：US12045932B2
公开(公告)日：2024-07-23
申请号：US17881264
申请日：2022-08-04
发明人： Mikko Strandborg , Kimmo Roimela
CPC分类号： G06T15/503 , G06T3/40 , G06T7/11 , G06T7/90 , G06T15/205 , G06T19/006 , G06T2200/08 , G06T2207/10024 , G06T2207/10028 , G06T2207/20021 , G06T2210/56
摘要： A computer-implemented method including: receiving visible-light images captured from viewpoints using visible-light camera(s); creating 3D model of real-world environment, wherein 3D model stores colour information pertaining to 3D points on surfaces of real objects (204); dividing 3D points into groups of 3D points, based on at least one of: whether surface normal of 3D points in group lie within predefined threshold angle from each other, differences in materials of real objects, differences in textures of surfaces of real objects; for group of 3D points, determining at least two of visible-light images in which group of 3D points is captured from different viewpoints, wherein said images are representative of different surface irradiances of group of 3D points; and storing, in 3D model, information indicative of different surface irradiances.
-
-
-
-
-
-
-
-
-
搜索结果
47 条记录 (耗时 0.022 秒)
