公开(公告)号：US12008712B2

公开(公告)日：2024-06-11

申请号：US18296809

申请日：2023-04-06

申请人： QUALCOMM Incorporated

发明人： Bappaditya Ray ,  Adarsh Krishnan Ramasubramonian ,  Geert Van der Auwera ,  Marta Karczewicz

IPC分类号： G06T17/00 ,  G06T9/00 ,  G06T19/20 ,  H04N13/161 ,  H04N19/186 ,  H04N19/50 ,  H04N19/70

CPC分类号： G06T17/00 ,  G06T9/00 ,  G06T19/20 ,  H04N13/161 ,  H04N19/186 ,  H04N19/50 ,  H04N19/70 ,  G06T2210/36 ,  G06T2219/2016

摘要： A device for decoding encoded point cloud data can be configured to, for a point of a point cloud, determine a first color value for a first color component based on a first predicted value and a first residual value; apply a scaling factor to the first residual value to determine a predicted second residual value, wherein the scaling factor has one or both of a non-integer value or an absolute value greater than one; for the point of the point cloud, receive a second residual value in the encoded point cloud data; determine a final second residual value based on the predicted second residual value and the received second residual value; and for the point of the point cloud, determine a second color value for a second color component based on a second predicted value and the final second residual value.

公开(公告)号：US20240187559A1

公开(公告)日：2024-06-06

申请号：US18524153

申请日：2023-11-30

申请人： Samsung Electronics Co., Ltd.

发明人： Weiming LI ,  Inwoo HA ,  Qiang WANG ,  Young Hun SUNG ,  Hao WANG

IPC分类号： H04N9/73 ,  G06T5/50 ,  G06T7/11 ,  G06T7/90 ,  G06T9/00 ,  G06V10/42 ,  G06V10/60

CPC分类号： H04N9/73 ,  G06T5/50 ,  G06T7/11 ,  G06T7/90 ,  G06T9/00 ,  G06V10/42 ,  G06V10/60 ,  G06T2207/20208 ,  G06T2207/20221

摘要： A processor-implemented method includes obtaining an input image, predicting light source color information of a scene corresponding to the input image and a panoramic image corresponding to the input image using an image processing model, and generating a rendered image by rendering the input image based on either one or both of the light source color information and the panoramic image.

公开(公告)号：US20240185474A1

公开(公告)日：2024-06-06

申请号：US18439213

申请日：2024-02-12

申请人： Malikie Innovations Limited

发明人： Sébastien Lasserre

IPC分类号： G06T9/40 ,  G06F17/18 ,  G06T9/00 ,  G06T17/10 ,  H03M7/30 ,  H04N19/105 ,  H04N19/13 ,  H04N19/169 ,  H04N19/46 ,  H04N19/96

CPC分类号： G06T9/40 ,  G06F17/18 ,  G06T9/001 ,  G06T17/10 ,  H03M7/6005 ,  H03M7/6011 ,  H04N19/105 ,  H04N19/13 ,  H04N19/1883 ,  H04N19/46 ,  H04N19/96

摘要： Methods and devices for encoding a point cloud. A bit sequence signalling an occupancy pattern for sub-volumes of a volume is coded using binary entropy coding. For a given bit in the bit sequence, a context may be based on a sub-volume neighbour configuration for the sub-volume corresponding to that bit. The sub-volume neighbour configuration depends on an occupancy pattern of a group of sub-volumes of neighbouring volumes to the volume, the group of sub-volumes neighbouring the sub-volume corresponding to the given bit. The context may be further based on a partial sequence of previously-coded bits of the bit sequence.

公开(公告)号：US20240185473A1

公开(公告)日：2024-06-06

申请号：US17969551

申请日：2022-10-19

申请人： SANTA CLARA UNIVERSITY ,  KWAI INC.

发明人： Yifei PEI ,  Ying LIU ,  Nam LING ,  Yongxiong REN ,  Lingzhi LIU

IPC分类号： G06T9/00

CPC分类号： G06T9/002

摘要： A neural network system, a method and an apparatus for image compression are provided. The neural network may include a generator including an encoder, an entropy estimator, and a decoder, where the encoder receives an input image and generates an encoder output, a plurality of quantized feature entries are obtained based on the encoder output outputted at a last encoder block, the entropy estimator receives the plurality of quantized feature entries and calculates an entropy loss based on the plurality of quantized feature entries, and the decoder receives the plurality of quantized feature entries and generates a reconstructed image. Furthermore, the neural network may include a discriminator that determines whether the reconstructed image different from the input image based on a discriminator loss. Moreover, the generator may determine whether content of the reconstructed image matches content of the input image based on a generator loss including the entropy loss.

公开(公告)号：US20240185472A1

公开(公告)日：2024-06-06

申请号：US18553816

申请日：2021-10-13

申请人： Beijing Xiaomi Mobile Software Co., Ltd.

发明人： Sebastien LASSERRE ,  Jonathan TAQUET

IPC分类号： G06T9/00 ,  G06T9/40

CPC分类号： G06T9/001 ,  G06T9/40

摘要： There is provided methods and apparatus of encoding/decoding a point cloud representing a physical object, each point of the point cloud being associated with a residual radius between a radius responsive to a distance of the point from a referential and a predicted radius. The method entropy encodes/decodes the sign of the residual radius associated with a current point of the point cloud based on the sign of a previously entropy encoded/decoded non-zero residual radius associated with a previous point.

公开(公告)号：US20240185467A1

公开(公告)日：2024-06-06

申请号：US18287839

申请日：2022-04-20

申请人： LG ELECTRONICS INC.

发明人： Sooyeon LEE ,  Hyunmook OH ,  Hyejung HUR ,  Yousun PARK

IPC分类号： G06T9/00

CPC分类号： G06T9/001

摘要： A point cloud data transmission method according to embodiments comprises the steps of: encoding geometry data including positions of points of point cloud data; encoding, on the basis of the geometry data, attribute data including attribute values of the points of the point cloud data; and transmitting the encoded geometry data, the encoded attribute data, and signaling information, wherein, in the step of encoding the geometry data, the geometry data can be compressed on the basis of the correlation between frames and the distribution of the points.

公开(公告)号：US20240185466A1

公开(公告)日：2024-06-06

申请号：US18286059

申请日：2021-10-13

申请人： BEIJING XIAOMI MOBILE SOFTWARE CO., LTD.

发明人： Jonathan TAQUET ,  Sebastien LASSERRE

IPC分类号： G06T9/00

CPC分类号： G06T9/001

摘要： A method of encoding/decoding a point cloud into/from a bitstream of encoded point cloud data representing a physical object includes determining a dynamic list of at least one prediction data used to derive at least one candidate predictor used to encode geometry data of points of the point cloud. The list of at least one prediction data is dynamic because during the encoding of points, prediction data are updated based on residuals radius of decoded points.

公开(公告)号：US12003701B2

公开(公告)日：2024-06-04

申请号：US17712517

申请日：2022-04-04

申请人： Huawei Technologies Co., Ltd.

发明人： Ye-Kui Wang ,  Huameng Fang ,  Yuqun Fan ,  Jianle Chen

IPC分类号： H04N19/105 ,  G06T9/00 ,  G06T19/00 ,  H04N19/13 ,  H04N19/132 ,  H04N19/139 ,  H04N19/159 ,  H04N19/167 ,  H04N19/172 ,  H04N19/176 ,  H04N19/436 ,  H04N19/44 ,  H04N19/46 ,  H04N19/597 ,  H04N19/70

CPC分类号： H04N19/105 ,  G06T9/00 ,  G06T19/006 ,  H04N19/13 ,  H04N19/132 ,  H04N19/139 ,  H04N19/159 ,  H04N19/167 ,  H04N19/172 ,  H04N19/176 ,  H04N19/436 ,  H04N19/44 ,  H04N19/46 ,  H04N19/597 ,  H04N19/70

摘要： A video coding mechanism for viewpoint dependent video coding is disclosed. The mechanism includes mapping a spherical video signal, stitched from multiple directional video signals, into a plurality of sub-picture video signals each containing a sequence of sub-pictures. The plurality of sub-picture video signals are encoded as a plurality of sub-picture bitstreams. The plurality of sub-picture bitstreams are composed into a plurality of sub-picture tracks to be compatible with a multi-bitstream merge function for reconstruction of the spherical video signal. A track level mergable indication is encoded within a track level box for the sub-picture tracks, which indicates the sub-picture tracks are compatible with the multi-bitstream merge function for reconstruction of the spherical video signal.

公开(公告)号：US20240177392A1

公开(公告)日：2024-05-30

申请号：US18126900

申请日：2023-03-27

申请人： NVIDIA Corporation

发明人： Adithyavairavan Murali ,  Arsalan Mousavian ,  Clemens Eppner ,  Adam Fishman ,  Dieter Fox

IPC分类号： G06T15/00 ,  B25J9/16 ,  G06T9/00

CPC分类号： G06T15/00 ,  B25J9/1697 ,  G06T9/001 ,  G06T2210/21

摘要： One common robotic task is the rearrangement of physical objects situated in an environment. This typically involves a robot manipulator picking up a target object and placing the target object in some target location, such as a shelf, cabinet or cubby, and requires the skills of picking, placing and generating complex collision-free motions, oftentimes in a cluttered environment. The present disclosure provides collision detection for object rearrangement using a three-dimensional (3D) scene representation.

公开(公告)号：US20240177356A1

公开(公告)日：2024-05-30

申请号：US18432973

申请日：2024-02-05

申请人： TENCENT AMERICA LLC

发明人： Wen GAO ,  Xiang ZHANG ,  Shan LIU

IPC分类号： G06T9/40 ,  G06T9/00 ,  G06T17/20

CPC分类号： G06T9/40 ,  G06T9/001 ,  G06T17/205

摘要： A method, computer program, and computer system is provided for decoding point cloud data. Data corresponding to a point cloud is received. A number of contexts associated with the received data is reduced based on reducing a size of an array corresponding to syntax elements for predictive tree-based coding of the point cloud. The data corresponding to the point cloud is decoded based on the reduced number of contexts.