Samsung Electronics Co., Ltd.

Hossein Najaf-Zadeh

Madhukar Budagavi

Rajan Laxman Joshi

Esmaeil Faramarzi

Ankur Saxena

Indranil Sinharoy

Youngkwon Lim

Sungryeul Rhyu

Neha Dawar

Tuan Ho

Yeshwant Kumar Muthusamy

Barry Woodward

Yeshwant Muthusamy

Young-Kwon Lim

A method for point cloud decoding includes receiving a bitstream. The method also includes decoding the bitstream into multiple frames that include pixels. Certain pixels of the multiple frames correspond to points of a three-dimensional (3D) point cloud. The multiple frames include a first set of frames that represent locations of the points of the 3D point cloud and a second set of frames that represent attribute information for the points of the 3D point cloud. The method further includes reconstructing the 3D point cloud based on the first set of frames. Additionally, the method includes identifying a first portion of the points of the reconstructed 3D point cloud based at least in part on a property associated with the multiple frames. The method also includes modifying a portion of the attribute information. The portion of the attribute information that is modified corresponds to the first portion of the points.

Attribute transfer in V-PCC

A method for point cloud decoding includes receiving a bitstream. The method also includes decoding the bitstream into multiple frames that include pixels. A portion of the pixels are organized into patches and correspond to respective clusters of points of a 3D point cloud. The method further includes decoding, from the bitstream, an occupancy map frame. The occupancy map frame indicates the portion of the pixels included in the multiple frames that represent the points of the 3D point cloud. In addition, the method includes reconstructing the 3D point cloud using the multiple frames and the occupancy map frame. The method also includes determining whether to perform smoothing to the 3D point cloud based at least in part on properties of the multiple frames. Based on determining to perform the smoothing, the method includes performing the smoothing to the 3D point cloud.

Decision-making rules for attribute smoothing

An apparatus includes a memory and a processor. The memory receives a plurality of frames of a scene captured from a camera array. The processor selects a first frame and a second frame from the plurality of frames. The processor also rectifies and aligns the first frame and the second frame to a reference frame, where a blank region of the second frame has a greater area than a blank region of the first frame. The processor further transforms the first frame to have near-optimal superposition to the second frame. The processor inserts a patch from the transformed first frame into the blank region of the second frame.

Restoration of the FOV of images for stereoscopic rendering

An encoding device, a decoding device, and a method for mesh decoding are disclosed. The method for mesh decoding includes receiving a compressed bitstream. The method also includes separating, from the compressed bitstream, a first bitstream and a second bitstream. The method further includes decoding, from the second bitstream, connectivity information of a three dimensional (3D) mesh. The method additionally includes decoding, from the first bitstream, a first frame and a second frame that include patches. The patches included in the first frame represent vertex coordinates of the 3D mesh and the patches included in the second frame represent a vertex attribute of the 3D mesh. The method also includes reconstructing a point cloud based on the first and second frames. Additionally, the method also includes applying the connectivity information to the point cloud to reconstruct the 3D mesh.

Mesh compression

An encoding device and a decoding device is disclosed. The encoding device includes a processor and a communication interface. The processor is configured to generate, for a 3D point cloud, a first frame representing a first attribute and a second frame representing a second attribute. The first and second frames include patches representing respective clusters of points from the 3D point cloud. The processor is configured to generate an occupancy map frame. The processor is configured to identify a query point that is positioned on a boundary of one of the patches. The processor is configured to perform smoothing with respect to the query point. The processor is configured to encode the frames and generate a compressed bitstream. The communication is configured to transmit the compressed bitstream.

Point cloud compression via color smoothing of point cloud prior to texture video generation

An encoding device, a method of encoding, and decoding device for point cloud compression of a 3D point cloud. The encoding device is configured to generate, for the three-dimensional (3D) point cloud, at least a set of geometry frames and a set of occupancy map frames for points of the 3D point cloud. The encoding device is also configured to select an occupancy precision value based on a quantization parameter (QP) associated with at least one generated geometry frame in the set of geometry frames, subsample at least one occupancy map frame in the set of occupancy map frames based on the selected occupancy precision value, and encode the set of geometry frames and the set of occupancy map frames into a bitstream for transmission.

Adaptive selection of occupancy map precision

A user equipment (UE) includes a receiver, display, and processor. The receiver is configured to receive a data stream including a plurality of frames. The data stream includes a region of interest in a key frame of the plurality of frames. The display is configured to display a portion of a frame of the plurality of frames. The processor is configured to perform an action to focus a current view of the UE to the region of interest in the key frame. Each frame of the plurality of frames includes a plurality of images stitched together to form a stitched image. The stitched image for at least one frame of the plurality of frames includes at least one high dynamic range (HDR) image and at least one standard dynamic range (SDR) image.

Generating and transmitting metadata for virtual reality

A decoding device includes a communication interface and a processor. The communication interface is configured to receive a bitstream. The processor is configured to decode from the bitstream a first frame, a second frame and an occupancy map frame. The processor is also configured to reconstruct the 3D point cloud using the first frame, the second frame, and the occupancy map frame. The processor is further configured to perform a single pass of the occupancy map frame to identify points of the reconstructed 3D point cloud that correspond to a subset of pixels in the first frame and the second frame that are positioned within a proximity threshold to a boundary of any of the patches.

Single-pass boundary detection in video-based point cloud compression

A decoding device, an encoding device and a method for point cloud decoding is disclosed. The method includes receiving a bitstream. The method also includes decoding the bitstream into a geometry frame and a texture frame. The geometry and texture frames represent include pixels representing points of the 3D point cloud from different layers. The method further includes deriving a set of missing geometry values from the pixels in the geometry frame and a set of missing texture values from the pixels in the texture frame. The method additionally includes generating a first set of frames representing geometry based on the geometry frame and the set of missing geometry values and generating a second set of frames representing texture based on the texture frame and the set of missing texture values. The method also includes generating the 3D point cloud using the first and second sets of frames.

Point cloud compression using interpolation

A method and decoder for point cloud decoding. The method includes receiving and decoding a bitstream into multiple frames that include patches corresponding to respective clusters of points from a 3D point cloud. The method also includes generating a grid that includes a plurality of 3D cells, wherein the 3D point cloud is within the grid. The method further includes identifying a first cell of the plurality of 3D cells that includes a query point corresponding to a pixel on a boundary of one of the patches. The method additionally includes identifying a luminance value of the first cell. The method also includes performing color smoothing on the query point based on comparison of the luminance value of the first cell to a threshold.

Low complexity color smoothing of reconstructed point clouds

A decoding device, an encoding device and a method for point cloud decoding is disclosed. The method includes receiving a compressed bitstream. The method also includes decoding the compressed bitstream into 2D frames that represent a 3D point cloud, each of the 2D frames including a set of patches representing a cluster of pixels of the 3D point cloud. The method further includes identifying an occupancy map included in the compressed bitstream. The method additionally includes identifying valid boundary points located at a boundary of a patch of the set of patches based on the occupancy map and identifying valid neighboring points of each of the valid boundary points of the patch. The method also includes generating the 3D point cloud using the 2D frames based on the valid neighboring points and the valid boundary points.

Visual quality enhancement of reconstructed point clouds via color smoothing

A decoding device, an encoding device and a method for point cloud decoding is disclosed. The method includes receiving a compressed bitstream. The method also includes decoding the compressed bitstream into 2-D frames that represent a 3-D point cloud. Each of the 2-D frames including a set of patches, and each patch includes a cluster of points of the 3-D point cloud. The cluster of points corresponds to an attribute associated with the 3-D point cloud. One patch of the set of patches, the set of patches, and the 2-D frames correspond to respective access levels representing the 3-D point cloud. The method also includes identifying a first and a second flag. In response to identifying the first and the second flag, the method includes reading the metadata from the bitstream. The method further includes generating, based on metadata and using the sets of 2-D frames, the 3-D point cloud.

Growing community of inventors

Allen, TX, United States of America

Hossein Najaf-Zadeh