Abstract: Methods and apparatuses of decoding a video stream encoded using video point cloud coding include obtaining a geometry-reconstructed point cloud; dividing the geometry-reconstructed point cloud into a plurality of cells; obtaining a first reference point including a centroid of a first plurality of points; generating a second plurality of points by applying a first filter to the first plurality of points based on the first reference point; obtaining a second reference point including a centroid of the second plurality of points; generating a third plurality of points by applying a second filter to the second plurality of points based on the second reference point, wherein a strength of the first filter is higher than a strength of the second filter; obtaining a smoothed geometry-reconstructed point cloud based on the third plurality of points; and reconstructing a dynamic point cloud using the smoothed geometry-reconstructed point cloud.

Abstract: Methods and apparatuses of decoding a video stream encoded using video point cloud coding include obtaining a geometry-reconstructed point cloud; dividing the geometry-reconstructed point cloud into a plurality of cells, wherein a cell of the plurality of cells includes a first plurality of points; determining a plane representing the first plurality of points; generating a second plurality of points by projecting the first plurality of points onto the plane; obtaining a smoothed geometry-reconstructed point cloud based on the second plurality of points; and reconstructing a dynamic point cloud using the smoothed geometry-reconstructed point cloud.

Abstract: A method and apparatus for encoding a video stream using video point cloud coding, the decoding including obtaining an input point cloud; dividing the input point cloud into a plurality of chunks, including a first chunk including a first plurality of points and a second chunk including a second plurality of points; generating a first plurality of patches based on the first plurality of points; generating a second plurality of patches based on the second plurality of points; packing the first plurality of patches and the second plurality of patches into an image; and generating the video stream based on the image.

Abstract: A method of dynamic point cloud partition packing is by at least one processor and includes obtaining one or more region of interest (ROI) patches from an ROI of a point cloud, and attempting to pack, into one among tiles of a tile map, one among the obtained one or more ROI patches, in a tile scan order. The method further includes identifying whether the one among the one or more ROI patches is packed successfully into the one among the tiles, and based on the one among the one or more ROI patches being determined to be not packed successfully into the one among the tiles, chunking the one among the one or more ROI patches into multiple ROI patches.

Abstract: An improved octree traversal implementation improves the color coding gain for point cloud compression. The improved octree traversal order to be used in Anchor PCC or any other octree-based point cloud compression such as Directed Acyclic Graph (DAG). The improved octree traversal makes minimal jumps in 3D space which makes traversed colors more correlated, which improves color coding gain.

Abstract: A method of video decoding performed in a video decoder includes receiving compressed geometric data corresponding to a three dimensional (3D) space. The method further includes receiving a low resolution occupancy map associated with the data cloud. The method further includes converting the low resolution occupancy map to a high resolution occupancy map. The method further includes reconstructing a point cloud using the compressed geometric data and the high resolution occupancy map. The method further includes performing a smoothing operation on one of the (i) reconstructed point cloud and (ii) the high resolution occupancy map.

Abstract: A method for reducing color leaking artefacts in an image formed by projection processing from a 3D point cloud comprises: receiving an input image comprising the 3D point cloud; classifying the cloud into a plurality of surface patches; projecting the patches onto a plane to form a first 2D image; processing the first 2D image, by coding, transmitting and decoding, to form a final 2D image; and providing the final 2D image as an output. Processing comprises at least one of: coding comprising independent patch processing to reduce inter-patch color leakage; coding comprising background filling of pixels between patches to reduce inter-patch color leakage; coding comprising applying a chroma down-sampling scheme, based on depth and color value, that reduces intra-patch color leakage; and decoding comprising post-filtering to detect potential intra-patch color leakage, followed by an adaptive chroma up-sampling scheme that reduces intra-patch color leakage.

Abstract: Systems, methods, and instrumentalities are disclosed for inverse shaping for high dynamic range (HDR) video coding. A video coding device, e.g., such as a decoder, may determine a plurality of pivot points associated with a plurality of piecewise segments of an inverse reshaping model. The plurality of pivot points may be determined based on an indication received via a message. Each piecewise segment may be defined by a plurality of coefficients. The video coding device may receive an indication of a first subset of coefficients associated with the plurality of piecewise segments. The video coding device may calculate a second subset of coefficients based on the first subset of coefficients and the plurality of pivot points. The video coding device may generate an inverse reshaping model using one or more of the plurality of pivot points, the first subset of coefficients, and the second subset of coefficients.

Abstract: A method includes receiving a data cloud including a plurality of data points. The method further includes identifying each data point including a region-of-interest (ROI) and dividing the data cloud into a ROI cloud and one or more non-ROI clouds. The method includes performing a patch generation process on the ROI cloud, the patch generation process including generating a ROI patch from each data point including the ROI. The method includes performing a patch packing process on the ROI cloud, the patch packing process including: (i) mapping each ROI patch to a two dimensional (2D) map, (ii) determining whether at least two ROI patches from the plurality of ROI patches are located in more than one tile of the map, and (iii) in response to the determination that at least two ROI patches are located in more than one tile, moving each of the ROI patches to a tile.

Abstract: Lifting is a transform designed for color compression of point clouds which is adopted in one of the MPEG test models. The performance of lifting is improved herein. All the lifting coefficients are first divided into several subbands based on their assigned weights, which indicate the level of importance of each coefficient. Then, for each subband, a set of three dead-zones are derived for the three color components. The dead-zones of Cb and Cr channels are typically larger than that of Luma channel. In the original lifting scheme, Chroma is not suppressed at all. In contrast, as described herein, the size of the dead-zone is increased for different color components, which means that more quality (and bandwidth) is able to be adaptively provided for luminance coefficients than chrominance coefficients.

Abstract: A method for rate distortion optimization for adaptive sub-band coding of Region-Adaptive Hierarchical Transform (RAHT) coefficients, which is a point cloud color compression method adopted in PCC test model TMC13 for compression of CAT1 sequences is described herein. Based on Lagrangian optimization, the method estimates the coefficient distortion by using the compressed mesh geometry as reference. The Lagrange factor is calculated based on the quantization parameters, and the results show that the parameters obtained automatically have similar or better performance than parameters chosen after an extensive search.

Abstract: An electronic apparatus and method for adaptive sub-band based coding of hierarchical transform coefficients of a 3D point cloud, is provided. The electronic apparatus stores the 3D point cloud and generates a plurality of voxels from the 3D point cloud. The electronic apparatus generates a plurality of hierarchical transform coefficients by application of a hierarchical transform scheme on the generated plurality of voxels and classifies the plurality of hierarchical transform coefficients into a plurality of sub-bands of hierarchical transform coefficients. The plurality of hierarchical transform coefficients are classified based on a weight of each of the plurality of hierarchical transform coefficients.

Abstract: The present invention provides a method for performing transformation using a layered Givens transform (LGT), comprising the steps of: deriving at least one rotation layer and at least one permutation layer on the basis of a given transform matrix (H) and a given error parameter; acquiring a LGT coefficient on the basis of the rotation layer and the permutation layer; and quantizing and entropy-encoding the LGT coefficient, wherein the permutation layer comprises a permutation matrix obtained by permuting a row of an identity matrix.

Abstract: A method for reducing color leaking artefacts in an image formed by projection processing from a 3D point cloud comprises: receiving an input image comprising the 3D point cloud; classifying the cloud into a plurality of surface patches; projecting the patches onto a plane to form a first 2D image; processing the first 2D image, by coding, transmitting and decoding, to form a final 2D image; and providing the final 2D image as an output. Processing comprises at least one of: coding comprising independent patch processing to reduce inter-patch color leakage; coding comprising background filling of pixels between patches to reduce inter-patch color leakage; coding comprising applying a chroma down-sampling scheme, based on depth and color value, that reduces intra-patch color leakage; and decoding comprising post-filtering to detect potential intra-patch color leakage, followed by an adaptive chroma up-sampling scheme that reduces intra-patch color leakage.

Abstract: An apparatus receives a video which includes at least one three-dimensional (3D) object in a 3D physical space. A 3D geometrical representation of a point cloud is generated based on the video. The 3D geometrical representation of the point cloud includes a first set of points associated with geometrical information and texture information corresponding to the at least one 3D object. A plurality of two-dimensional (2D) projections are generated from the 3D geometrical representation of the point cloud. A second set of points that are occluded in the first set of points is detected, corresponding to the plurality of 2D projections. The plurality of 2D projections and the second set of points are distinctly encoded, and the remaining points, other than the detected second set of points, in the first set of points are discarded for efficient compression of the 3D geometrical representation of the point cloud.

Abstract: A point cloud compression approach that exploits HEVC for compression of both the geometry and color data is described herein. Although both the geometry and color could be compressed in a lossy fashion, the point cloud compression approach is suggested for the scenario of lossless geometry and lossy color coding. Both geometry and color data are first mapped into 2D images and then compressed by HEVC. A sorting technique is used to sort the geometry data to make it as correlated as possible when it is mapped to a 2D image. For color coding, clustering is used to put similar colors in a point cloud into spatial neighbors in the mapped 2D image. This significantly avoids color leaking due to quantization errors to neighbor points in 3D. The results show that much better compression is achieved compared to the Anchor when it is configured for lossless geometry coding.

Abstract: A method of compression of the color data of point clouds is described herein. A palette of colors that best represent the colors existing in the cloud is generated. Clustering is utilized for generating the palette. Once the palette is generated, an index to the palette is found for each point in the cloud. The indexes are coded using an entropy coder afterwards. A decoding process is then able to be used to reconstruct the point clouds.

Abstract: The color coding approach adopted by the Anchor Point Cloud Compression (PCC) leads to a significant color distortion, even at very low compression ratios. This color distortion is also referred to as color leaking Two approaches are able to mitigate the color leaking Both approaches reduce the color leaking significantly, while one of them (e.g., 1D subsampling) is more robust and preferred in most cases. A more general approach is an adaptive selection between these two approaches.

Abstract: An improved octree traversal implementation improves the color coding gain for point cloud compression. The improved octree traversal order to be used in Anchor PCC or any other octree-based point cloud compression such as Directed Acyclic Graph (DAG). The improved octree traversal makes minimal jumps in 3D space which makes traversed colors more correlated, which improves color coding gain.

Abstract: A video sequence may include a first-temporal level picture and a second-temporal level picture. The first-temporal level picture may be associated with a first temporal level, and the second-temporal level picture may be associated with a second temporal level. The second-temporal level picture may reference the first-temporal level picture. A first chroma quantization parameter (QP) may be determined based on a temporal level of the first-temporal level picture. A second chroma QP may be determined based on a temporal level of the second-temporal level picture. The first-temporal level picture may be encoded based on the first chroma QP to the first-temporal level picture and/or the second-temporal level picture may be encoded based on the second chroma QP to the second-temporal level picture. The first chroma QP may be different than the second chroma QP.