Abstract: An image encoding/decoding method, device and recording medium based sed on multiple compression levels disclosure may include extracting a region of interest for machine vision from an input image, determining a compression level of the region of interest, and encoding the compression level of the region of interest.

Abstract: An object-based image encoding/decoding method and device of the present disclosure may include an image partition step which partitions an image to obtain a first object region, a region scaling step which scales the first object region based on a scaling factor of the first object region to obtain a second objection region, a region merging step which merges the second object region with at least one of an object region different from the second object region or a non-object region to obtain a merged image, and an image reconstruction step which reconstructs the merged image.

Abstract: An image encoding method includes detecting at least one attention region from an original image, acquiring a reconstructed picture for the original image, generating residual data between a first attention region in the original image and a second attention region corresponding to the first attention region in the reconstructed picture, and encoding the residual data.

Abstract: A method of switching an atlas according to a watching position according to the present disclosure includes acquiring information on a view image required to reproduce a viewport image; acquiring information of a first atlas mapped to the view image; and receiving a bitstream of the first atlas and a bitstream of a second atlas different from the first atlas. In this case, when it is determined that atlas switching is necessary, reception of any one of a bitstream of the first atlas and a bitstream of the second atlas may be stopped and a bitstream of a third atlas may be newly received.

Abstract: A video decoding method comprises warping different viewpoint images into a virtual viewpoint by using depth information of an input viewpoint; determining a first weight for the pixels based on quality and depth of pixels of the warped viewpoint images; determining a second weight for the pixels based on a location relation between the pixels of the warped viewpoint images and the virtual viewpoint; determining a blending weight for the pixels based on the first weight and the second weight; blending the warped viewpoint images according to the blending weight; and synthesizing an image of the virtual viewpoint based on the blended viewpoint images.

Abstract: The present disclosure provides an apparatus and a method for selecting camera providing input images to synthesize virtual view images. According to the present disclosure, A method of selecting a camera providing as input image to synthesize a virtual view image, the method may comprise, for a camera providing an input image, determining whether or not the camera is comprised in a field of view (FoV) at a virtual view position and in response to the camera determined to be comprised in the field of view, selecting the camera to synthesize the virtual image, wherein the determining determines, by way of comparison, whether or not a direction from the virtual view position to a position of the camera is in the FoV at the virtual view position.

Abstract: A neural network feature decoding method and apparatus according to the present disclosure receives a bitstream including an encoded feature, decodes a feature from a bitstream, and reconstructs features corresponding to a plurality of layers of a neural network based on a decoded feature.

Abstract: Disclosed herein is a method for blending warped images based on depth distribution. The method includes generating images warped to a virtual viewpoint using input images, generating a blended warped image based on the warped images, and generating a final virtual viewpoint image by applying inpainting to the blended warped image.

Abstract: Disclosed herein is a method for encoding a feature map. The method may include arranging multiple channels based on similarity therebetween for a feature map having the multiple channels, rearranging the arranged multiple channels so as to be adjacent to each other in a feature map channel having a matrix form, and generating an encoded feature map by converting a feature value corresponding to the feature map channel from a real number to an integer.

Abstract: The present invention provides a laundry sheet in which at least one laundry component is distributed inside a matrix formed from a water-soluble polymer, which is a polyvinyl alcohol or a polyvinyl alcohol-based polymer, and the laundry sheet has (i) a foamability of 0.5-0.9 (g/cm3) or (ii) a drape stiffness of 3.5-7.5 cm.

Abstract: Disclosed herein is an immersive video processing method. The immersive video processing method may include classifying a multiplicity of view videos into a base view and an additional view, generating a residual video for the additional view video classified as an additional view, packing a patch, which is generated based on the residual video, into an atlas video, and generating metadata for the patch.

Abstract: Disclosed herein are an apparatus for encoding and decoding a feature map and a method using the apparatus. The feature map encoding apparatus include a processor for acquiring feature map information corresponding to a feature map, reconstructing the feature map based on the feature map information, and generating an encoded feature map by converting each feature value corresponding to the reconstructed feature map from a real number into an integer, and a memory for storing the feature map information.

Abstract: Disclosed herein are an apparatus and method for synthesizing virtual viewpoint image. The apparatus for synthesizing virtual viewpoint images includes one or more processors, and an execution memory for storing at least one program that is executed by the one or more processors, wherein the at least one program is configured to receive multiple viewpoint images from cameras that capture images of multiple viewpoints, and back-project the multiple viewpoint images onto a world coordinate system in a three-dimensional (3D) space, generate warped images by performing triangular warping of projecting the multiple viewpoint images, back-projected onto the world coordinate system, onto a virtual viewpoint image coordinate system, and generate a finally synthesized virtual viewpoint image by blending the warped images.

Abstract: A video decoding method comprises warping different viewpoint images into a virtual viewpoint by using depth information of an input viewpoint; determining a first weight for the pixels based on quality and depth of pixels of the warped viewpoint images; determining a second weight for the pixels based on a location relation between the pixels of the warped viewpoint images and the virtual viewpoint; determining a blending weight for the pixels based on the first weight and the second weight; blending the warped viewpoint images according to the blending weight; and synthesizing an image of the virtual viewpoint based on the blended viewpoint images.

Abstract: The present disclosure provides an apparatus and a method for selecting camera providing input images to synthesize virtual view images. According to the present disclosure, A method of selecting a camera providing an input image to synthesize a virtual view image, the method may comprise, for a camera providing an input image, determining whether or not the camera is comprised in a field of view (FoV) at a virtual view position and in response to the camera determined to be comprised in the field of view, selecting the camera to synthesize the virtual image, wherein the determining determines, by way of comparison, whether or not a direction from the virtual view position to a position of the camera is in the FoV at the virtual view position.

Abstract: Disclosed herein is an immersive video processing method. The immersive video processing method may include classifying a multiplicity of source view videos into base view videos and additional view videos, generating residual data for the additional view videos, packing a patch, which is generated based on the residual data, into an altas video, and generating metadata for the patch.

Abstract: Disclosed herein are an apparatus and method for synthesizing virtual viewpoint image. The apparatus for synthesizing virtual viewpoint images includes one or more processors, and an execution memory for storing at least one program that is executed by the one or more processors, wherein the at least one program is configured to receive multiple viewpoint images from cameras that capture images of multiple viewpoints, and back-project the multiple viewpoint images onto a world coordinate system in a three-dimensional (3D) space, generate warped images by performing triangular warping of projecting the multiple viewpoint images, back-projected onto the world coordinate system, onto a virtual viewpoint image coordinate system, and generate a finally synthesized virtual viewpoint image by blending the warped images.

Abstract: Disclosed herein is an immersive video processing method. The immersive video processing method may include classifying a multiplicity of view videos into a base view and an additional view, generating a residual video for the additional view video classified as an additional view, packing a patch, which is generated based on the residual video, into an atlas video, and generating metadata for the patch.

Abstract: Disclosed is a method and apparatus for providing an omni-directional stereoscopic image based on layer projection. According to an embodiment of the present disclosure, there is provided a method of providing an omni-directional stereoscopic image based on layer projection, the method including: obtaining a spatial-information-point set; and generating a layer image based on a spatial-information-point subset constructed for each of multiple layers, the layer image corresponding to each of the multiple layers, wherein the spatial-information-point subset constructed for each of two consecutive layers includes one or more duplicate spatial information points.

Abstract: The present invention provides a laundry sheet in which at least one laundry component is distributed inside a matrix formed from a water-soluble polymer, which is a polyvinyl alcohol or a polyvinyl alcohol-based polymer, and the laundry sheet has (i) a foamability of 0.5-0.9 (g/cm3) or (ii) a drape stiffness of 3.5-7.5 cm.