Abstract: A method and an apparatus for encoding a picture are disclosed. For at least one block of a picture to encode, a block predictor is determined (22) for a decoded first component (21) of said at least one block, from a reconstructed region of a first component of said picture. At least one second component of said at least one block is then encoded (23) by predicting said at least one second component from a second component of said block predictor. Corresponding decoding method and apparatus are disclosed.

Abstract: The present disclosure generally relates to a method for predicting at least one block of pixels of a view (170) belonging to a matrix of views (17) obtained from light-field data belong with a scene. According to present disclosure, the method is implemented by a processor and comprises for at least one pixel to predict of said block of pixels: —from said matrix of views (17), obtaining (51) at least one epipolar plane image (EPI) belong with said pixel to predict, —among a set of unidirectional prediction modes, determining (52) at least one optimal unidirectional prediction mode from a set of previous reconstructed pixels neighboring said pixel to predict in said at least one epipolar plane image, —extrapolating (53) a prediction value of said pixel to predict by using said at least one optimal unidirectional prediction mode.

Abstract: The present disclosure generally relates to a method for predicting at least one block of pixels of a view (170) belonging to a matrix of views (17) obtained from light-field data belong with a scene, According to present disclosure, the method is implemented by a processor and comprises for at least one pixel to predict of said block of pixels: —from said matrix of views (17), obtaining (51) at least one epipolar plane image (EPI) belong with said at least one pixel to predict, —among a set of bidirectional prediction modes, determining (52) at least one optimal bidirectional prediction mode from a set of previous reconstructed pixels neighbouring said at least one pixel to predict in said at least one epipolar plane image, —extrapolating (53) a prediction value of said at least one pixel to predict by using said at least one optimal bidirectional prediction mode.

Abstract: A method and an apparatus for encoding a picture are disclosed. For at least one block of a picture to encode, a block predictor is determined (22) for a decoded first component (21) of said at least one block, from a reconstructed region of a first component of said picture. At least one second component of said at least one block is then encoded (23) by predicting said at least one second component from a second component of said block predictor. Corresponding decoding method and apparatus are disclosed.

Abstract: A method for generating at least one image with a first dynamic range, from an image with a second dynamic range, which is lower than the first dynamic range is described. The method includes obtaining an epitome of the image with a first dynamic range, called a first epitome. Thereafter, the image with a first dynamic range is generated from the image with a second dynamic range and the first epitome.

Abstract: The present disclosure generally relates to a method for predicting at least one block of pixels of a view (170) belonging to a matrix of views (17) obtained from light-field data belong with a scene, According to present disclosure, the method is implemented by a processor and comprises for at least one pixel to predict of said block of pixels: —from said matrix of views (17), obtaining (51) at least one epipolar plane image (EPI) belong with said at least one pixel to predict, —among a set of bidirectional prediction modes, determining (52) at least one optimal bidirectional prediction mode from a set of previous reconstructed pixels neighbouring said at least one pixel to predict in said at least one epipolar plane image, —extrapolating (53) a prediction value of said at least one pixel to predict by using said at least one optimal bidirectional prediction mode.

Abstract: An aspect of present principles is directed to methods, apparatus, systems and computer readable media for image processing. The image processing may include receiving a standard dynamic range (SDR) image or a receiver for receiving a standard dynamic range (SDR) image. It may further include determining an over-exposed region of the SDR image and determining a corrected luminance value for at least a pixel of the over-exposed region, or a processor configured to determine an over-exposed region of the SDR image and a corrected luminance value for at least a pixel of the over-exposed region. The corrected luminance value is determined based on at least one of a shape of the over-exposed region, luminance information of pixels surrounding the over-exposed region, and edge information of the pixels surrounding the over-exposed region. The over-exposed region may be an irregularly shaped region.

Abstract: Aspects of present principles are directed to methods and apparatus for tone mapping a high dynamic range image. The apparatus includes a processor for performing the following and the method includes the following: obtaining a luminance component of the high dynamic range image; determining an hdr-to-hdr tone mapper curve; determining a tone compressed image by applying the hdr-to-hdr tone mapper curve to the luminance component of the high dynamic range image; wherein the hdr-to-hdr tone mapper curve comprises a linear part for dark and mid-tone levels, and a compressive non-linear part for highlights.

Abstract: A method is proposed for filling-in missing regions in an image of a multimedia content. Such method comprises, for a block x comprising a patch xa of known pixels and a patch xu of unknown pixels: obtaining (300) a set {yi} of N blocks of pixels; splitting (310) the set {yi} for providing a set {yia}, respectively {yiu}, of N patches referring to pixels in the set {yi} having the same relative spatial positions as xa, respectively xu, in x; determining (320) a fill-in patch yfill based on an optimization of an objective function subject to a boundary smoothness constraint taking into account at least one isophote vector estimated at position of at least one pixel p in xa for insuring a smooth transition between the patches xa and xu; filling-in (330) missing regions in the image by associating the patch yfill to the patch xu.

Abstract: A method for enhancing quality of an image comprises deriving from an initial low-resolution image (LRI) an initial high-resolution image (IHRI) by upsampling (S2, S3), providing (S4), based on the initial low-resolution image (LRI), at least one downsampled filtered image (AIij, AIi?j?) with lower resolution, providing (S6), based on the initial low-resolution image (LRI), an unfiltered image (LRI, UIi?j?) having same resolution as the downsampled filtered image, selecting a patch (PI) from the initial high-resolution image (IHRI), finding (S8) filial patches (PA k) similar to the selected patch in the downsampled filtered image (AIij, AIi?j?), finding, in the unfiltered image (LRI, UIi?j?), parent patches (PPk) locally associated to the filial patches (PAk), and linearly combining (S14) the parent patches (PPk) to form an enhanced quality patch (EP).

Abstract: Different implementations are described, in particular, implementations for coding and decoding a scalable stream comprising a base layer and at least one enhancement layer. For example, one method provides for decoding a first part of the enhancement layer relating to a group of blocks into decoded enhancement data which comprise at least one item of information for identifying at least one region of the reconstructed at least one image and obtaining residues for at least one block of the group of blocks from a second part of the enhancement layer.

Abstract: A method for enhancing quality of an image comprises deriving from an initial low-resolution image (LRI) an initial high-resolution image (IHRI) by upsampling (S2, S3), providing (S4), based on the initial low-resolution image (LRI), at least one downsampled filtered image (AIij, AIi?j?) with lower resolution, providing (S6), based on the initial low-resolution image (LRI), an unfiltered image (LRI, UIi?j?) having same resolution as the downsampled filtered image, selecting a patch (PI) from the initial high-resolution image (IHRI), finding (S8) filial patches (PA k) similar to the selected patch in the downsampled filtered image (AIij, AIi?j?), finding, in the unfiltered image (LRI, UIi?j?), parent patches (PPk) locally associated to the filial patches (PAk), and linearly combining (S14) the parent patches (PPk) to form an enhanced quality patch (EP).

Abstract: Super-resolution refers to a process of recovering the missing high-frequency details of a given low-resolution image. Known single image SR algorithms are often computationally intractable or unusable for most of the practical applications. The invention relates to a method for performing hierarchical super-resolution based on self content neighboring patches information is based on pyramidal decomposition. The intrinsic geometric property of an input LR patch neighborhood is obtained from the input LR patch and its K nearest neighbors taken from different down-scaled versions of the LR image.

Abstract: An aspect of present principles is directed to methods, apparatus, systems and computer readable media for image processing. The image processing may include receiving a standard dynamic range (SDR) image or a receiver for receiving a standard dynamic range (SDR) image. It may further include determining an over-exposed region of the SDR image and determining a corrected luminance value for at least a pixel of the over-exposed region, or a processor configured to determine an over-exposed region of the SDR image and a corrected luminance value for at least a pixel of the over-exposed region. The corrected luminance value is determined based on at least one of a shape of the over-exposed region, luminance information of pixels surrounding the over-exposed region, and edge information of the pixels surrounding the over-exposed region. The over-exposed region may be an irregularly shaped region.

Abstract: A method for generating at least one image with a first dynamic range, from an image with a second dynamic range, which is lower than the first dynamic range is described. The method includes obtaining an epitome of the image with a first dynamic range, called a first epitome. Thereafter, the image with a first dynamic range is generated from the image with a second dynamic range and the first epitome.

Abstract: A method for decoding a scalable stream comprising a base layer and at least one enhancement layer is described. The method includes: reconstructing at least one image from the base layer, decoding a first part of the enhancement layer relating to a group of blocks into decoded enhancement data which comprise at least one item of information for identifying at least one region of the reconstructed at least one image, processing the region of the reconstructed at least one image identified by the information, obtaining residues for at least one block of the group of blocks from a second part of the enhancement layer, and reconstructing the blocks of the group from residues and from the region processed.

Abstract: A method and apparatus for dynamic range expansion of an LDR video sequence are suggested. The suggested method comprises the steps of: acquiring the LDR video sequence and at least one HDR panoramas concurrently, an image in said HDR encompassing a wider field of view than an image in said LDR; determining a dynamic range expansion operator based on the LDR video sequence and the HDR panoramas; and applying the determined dynamic range expansion operator on the LDR video sequence.

Abstract: Super-resolution refers to a process of recovering the missing high-frequency details of a given low-resolution image. Known single image SR algorithms are often computationally intractable or unusable for most of the practical applications. The invention relates to a method for performing hierarchical super-resolution based on self content neighboring patches information is based on pyramidal decomposition. The intrinsic geometric property of an input LR patch neighborhood is obtained from the input LR patch and its K nearest neighbors taken from different down-scaled versions of the LR image.