To encode High Dynamic Range (HDR) images, the HDR images can be converted to Low Dynamic Range (LDR) images through tone mapping operation, and the LDR images can be encoded with an LDR encoder. The present principles formulates a rate distortion minimization problem when designing the tone mapping curve. In particular, the tone mapping curve is formulated as a function of the probability distribution function of the HDR images to be encoded and a Lagrangian multiplier that depends on encoding parameters. At the decoder, based on the parameters indicative of the tone mapping function, an inverse tone mapping function can be derived to reconstruct HDR images from decoded LDR images.

An image coding apparatus, comprising an image reconstruction unit configured to reconstruct an image, a parameter determination unit configured to determine one or more filter parameters, based on one or more first parameters which are based on the reconstructed image and one or more second parameters which are based on codec signaling information, and a mixed-domain filtering unit configured to filter in a frequency domain and a pixel domain the reconstructed image based on the determined filter parameters to obtain a filtered image.

An image coding apparatus, comprising an image reconstruction unit configured to reconstruct an image, a parameter determination unit configured to determine one or more filter parameters, based on one or more first parameters which are based on the reconstructed image and one or more second parameters which are based on codec signaling information, and a mixed-domain filtering unit configured to filter in a frequency domain and a pixel domain the reconstructed image based on the determined filter parameters to obtain a filtered image.

A decoding apparatus is provided. The decoding apparatus includes a communication unit for receiving multiple encoding data respectively corresponding to multiple areas constituting one image, and reference data including attribute information of each of the multiple areas, and a processor for generating multiple divided images by decoding the multiple encoding data respectively, changing the resolutions of some divided images among the multiple divided images on the basis of the received attribute information, and generating a reconstructed image by merging the some divided images having the changed resolutions and the remaining divided images.

A decoding apparatus is provided. The decoding apparatus includes a communication unit for receiving multiple encoding data respectively corresponding to multiple areas constituting one image, and reference data including attribute information of each of the multiple areas, and a processor for generating multiple divided images by decoding the multiple encoding data respectively, changing the resolutions of some divided images among the multiple divided images on the basis of the received attribute information, and generating a reconstructed image by merging the some divided images having the changed resolutions and the remaining divided images.

An apparatus for encoding a block of a picture includes a convolutional neural network (CNN) for determining a block partitioning of the block, the block having an NN size and a smallest partition determined by the CNN being of size SS. The CNN includes feature extraction layers; a concatenation layer that receives, from the feature extraction layers, first feature maps of the block, where each first feature map of the first feature maps is of the smallest possible partition size SS of the block; and at least one classifier that is configured to infer partition decisions for sub-blocks of size (S)(S) of the block, where is a power of 2.

An apparatus for encoding a block of a picture includes a convolutional neural network (CNN) for determining a block partitioning of the block, the block having an NN size and a smallest partition determined by the CNN being of size SS. The CNN includes feature extraction layers; a concatenation layer that receives, from the feature extraction layers, first feature maps of the block, where each first feature map of the first feature maps is of the smallest possible partition size SS of the block; and at least one classifier that is configured to infer partition decisions for sub-blocks of size (S)(S) of the block, where is a power of 2.

A method for processing a video stream prior to encoding, the video stream potentially comprising a film grain, the method comprising: measuring a film grain intensity in the video stream; obtaining at least one encoding rate information item associated with the video stream, in order to determine a pair of respective values for the grain intensity and encoding rate; comparing the pair values with predetermined respective threshold values in order to categorize the video stream with respect to pairs of predetermined values of grain intensity and rate; and selecting a film grain management strategy among at least four combinations based on the categorization of the video stream.

A coding method and a decoding method for decoding a coded data stream representative of at least one image that is split into blocks. For at least one current block of the image, an item of information indicating a coding mode of the current block is decoded from the data stream. When the coding mode of the current block corresponds to a first coding mode, the current block is decoded using a first determined quantization step to dequantize, in the transform domain, a prediction residue associated with the current block. When the coding mode of the current block corresponds to a second coding mode, the current block is decoded using a second determined quantization step to dequantize, in the spatial domain, a prediction residue associated with the current block. The first quantization step and the second quantization step are determined according to the same quantization parameter.

A coding method and a decoding method for decoding a coded data stream representative of at least one image that is split into blocks. For at least one current block of the image, an item of information indicating a coding mode of the current block is decoded from the data stream. When the coding mode of the current block corresponds to a first coding mode, the current block is decoded using a first determined quantization step to dequantize, in the transform domain, a prediction residue associated with the current block. When the coding mode of the current block corresponds to a second coding mode, the current block is decoded using a second determined quantization step to dequantize, in the spatial domain, a prediction residue associated with the current block. The first quantization step and the second quantization step are determined according to the same quantization parameter.