A method for processing image or video data is performed in an image processing pipeline. Color filtered mosaiced raw image or video data is received. A one-level wavelet transform of subbands of the color filtered mosaiced raw image or video data to provide LL, HH, LH and HL subbands. The LH and HL subbands are de-correlated by summing and difference operations to provide decorrelated sum and difference subbands. Additional n-level wavelet transformation on the sum and difference subbands and the LL and HH subbands to provide sparsified subbands for encoding. LL and HH and sum subbands are recombined into standard color images e.g., red, green, and blue color components, which are subsequently processed by color correction, white balance, and gamma correction. The sparsified subbands are encoded.

A method for processing image or video data is performed in an image processing pipeline. Color filtered mosaiced raw image or video data is received. A one-level wavelet transform of subbands of the color filtered mosaiced raw image or video data to provide LL, HH, LH and HL subbands. The LH and HL subbands are de-correlated by summing and difference operations to provide decorrelated sum and difference subbands. Additional n-level wavelet transformation on the sum and difference subbands and the LL and HH subbands to provide sparsified subbands for encoding. LL and HH and sum subbands are recombined into standard color images e.g., red, green, and blue color components, which are subsequently processed by color correction, white balance, and gamma correction. The sparsified subbands are encoded.

Embodiments of the present invention relate to methods and systems for ordering, communicating and applying pixel intra-prediction modes.

Methods of encoding and decoding for video data are described in which multi-level significance maps are used in the encoding and decoding processes. The significant-coefficient flags that form the significance map are grouped into contiguous groups, and a significant-coefficient-group flag signifies for each group whether that group contains no non-zero significant-coefficient flags. A multi-level scan order may be used in which significant-coefficient flags are scanned group-by-group. The group scan order specifies the order in which the groups are processed, and the scan order specifies the order in which individual significant-coefficient flags within the group are processed. The bitstream may interleave the significant-coefficient-group flags and their corresponding significant-coefficient flags, if any.

Methods of encoding and decoding for video data are described in which multi-level significance maps are used in the encoding and decoding processes. The significant-coefficient flags that form the significance map are grouped into contiguous groups, and a significant-coefficient-group flag signifies for each group whether that group contains no non-zero significant-coefficient flags. A multi-level scan order may be used in which significant-coefficient flags are scanned group-by-group. The group scan order specifies the order in which the groups are processed, and the scan order specifies the order in which individual significant-coefficient flags within the group are processed. The bitstream may interleave the significant-coefficient-group flags and their corresponding significant-coefficient flags, if any.

Wavelet transformation is performed on first image data and second image data until a decomposition level becomes a decomposition level based on synthesis control data or the like, and first wavelet coefficient data and second wavelet coefficient data are thereby generated. An ROI coefficient related to an ROI and a non-ROI coefficient in the first wavelet coefficient data are determined on the basis of mask data and the ROI coefficient in the first wavelet coefficient data and a wavelet coefficient in the second wavelet coefficient data are synthesized with each other, and synthesized coefficient data are thereby generated. Inverse wavelet transformation is performed on the synthesized coefficient data until a decomposition level becomes a predetermined end level, and synthetic image data are thereby generated.

An ROI coefficient and a non-ROI coefficient in first wavelet coefficient data corresponding to a first target image are determined on the basis of mask data which is developed for the first wavelet coefficient data. The ROI coefficient in the first wavelet coefficient data and a coefficient in second wavelet coefficient data corresponding to a second target image are synthesized. Synthesized coefficient data are thereby generated. Inverse wavelet transformation is performed on the synthesized coefficient data until a decomposition level becomes a predetermined end level. Synthetic image data are thereby generated.

An ROI coefficient and a non-ROI coefficient in first wavelet coefficient data corresponding to a first target image are determined on the basis of mask data which is developed for the first wavelet coefficient data. The ROI coefficient in the first wavelet coefficient data and a coefficient in second wavelet coefficient data corresponding to a second target image are synthesized. Synthesized coefficient data are thereby generated. Inverse wavelet transformation is performed on the synthesized coefficient data until a decomposition level becomes a predetermined end level. Synthetic image data are thereby generated.

In one embodiment, an apparatus comprises a memory and a processor. The memory is to store visual data associated with a visual representation captured by one or more sensors. The processor is to: obtain the visual data associated with the visual representation captured by the one or more sensors, wherein the visual data comprises uncompressed visual data or compressed visual data; process the visual data using a convolutional neural network (CNN), wherein the CNN comprises a plurality of layers, wherein the plurality of layers comprises a plurality of filters, and wherein the plurality of filters comprises one or more pixel-domain filters to perform processing associated with uncompressed data and one or more compressed-domain filters to perform processing associated with compressed data; and classify the visual data based on an output of the CNN.

Described herein is an image processing apparatus (701) comprising one or more processors (704) configured to: receive (601) a plurality of input images (301, 302, 303); for each input image, form (602) a set of decomposed data by decomposing the input image (301, 302, 303) or a filtered version thereof (307, 308, 309) into a plurality of frequency-specific components (313) each representing the occurrence of features of a respective frequency interval in the input image or the filtered version thereof; process (603) each set of decomposed data using one or more convolutional neural networks to form a combined image dataset (327); and subject (604) the combined image dataset (327) to a construction operation that is adapted for image construction from a plurality of frequency-specific components to thereby form an output image (333) representing a combination of the input images. The resulting HDR output image may have fewer artifacts and provide a better quality result. The apparatus is also computationally efficient, having a good balance between accuracy and efficiency.