Qualcomm Incorporated

Apoorva Nagarajan

Ashish Kumar Mishra

Sandeep Nellikatte Srivatsa

Vikrant Mahajan

Pawan Kumar Baheti

Naveen Srinivasamurthy

Narendranath Malayath

Mahant Siddaramanna

Lingfeng Li

Divya Goswami

Prasant Shekhar Singh

A device for upscale filtering video data includes one or more processors configured to generate a number of upscaled pixels that is an integer multiple of one half of a size of a filter used to upscale filter the video data. The device may then store the remaining pixels to be used to upscale filter a subsequent, right-neighboring block. In this manner, the device may avoid generating upscaled pixels that will result in being unaligned with the block and that may not be output due to being unaligned.

Upscale filtering of video data

Video decoding systems and techniques are described. The decoder applies a deblocking (DB) filter to the plurality of sub-blocks of a block of video data to generate a DB-filtered plurality of sub-blocks. The decoder applies the DB filter to one or more lines (e.g., columns) of pixels in an additional sub-block of the block to generate a DB-filtered portion of the additional sub-block. The one or more lines of pixels in the additional sub-block are filtered without filtering an entirety of the additional sub-block using the DB filter. The additional sub-block is adjacent to at least one of the plurality of sub-blocks. The decoder applies a constrained directional enhancement filter (CDEF) to the DB-filtered plurality of sub-blocks and the DB-filtered portion of the additional sub-block to generate a CDEF-filtered plurality of sub-blocks.

Systems and methods for video decoding with partial-block deblocking filtering for use by constrained directional enhancement filter

Systems and techniques are described for data encoding using a machine learning approach to generate a distortion prediction {circumflex over (D)} and a predicted bit rate {circumflex over (R)}, and to use {circumflex over (D)} and {circumflex over (R)} to perform rate-distortion optimization (RDO). For example, a video encoder can generate the distortion prediction {circumflex over (D)} and the bit rate residual predictionbased on outputs of the one or more neural networks in response to the one or more neural networks receiving a residual portion of a block of a video frame as input. The video encoder can determine bit rate metadata predictionbased on metadata associated with a mode of compression, and determine {circumflex over (R)} to be the sum ofand. The video encoder can determine a rate-distortion cost prediction &#x134; as a function of {circumflex over (D)} and {circumflex over (R)}, and can determine a prediction mode for compressing the block based on &#x134;.

Machine learning based rate-distortion optimizer for video compression

Growing community of inventors

Bengaluru, India

Apoorva Nagarajan