Systems and methods for signaling neural network post-filter filter strength control information in video coding
A device may be configured to perform filtering based on information included in a neural network post-filter characteristics message. In one example, the neural network post-filter characteristics message includes a syntax element indicating auxiliary input data is present in an input tensor of the neural network post-filter. The device may derive a filtering strength control value array where each entry in the array is based on a quantization parameter of a respective input picture for the neural network post-filter.
1. A method of performing neural network filtering for video data, the method comprising:
receiving a neural network post-filter characteristics message;
parsing a first syntax element from the neural network post-filter characteristics message indicating whether auxiliary input data is present in an input tensor of a neural network post-filter; and
deriving a filtering strength control value array where an entry in the filtering strength control value array is based on a quantization parameter of an input picture for the neural network post-filter,
where the entry in the filtering strength control value array is set equal to a value of (SliceQpY+QpBdOffset)÷(63+QpBdOffset) of a first slice of the input picture,
wherein SliceQpY is based on the quantization parameter, and
QpBdOffset is based on a bit depth.
2. A device comprising one or more processors configured to:
receive a neural network post-filter characteristics message;
parse a first syntax element from the neural network post-filter characteristics message indicating whether auxiliary input data is present in an input tensor of a neural network post-filter; and
derive a filtering strength control value array where an entry in the filtering strength control value array is based on a quantization parameter of an input picture for the neural network post-filter,
where the entry in the filtering strength control value array is set equal to a value of (SliceQpY+QpBdOffset)÷(63+QpBdOffset) of a first slice of the input picture,
wherein SliceQpY is based on the quantization parameter, and
QpBdOffset is based on a bit depth.
3. The device of claim 2 , wherein the device includes a video decoder.