Adaptive clipping in models parameters derivations methods for video compression

A method of video encoding, comprising:

• determining to code a current block in a current picture using a model based prediction technique, the model based prediction technique generating a prediction sample of the current block based on a model with one or more reconstructed samples of a reference block being input to the model, the model including one or more parameters derived based on a current template of the current block and a reference template of the reference block;
• performing at least a clipping operation on at least one of the current template and the reference template to obtain clipped template samples;
• deriving one or more parameter values of the one or more parameters of the model according to the clipped template samples;
• and
• encoding the current block based on the model with the one or more parameters being set to the one or more parameter values.

A method of processing visual media data, the method comprising:

• processing a bitstream of visual media data according to a format rule:
• the bitstream includes coded information of a current block in a current picture, the coded information indicating a prediction of a current block in a current picture using a model based prediction technique, the model based prediction technique generating a prediction sample of the current block based on a model with one or more reconstructed samples of a reference block being input to the model, the model including one or more parameters derived based on a current template of the current block and a reference template of the reference block;
• and
• the format rule specifies that:
• at least a clipping operation is performed on at least one of the current template and the reference template to obtain clipped template samples;
• one or more parameter values of the one or more parameters of the model are derived according to the clipped template samples;
• and
• at least a prediction sample of the current block is generated by the model with the one or more parameters being set to the one or more parameter values.