Bildfilterungsverfahren und -Vorrichtung auf Basis eines Neuronalen Netzwerks, Codierungsverfahren, Decodierungsverfahren, Vorrichtung und Speichermedium

Details

Veröffentlichungs-Nr.

EP4734045

Anmeldetag

6. Mai 2024

Veröffentlichung

2. Januar 2025

Rechtsraum

EP

IPC

G06T5/50, H04N19/85

Abstract

This application provides neural network-based picture filtering, encoding, and decoding methods and apparatuses, a device, and a storage medium. The method may be applied to fields such as picture processing, video encoding and decoding, and video live streaming, and includes: determining input information of a neural network loop filter (NNLF) based on a to-be-filtered picture, the input information including the to-be-filtered picture; and filtering the input information through the NNLF to obtain a filtered picture of the to-be-filtered picture, wherein the NNLF includes a plurality of convolution layers configured to extract picture feature information, and the plurality of convolution layers are obtained by processing a standard convolution layer in at least two of a multi-level receptive field (MLRF) mode, a tensor decomposition mode, and a group convolution (GC) mode. Thus, the filtering operation complexity of the NNLF is reduced without reducing the filtering performance of the NNLF, thereby improving the picture filtering effect.

Anmelder

Firma

Tencent Technology (Shenzhen) Company Limited

Land

🇨🇳 China