Independent localization of auxiliary information in neural network-based image processing

Methods and apparatus are provided for processing image data or image feature data using a neural network having two or more layers. The method can be applied to the technical field of video or image compression based on artificial intelligence (AI), in particular to the technical field of video compression based on a neural network. According to some embodiments, the two data are combined during processing including processing by the neural network. The two kinds of data are obtained by the network from different processing stages. Some advantages may include the neural network architecture having greater scalability and more flexible design, so that encoding/decoding performance may be further improved. 本申请提供了用于使用具有两个或两个以上层的神经网络处理图像数据或图像特征数据的方法和装置。本发明可应用于基于人工智能(artificial intelligence，AI)的视频或图像压缩技术领域，尤其应用于基于神经网络的视频压缩技术领域。根据一些实施例，在包括由所述神经网络处理等处理期间组合两种数据。所述两种数据是由所述网络从不同处理级获得的。一些优点可以包括神经网络架构具有更大的可扩展性和更灵活的设计，从而可以进一步提高编码/解码性能。