A Projection-Based Surrogate Gradient Interpretation for Neural Codec Wrappers

arXiv:2606.20671v1 Announce Type: new Abstract: Neural wrappers are learned pre-and postprocessing networks designed to enhance the performance of conventional video codecs. Although these approaches can significantly improve compression efficiency, training them remains challenging due to the non-differentiability of video codecs, which arises from the multiple discrete decisions involved in the encoding process. Surrogate gradients have recently emerged as an effective solution for enabling en...