Group-aware Parameter-efficient Updating for Content-Adaptive Neural Video Compression

arXiv:2405.04274v1 Announce Type: cross
Abstract: Content-adaptive compression is crucial for enhancing the adaptability of the pre-trained neural codec for various contents. Although these methods have been very practical in neural image compression (NIC), their application in neural video compression (NVC) is still limited due to two main aspects: 1), video compression relies heavily on temporal redundancy, therefore updating just one or a few frames can lead to significant errors accumulating over time; 2), NVC frameworks are generally more complex, with …

abstract adaptability application arxiv codec compression contents cs.cv eess.iv image practical type video video compression