H Kim, M Bauer, L Theis… - Proceedings of the …, 2024 - openaccess.thecvf.com
Most neural compression models are trained on large datasets of images or videos in order to generalize to unseen data. Such generalization typically requires large and expressive …
HM Kwan, G Gao, F Zhang… - Advances in Neural …, 2024 - proceedings.neurips.cc
Learning-based video compression is currently a popular research topic, offering the potential to compete with conventional standard video codecs. In this context, Implicit Neural …
B Chen, S Yin, P Chen, S Wang, Y Ye - arXiv preprint arXiv:2402.02140, 2024 - arxiv.org
Artificial Intelligence Generated Content (AIGC) is leading a new technical revolution for the acquisition of digital content and impelling the progress of visual compression towards …
Y Tian, G Lu, G Zhai, Z Gao - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Most video compression methods aim to improve the decoded video visual quality, instead of particularly guaranteeing the semantic-completeness, which deteriorates downstream …
X Sheng, L Li, D Liu, H Li - … on Circuits and Systems for Video …, 2024 - ieeexplore.ieee.org
Video compression performance is closely related to the accuracy of inter prediction. It tends to be difficult to obtain accurate inter prediction for the local video regions with inconsistent …
T van Rozendaal, T Singhal, H Le… - Proceedings of the …, 2024 - openaccess.thecvf.com
Neural video codecs have recently become competitive with standard codecs such as HEVC in the low-delay setting. However, most neural codecs are large floating-point networks that …
Video coding that pursues the highest compression efficiency is the art of computing for rate- distortion optimization. The optimization has been approached in different ways, exemplified …
T Xu, H Gao, C Gao, Y Wang, D He… - International …, 2023 - proceedings.mlr.press
In this paper, we consider the problem of bit allocation in Neural Video Compression (NVC). First, we reveal a fundamental relationship between bit allocation in NVC and Semi …
Video compression relies heavily on exploiting the temporal redundancy between video frames, which is usually achieved by estimating and using the motion information. The …