ResiComp: Loss-Resilient Image Compression via Dual-Functional Masked Visual Token Modeling
IEEE Transactions on Circuits and Systems for Video Technology · 2025-07 · 35 (7) · 7181-7195
DOI: 10.1109/tcsvt.2025.3539747 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-07. Verfasst von Sixian Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Beijing Municipal Natural Science Foundation.
Abstract (Originalsprache)
Recent advancements in neural image codecs (NICs) are of significant compression performance, but limited attention has been paid to their error resilience. These resulting NICs tend to be sensitive to packet losses, which are prevalent in real-time communications. In this paper, we investigate how to elevate the resilience ability of NICs to combat packet losses. We propose ResiComp, a pioneering neural image compression framework with feature-domain packet loss concealment (PLC). Motivated by the inherent consistency between generation and compression, we advocate merging the tasks of entropy modeling and PLC into a unified framework focused on latent space context modeling. To this end, we take inspiration from the impressive generative capabilities of large language models (LLMs), particularly the recent advances of masked visual token modeling (MVTM). In specific, ResiComp develops a bi-directional masked Transformer to model the contextual dependencies among latents with dual-functionality: 1) iteratively acts as a conditional entropy model to boost compression efficiency; 2) operates latent PLC to improve resilience. During training, we integrate MVTM to mirror the effects of packet loss, enabling a dual-functional Transformer to restore the masked latents by predicting their missing values and conditional probability mass functions. Our ResiComp jointly optimizes compression efficiency and loss resilience. Moreover, ResiComp provides flexible coding modes, allowing for explicitly adjusting the efficiency-resilience trade-off in response to varying Internet or wireless network conditions. Extensive experiments demonstrate that ResiComp can significantly enhance the NIC’s resilience against packet losses, while exhibits a worthy trade-off between compression efficiency and packet loss resilience. Additionally, packet-level simulations, conducted using diverse network models based on real traces, demonstrate that ResiComp exhibits much better robustness to fluctuating network conditions compared to redundancy-based approaches like VTM + FEC.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Beijing Municipal Natural Science Foundation
- Young Elite Scientists Sponsorship Ph.D. Program by China Association for Science and Technology
- Program for Youth Innovative Research Team of Beijing University of Posts and Telecommunications
Zitieren
APA
Wang, S., Dai, J., Qin, X., Yang, K., Niu, K., & Zhang, P. (2025). ResiComp: Loss-Resilient Image Compression via Dual-Functional Masked Visual Token Modeling. IEEE Transactions on Circuits and Systems for Video Technology, 35(7), 7181-7195. https://doi.org/10.1109/tcsvt.2025.3539747
Vancouver
Wang S, Dai J, Qin X, Yang K, Niu K, Zhang P. ResiComp: Loss-Resilient Image Compression via Dual-Functional Masked Visual Token Modeling. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(7):7181-7195. doi:10.1109/tcsvt.2025.3539747
BibTeX
@article{Wang2025,
author = {Wang, Sixian and Dai, Jincheng and Qin, Xiaoqi and Yang, Ke and Niu, Kai and Zhang, Ping},
title = {ResiComp: Loss-Resilient Image Compression via Dual-Functional Masked Visual Token Modeling},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2025},
volume = {35},
number = {7},
pages = {7181--7195},
doi = {10.1109/tcsvt.2025.3539747}
}
EUVIMED