A Generalized Slimmable INR Framework for Scalable Video Coding
Electronics · 13.08.2026 · 15 (16) · 3609
DOI: 10.3390/electronics15163609 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 13.08.2026. Verfasst von Qingyu Mao und 5 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Guangdong Provincial Universities, Pengcheng Laboratory.
Abstract (Originalsprache)
Implicit neural representations (INRs) encode video frames as network weights, offering a new compression paradigm. A persistent limitation is that existing INR codecs train one model per target bitrate, so multi-rate deployment needs separate runs, separate checkpoints, and model reloading, costs that grow with the number of rate points. We propose a Generalized Slimmable Framework that replaces standard layers with width-configurable counterparts in most INR decoders, letting a single checkpoint serve multiple bitrates through nested weight tensors without topology changes. To recover the quality lost in shared-weight training, we introduce Slimmable Conditional Decoder Modulation (SCDM), which blends slimmable expert convolutions via width- and frame-conditioned gating. For encoder-based backbones, encoder output caching separates encoder computation from multi-width training. Across four INR backbones on DAVIS and Bunny, the framework cuts multi-rate storage by about 2.3–2.5×, and SCDM recovers substantial quality at all rate points while surpassing independently trained fixed-width models at narrow widths.
Förderung
- National Natural Science Foundation of China
- Guangdong Provincial Universities
- Pengcheng Laboratory
Zitieren
APA
Mao, Q., Chen, J., Liu, S., Meng, F., Liang, Y., & Bao, Y. (2026). A Generalized Slimmable INR Framework for Scalable Video Coding. Electronics, 15(16), 3609. https://doi.org/10.3390/electronics15163609
Vancouver
Mao Q, Chen J, Liu S, Meng F, Liang Y, Bao Y. A Generalized Slimmable INR Framework for Scalable Video Coding. Electronics. 2026;15(16):3609. doi:10.3390/electronics15163609
BibTeX
@article{Mao2026,
author = {Mao, Qingyu and Chen, Jiacong and Liu, Shuai and Meng, Fanyang and Liang, Yongsheng and Bao, Youneng},
title = {A Generalized Slimmable INR Framework for Scalable Video Coding},
journal = {Electronics},
year = {2026},
volume = {15},
number = {16},
pages = {3609},
doi = {10.3390/electronics15163609}
}
EUVIMED