EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

A Generalized Slimmable INR Framework for Scalable Video Coding

Qingyu Mao, Jiacong Chen, Shuai Liu, Fanyang Meng, Yongsheng Liang, Youneng Bao

Electronics · 2026-08-13 · 15 (16) · 3609

DOI: 10.3390/electronics15163609 ↗

At a glance

Journal article in Electronics, published online on 2026-08-13. Written by Qingyu Mao and 5 co-authors. 29 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Natural Science Foundation of China, Guangdong Provincial Universities, Pengcheng Laboratory.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

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.

Funding

  • National Natural Science Foundation of China
  • Guangdong Provincial Universities
  • Pengcheng Laboratory

Cite

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}
}
Start for free →