EUVIMEDEUVIMED entdecken
Crossref

I-INR: Iterative Implicit Neural Representations

Ali Haider, Muhammad Salman Ali, Maryam Qamar, Tahir Khalil, Soo Ye Kim, Jihyong Oh, Enzo Tartaglione, Sung-Ho Bae

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (6) · 4520-4528

DOI: 10.1609/aaai.v40i6.42451 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Ali Haider und 7 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Implicit Neural Representations (INRs) have revolutionized signal processing and computer vision by modeling signals as continuous, differentiable functions parameterized by neural networks. However, INRs are prone to the spectral bias problem, limiting their ability to retain high-frequency information, and often struggle with noise robustness. Motivated by recent trends in iterative refinement processes, we propose Iterative Implicit Neural Representations (I-INRs). This novel plug-and-play framework iteratively refines signal reconstructions to restore high-frequency details, improve noise robustness, and enhance generalization, ultimately delivering superior reconstruction quality. I-INRs integrate seamlessly into existing INR architectures with only a 0.5–2% increase in parameters. During reconstruction, the iterative refinement adds just 0.8–1.6% additional FLOPs over the baseline while delivering a substantial performance boost of up to +2.0 PSNR. Extensive experiments demonstrate that I-INRs consistently outperform WIRE, SIREN, and Gauss across various computer vision tasks, including image fitting, image denoising, and object occupancy prediction.

Zitieren

APA

Haider, A., Ali, M. S., Qamar, M., Khalil, T., Kim, S. Y., Oh, J., Tartaglione, E., & Bae, S. (2026). I-INR: Iterative Implicit Neural Representations. Proceedings of the AAAI Conference on Artificial Intelligence, 40(6), 4520-4528. https://doi.org/10.1609/aaai.v40i6.42451

Vancouver

Haider A, Ali MS, Qamar M, Khalil T, Kim SY, Oh J, et al. I-INR: Iterative Implicit Neural Representations. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(6):4520-4528. doi:10.1609/aaai.v40i6.42451

BibTeX
@article{Haider2026,
  author = {Haider, Ali and Ali, Muhammad Salman and Qamar, Maryam and Khalil, Tahir and Kim, Soo Ye and Oh, Jihyong and Tartaglione, Enzo and Bae, Sung-Ho},
  title = {I-INR: Iterative Implicit Neural Representations},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {6},
  pages = {4520--4528},
  doi = {10.1609/aaai.v40i6.42451}
}
Kostenlos starten →