Metraipolis › archive › dc_402c34ded1df

4K Image Super-Resolution on Mobile NPUs: Mobile AI 2026 Challenge Report — arXiv:2611.00963

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.00963
License (as archived): CC0-1.0
Archived: 2026-11-03T10:56:20.304Z
SHA-256 of the archived text: f97f3a55dcada90c37a152538963045f8a1bc0bd3a6e20a81e94b0bf45e2c5ee
Stable URL of this page: https://metraipolis.com/documento/dc_402c34ded1df

How to cite

4K Image Super-Resolution on Mobile NPUs: Mobile AI 2026 Challenge Report — arXiv:2611.00963 — arXiv (en), https://arxiv.org/abs/2611.00963 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_402c34ded1df (Metraipolis archive dc_402c34ded1df, sha256 f97f3a55dcada90c37a152538963045f8a1bc0bd3a6e20a81e94b0bf45e2c5ee)

BibTeX

@misc{dc402c34ded1df,
  title = {4K Image Super-Resolution on Mobile NPUs: Mobile AI 2026 Challenge Report — arXiv:2611.00963},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00963},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_402c34ded1df; sha256 f97f3a55dcada90c37a152538963045f8a1bc0bd3a6e20a81e94b0bf45e2c5ee},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00963. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Image super-resolution is widely used on mobile devices for upscaling various types of image data. This creates a need for efficient deep learning-based models that are not only performant but can also be deployed on neural processing units (NPUs) present in the majority of mobile and IoT chipsets. In this Mobile AI challenge, we address this problem and propose the participants to design fast solutions that can upsample images from Full HD to 4K resolution while running on popular mobile NPUs from Qualcomm and MediaTek. For this, the participants were provided with the DIV2K dataset and trained models to do an efficient 3X image upscaling. The competition had two tracks: in the first track, the models had to be fully quantized (INT8), and the runtime of all models was evaluated on the Qualcomm Snapdragon 8 Elite Gen 5 NPU. In the second track, the participants were developing floating-point solutions that were evaluated on the MediaTek Dimensity 9500 NPU. Top solutions proposed in this challenge are able to reconstruct 4K images under 5 milliseconds while reaching a PSNR score of 30 dB. A comprehensive description of the models developed in the challenge is provided in this paper.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.00963 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T10:49:38.523Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).