arXiv · cs.AI · Andrey Ignatov, Georgy Perevozchikov, Radu Timofte, Fubin Ren, Shihao Wang, Liwen Zhang, Zhe Xu, Zhipei Lei, Minjian Zhang, Kailing Tang, Dingyong Gou, Yanlin Wu, Cong Li, Xiaohui Cui, Kihwan Yoon, Ganzorig Gankhuyag, Heo MyeongCheol, Yonghyun Park, Juho Jung, Sungjei Kim, Phuong-Nam Nguyen-Pham, Nam-Tien Le, Tinh-Anh Nguyen-Nhu, Matin Fazel, Abdelhak Bentaleb, Xinrui Li, Xusheng He, Jianlong Wu, Mohsin Ikram, Dmitry Ignatov, Hao Chen, Long Sun, Jiangxin Dong, Jinshan Pan, Jinhui Tang, Siyue Teng, Yuxuan Jiang, Fan Zhang, David Bull, Zhe Xiao, Jun Xiao, Zhi-Song Liu, Jiayi Pei, Songtao Wu, Hong Shang, Kuanhong Xu · 10 小时前模型评分33
Mobile 人工智能（AI，Artificial Intelligence） 2026 挑战赛报告：移动 神经网络处理器（NPU，Neural Processing Unit） 上的 4K 图像超分辨率
4K Image Super-Resolution on Mobile NPUs: Mobile AI 2026 Challenge Report
导读
Mobile 人工智能（AI，Artificial Intelligence） 2026 挑战赛要求参赛者在 Qualcomm 和 MediaTek 的移动 神经网络处理器（NPU，Neural Processing Unit） 上把 Full HD 图像放大到 4K，分为 INT8 全量化与浮点两条赛道。
分类置信度
中 · 待人工复核
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
事件类型：研究发布
证据摘录
- “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.”
- “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.”
- “the participants were provided with the DIV2K dataset and trained models to do an efficient 3X image upscaling.”
来源：arXiv · cs.AI · arxiv.org