4K Image Super-Resolution on Mobile NPUs: Mobile AI 2026 Challenge Report
cs.CV, cs.AI
Submitted: 2026-10-31
Updated: 2026-10-31
Code: https://github.com/aiff22/MAI-2025-Workshop
Project page: https://ai-benchmark.com/workshops/mai/2026
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
The gist: Image super-resolution is widely used on mobile devices for upscaling various types of image data.
Terminology
Abstract
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.
Sources
- Understanding and Overcoming the Challenges of Efficient Transformer Quantization
- Low-Rank Quantization-Aware Training for LLMs
- Recursive Generalization Transformer for Image Super-Resolution
- MambaIRv2: Attentive State Space Restoration
- AIM 2020 Challenge on Learned Image Signal Processing Pipeline
- Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks
- PQK: Model Compression via Pruning, Quantization, and Knowledge Distillation
- MQBench: Towards Reproducible and Deployable Model Quantization Benchmark
- A White Paper on Neural Network Quantization
- Neural Network Quantization with AI Model Efficiency Toolkit (AIMET)
- MobileQuant: Mobile-friendly Quantization for On-device Language Models
- Mixed Precision DNNs: All you need is a good parametrization
- MobileOne: An Improved One millisecond Mobile Backbone
- SparseByteNN: A Novel Mobile Inference Acceleration Framework Based on Fine-Grained Group Sparsity
- An Empirical Study of Low Precision Quantization for TinyML
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs