paper-with-me

Papers

Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report

2021-05-17 · Andrey Ignatov, Radu Timofte, Maurizio Denna, Abdel Younes, Andrew Lek, Mustafa Ayazoglu, Jie Liu, Zongcai Du, Jiaming Guo, Xueyi Zhou, Hao Jia, Youliang Yan, Zexin Zhang, Yixin Chen, Yunbo Peng, Yue Lin, Xindong Zhang, Hui Zeng, Kun Zeng, Peirong Li, Zhihuang Liu, Shiqi Xue, Shengpeng Wang

Image super-resolution is one of the most popular computer vision problems with many important applications to mobile devices. While many solutions have been proposed for this task, they are usually not optimized even for common smartphone AI hardware, not to mention more constrained smart TV platforms that are often supporting INT8 inference only. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based image super-resolution solutions that can demonstrate a real-time performance on mobile or edge NPUs. For this, the participants were provided with the DIV2K dataset and trained quantized models to do an efficient 3X image upscaling. The runtime of all models was evaluated on the Synaptics VS680 Smart Home board with a dedicated NPU capable of accelerating quantized neural networks. The proposed solutions are fully compatible with all major mobile AI accelerators and are capable of reconstructing Full HD images under 40-60 ms while achieving high fidelity results. A detailed description of all models developed in the challenge is provided in this paper.

📄 PDF Abstract BibTeX arXiv:2105.07825

Code (1)

NJU-Jet/SR_Mobile_Quantization tf

Tasks

Image Super-ResolutionSuper-Resolution

Similar Papers 제목 키워드 기반

Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report

2022-11-07 · Andrey Ignatov, Radu Timofte, Maurizio Denna, Abdel Younes 외

Image super-resolution is a common task on mobile and IoT devices, where one often needs to upscale and enhance low-resolution images and video frames. While numerous solutions have been proposed for this problem in the …

Image Super-ResolutionSuper-Resolution

Fully Quantized Image Super-Resolution Networks

2020-11-29 · Hu Wang, Peng Chen, Bohan Zhuang, Chunhua Shen

With the rising popularity of intelligent mobile devices, it is of great practical significance to develop accurate, realtime and energy-efficient image Super-Resolution (SR) inference methods. A prevailing method for im…

Image Super-ResolutionQuantizationSuper-Resolution

QArtSR: Quantization via Reverse-Module and Timestep-Retraining in One-Step Diffusion based Image Super-Resolution

2025-03-07 · Libo Zhu, Haotong Qin, Kaicheng Yang, Wenbo Li 외

One-step diffusion-based image super-resolution (OSDSR) models are showing increasingly superior performance nowadays. However, although their denoising steps are reduced to one and they can be quantized to 8-bit to redu…

DenoisingImage Super-ResolutionQuantizationSuper-Resolution

XCAT -- Lightweight Quantized Single Image Super-Resolution using Heterogeneous Group Convolutions and Cross Concatenation

2022-08-31 · Mustafa Ayazoglu, Bahri Batuhan Bilecen

We propose a lightweight, single image super-resolution network for mobile devices, named XCAT. XCAT introduces Heterogeneous Group Convolution Blocks with Cross Concatenations (HXBlock). The heterogeneous split of the i…

Data AugmentationGPUImage Super-ResolutionQuantization+1

Learning Data-Driven Vector-Quantized Degradation Model for Animation Video Super-Resolution

2023-03-17 · ICCV 2023 1 · Zixi Tuo, Huan Yang, Jianlong Fu, Yujie Dun 외

Existing real-world video super-resolution (VSR) methods focus on designing a general degradation pipeline for open-domain videos while ignoring data intrinsic characteristics which strongly limit their performance when …

Super-ResolutionvalidVideo Super-Resolution