paper-with-me

홈 › Papers

Mobile-friendly Image de-noising: Hardware Conscious Optimization for Edge Application

2026-01-16 · Srinivas Miriyala, Sowmya Vajrala, Hitesh Kumar, Sravanth Kodavanti, Vikram Rajendiran arxiv

Image enhancement is a critical task in computer vision and photography that is often entangled with noise. This renders the traditional Image Signal Processing (ISP) ineffective compared to the advances in deep learning. However, the success of such methods is increasingly associated with the ease of their deployment on edge devices, such as smartphones. This work presents a novel mobile-friendly network for image de-noising obtained with Entropy-Regularized differentiable Neural Architecture Search (NAS) on a hardware-aware search space for a U-Net architecture, which is first-of-its-kind. The designed model has 12% less parameters, with ~2-fold improvement in ondevice latency and 1.5-fold improvement in the memory footprint for a 0.7% drop in PSNR, when deployed and profiled on Samsung Galaxy S24 Ultra. Compared to the SOTA Swin-Transformer for Image Restoration, the proposed network had competitive accuracy with ~18-fold reduction in GMACs. Further, the network was tested successfully for Gaussian de-noising with 3 intensities on 4 benchmarks and real-world de-noising on 1 benchmark demonstrating its generalization ability.

📄 PDF Abstract BibTeX arXiv:2601.11684

Code (0)

등록된 구현이 없습니다.

Tasks

Neural Architecture SearchImage EnhancementImage Restoration

Similar Papers 제목 키워드 기반

Lightweight network towards real-time image denoising on mobile devices

2022-11-09 · Zhuoqun Liu, Meiguang Jin, Ying Chen, Huaida Liu 외

Deep convolutional neural networks have achieved great progress in image denoising tasks. However, their complicated architectures and heavy computational cost hinder their deployments on mobile devices. Some recent effo…

DenoisingImage Denoising

A Closer Look at Hardware-Friendly Weight Quantization

2022-10-07 · Sungmin Bae, Piotr Zielinski, Satrajit Chatterjee

Quantizing a Deep Neural Network (DNN) model to be used on a custom accelerator with efficient fixed-point hardware implementations, requires satisfying many stringent hardware-friendly quantization constraints to train …

Quantization

Low Power Inference for On-Device Visual Recognition with a Quantization-Friendly Solution

2019-03-12 · Chen Feng, Tao Sheng, Zhiyu Liang, Shaojie Zhuo 외

The IEEE Low-Power Image Recognition Challenge (LPIRC) is an annual competition started in 2015 that encourages joint hardware and software solutions for computer vision systems with low latency and power. Track 1 of the…

CPUQuantization

Practical Deep Raw Image Denoising on Mobile Devices

2020-10-14 · ECCV 2020 8 · Yuzhi Wang, Haibin Huang, Qin Xu, Jiaming Liu 외

Deep learning-based image denoising approaches have been extensively studied in recent years, prevailing in many public benchmark datasets. However, the stat-of-the-art networks are computationally too expensive to be di…

DenoisingEfficient Neural NetworkImage Denoising

Real-World Mobile Image Denoising Dataset with Efficient Baselines

2024-01-01 · CVPR 2024 1 · Roman Flepp, Andrey Ignatov, Radu Timofte, Luc van Gool

The recently increased role of mobile photography has raised the standards of on-device photo processing tremendously. Despite the latest advancements in camera hardware the mobile camera sensor area cannot be increa…

DenoisingImage Denoising