Pureformer: Transformer-Based Image Denoising
Gautam, Arnim Pawar, Aditi| Joshi, Aishwarya Tazi, Satyanarayan Narayan Chaudhary, Sachin Dudhane, Akshay A. Vipparthi, Santosh Kumar Murala, Subrahmanyam
Gautam, Arnim
Pawar, Aditi|
Joshi, Aishwarya
Tazi, Satyanarayan Narayan
Chaudhary, Sachin
Dudhane, Akshay A.
Vipparthi, Santosh Kumar
Murala, Subrahmanyam
Supervisor
Department
Computer Vision
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Image denoising is a crucial task in computer vision with applications in real-world smartphones image processing, remote sensing, and photography. Traditional convolution neural networks (CNNs) often struggle to reduce noise while preserving fine details due to their limited receptive fields. Transformer-based approaches, such as Restormer, improve long-range feature modeling, while PromptIR enhances local feature refinement. However, existing methods still face challenges in effectively integrating multi-scale features for robust noise reduction. We propose Pureformer, a Transformer-based encoder-decoder architecture specifically designed for image de-noising. The model employs a four-level encoder-decoder structure, where each stage utilizes Multi-Dconv Head Transposed Attention (MDTA) and Gated-Dconv Feed-Forward Network (GDFN) to extract and refine multi-scale features. We proposed a feature enhancer block in the latent space expands the receptive field using a spatial filter bank, improving feature fusion and texture restoration. Skip connections between the encoder and decoder help retain spatial information, ensuring high-fidelity reconstruction. Pureformer is evaluated on the NTIRE 2025 Image Denoising Challenge dataset, achieving a test PSNR of 29.64 dB and SSIM of 0.8601. We also validated our Pureformer on existing benchmark datasets BSD68 and Urban100 datasets. The results demonstrate that Pureformer surpasses existing methods in both noise reduction and detail preservation, making it a strong choice for real-world image denoising. Access our codes and models from https://github.com/Chapstick53/NTIRE2025_cipher_vision.
Co-author(s)
Citation
A. Gautam et al., "Pureformer: Transformer-Based Image Denoising," in 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Nashville, TN, USA, 2025, pp. 1-9, doi: 10.1109/CVPRW67362.2025.00133.
Source
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Conference
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025
Keywords
Tilter bank, Tmage denoising, Transformer
Subjects
Source
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025
Publisher
IEEE