eISSN: 2574-8092
Submit manuscript...
Research Article Volume 11 Issue 2
DiNAT-IR: Exploring dilated neighborhood attention for high-quality image restoration
Hanzhou Liu, Binghan Li, Chengkai Liu, Mi Lu
Received: August 23, 2025 | Published: September 23, 2025
Citation: Lu M, Liu H, Li B, et al. DiNAT-IR: Exploring dilated neighborhood attention for high-quality image restoration. Int Rob Auto J. 2025;11(2):50-58. DOI: 10.15406/iratj.2025.11.00301
Abstract
Transformers, with their self-attention mechanisms for modeling long-range dependencies, have become a dominant paradigm in image restoration tasks. However, the high computational cost of self-attention limits scalability to high-resolution images, making efficiency-quality trade-offs a key research focus. To address this, Restormer employs channel-wise self-attention, which computes attention across channels instead of spatial dimensions. While effective, this approach may overlook localized artifacts that are crucial for high-quality image restoration. To bridge this gap, we explore Dilated Neighborhood Attention (DiNA) as a promising alternative, inspired by its success in high-level vision tasks. DiNA balances global context and local precision by integrating sliding-window attention with mixed dilation factors, effectively expanding the receptive field without excessive overhead. However, our preliminary experiments indicate that directly applying this global-local design to the classic deblurring task hinders accurate visual restoration, primarily due to the constrained global context understanding within local attention. To address this, we introduce a channel-aware module that complements local attention, effectively integrating global context without sacrificing pixel-level precision. The proposed DiNAT-IR, a Transformer-based architecture specifically designed for image restoration, achieves competitive results across multiple benchmarks, offering a highquality solution for diverse low-level computer vision problems. Our codes will be released upon acceptance.
Keywords: low-level computer vision, image restoration, transformer, neural networks
©2025 Lu, et al. This is an open access article distributed under the terms of the, which permits unrestricted use, distribution, and build upon your work non-commercially.