DiCoNAT: Compact Two-Stage Single-Image Motion Deblurring with Rotated-View Feature Fusion and Decoder-Side Dilated Neighborhood Attention

Single-image motion deblurring restores detail degraded by camera or object motion. We present the Directional Convolutional Neighborhood Attention Transformer (DiCoNAT), a two-stage residual restoration network. Within each stage, native and 90° rotated views share one encoder–decoder mapping. Inverse-aligned bottleneck features are added before a decoder with dilated neighborhood attention predicts image updates. The stages have identical topology and independent parameters. Trained on GoPro, DiCoNAT achieves 32.86 dB peak signal-to-noise ratio (PSNR) and 0.9603 structural similarity (SSIM) on GoPro, and 30.66 dB PSNR on HIDE without further training. The network contains 7.5 million trainable parameters. With 3000 training epochs, the one-, two-, and three-stage configurations achieve 32.09, 32.86, and 32.25 dB PSNR, respectively. The ResBlock-encoder/DiNAT-decoder allocation achieves 32.86 dB, compared with 31.61 dB for the reversed allocation. Additional controls assess rotation angle, bottleneck fusion, frequency-loss weight, dilation, and the number of attention heads. On restored GoPro images, YOLOv8-nano class-averaged mAP@50 increases from 54.4 for blurred inputs to 63.8. In a 35-participant study covering 30 scenes, DiCoNAT receives the highest mean perceptual rating among the evaluated methods, at 3.18.

Authors

Institutions

Publication Details

Journal
Electronics
Published
2026-11-17
DOI
https://doi.org/10.3390/electronics15225346
Primary Topic
Advanced Image Processing Techniques
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

DiCoNAT: Compact Two-Stage Single-Image Motion Deblurring with Rotated-View Feature Fusion and Decoder-Side Dilated Neighborhood Attention

Minyoung Lee, Ho-Sub Lee
1 links
Electronics
Advanced Image Processing Techniques
article

DiCoNAT: Compact Two-Stage Single-Image Motion Deblurring with Rotated-View Feature Fusion and Decoder-Side Dilated Neighborhood Attention

Minyoung Lee, Ho-Sub Lee
article en

Abstract

Single-image motion deblurring restores detail degraded by camera or object motion. We present the Directional Convolutional Neighborhood Attention Transformer (DiCoNAT), a two-stage residual restoration network. Within each stage, native and 90° rotated views share one encoder–decoder mapping. Inverse-aligned bottleneck features are added before a decoder with dilated neighborhood attention predicts image updates. The stages have identical topology and independent parameters. Trained on GoPro, DiCoNAT achieves 32.86 dB peak signal-to-noise ratio (PSNR) and 0.9603 structural similarity (SSIM) on GoPro, and 30.66 dB PSNR on HIDE without further training. The network contains 7.5 million trainable parameters. With 3000 training epochs, the one-, two-, and three-stage configurations achieve 32.09, 32.86, and 32.25 dB PSNR, respectively. The ResBlock-encoder/DiNAT-decoder allocation achieves 32.86 dB, compared with 31.61 dB for the reversed allocation. Additional controls assess rotation angle, bottleneck fusion, frequency-loss weight, dilation, and the number of attention heads. On restored GoPro images, YOLOv8-nano class-averaged mAP@50 increases from 54.4 for blurred inputs to 63.8. In a 35-participant study covering 30 scenes, DiCoNAT receives the highest mean perceptual rating among the evaluated methods, at 3.18.

ElectronicsVol. 15(22)
Kumoh National Institute of Technology (KR)
National Research Foundation of Korea
Advanced Image Processing Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon