← Back to all news
arXiv Computer Vision By Hanzhou Liu, Binghan Li, Chengkai Liu, Mi Lu

DiNAT-IR: Exploring Dilated Neighborhood Attention for High-Quality Image Restoration

Read the original on arXiv Computer Vision →

DiNAT-IR introduces Dilated Neighborhood Attention (DiNA) to balance global context and local precision in image restoration. By combining sliding-window attention with mixed dilation factors and a channel-aware module, it addresses the limitations of channel-wise self-attention and improves pixel-level accuracy. The resulting Transformer-based architecture delivers competitive performance across multiple benchmarks for low-level vision tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Oct 21

Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear Attention

The paper introduces SANA‑SR, an efficient one‑step diffusion restoration framework for real‑world image super‑resolution. It uses a deep compression autoencoder to reduce latent tokens by a 32× ratio, preserving essential structures and textures, and applies a linear‑attention DiT with LoRA fine‑tuning for linear‑complexity token mixing. Experiments show competitive or superior performance on benchmark datasets, and the pruned model runs in 0.019 s with 407.95 G MACs and 344 M parameters, indicating strong potential for mobile deployment.

By Bingtian Qiao, Yue Shi, Yingjie Zhou, Yong Guo, Guangtao Zhai, Jiezhang Cao
diffusionfine-tuningefficiencybenchmarks
More like this →
arXiv Machine Learning
Aug 26

NAIMA: Semantics Aware RGB Guided Depth Super-Resolution

The paper introduces NAIMA, a guided depth super‑resolution framework that leverages global contextual semantic priors from pretrained vision transformer token embeddings. Its Guided Token Attention (GTA) module uses depth encodings as queries to attend over semantic tokens, with a zero‑initialized gate controlling the influence of semantic evidence. NAIMA achieves competitive in‑distribution performance while delivering superior cross‑dataset generalization without relying on decoded priors or auxiliary objectives.

By Tayyab Nasir, Daochang Liu, Ajmal Mian
llmsragcomputer-visionmultimodalsafety
More like this →