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.
arXiv:2505.16157v3 Announce Type: replace Abstract: Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Tran...
arXiv:2404.06135v4 Announce Type: replace Abstract: The Transformer architecture has achieved remarkable success in natural language processing and high-level vision tasks over the past few years. Ho...
arXiv:2511. 10806v1 Announce Type: cross Abstract: Image deblurring is vital in computer vision, aiming to recover sharp images from blurry ones caused by motion or camera shake.
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.
arXiv:2412.10338v4 Announce Type: replace Abstract: Deep state-space models (SSMs), like recent Mamba architectures, are emerging as a promising alternative to CNN and Transformer networks. Existing...
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.
arXiv:2601. 12507v2 Announce Type: replace-cross Abstract: Low-resolution remote sensing small object detection is limited by both missing visual details and the ambiguity of how details serve detection.
arXiv:2608.03423v2 Announce Type: replace Abstract: Local feature matching is a fundamental component of photogrammetry, enabling accurate image correspondence critical for tasks such as 3D reconstru...
arXiv:2609.16578v1 Announce Type: new Abstract: The spatial support required for image restoration varies across degradation types, image regions, and reconstruction stages. However, most existing me...
Local feature matching is a fundamental component of photogrammetry, enabling accurate image correspondence critical for tasks such as 3D reconstruction, stereo mapping, and visual localization. While recent detector-free matching methods, like LoFTR, have advanced the field, the global features obtained by leveraging the global-range modeling capacity of the unconstrained attention mechanism compromise the model's attention to the salient structures in certain scenarios.
HiLRP introduces a unified attribution framework for Vision Transformers (ViTs) that addresses the challenges posed by diverse architectural designs. By decomposing ViT operations into four basic types—linear maps, bilinear mixing, normalization/gating, and reindexing—HiLRP applies conservation‑satisfying relevance rules, enabling reliable explanations across a wide range of backbones. The method outperforms 14 existing attribution techniques on 10 architectures, maintaining conservation and improving localization accuracy (0.97 Pointing) compared to competitors.
arXiv:2609.24494v1 Announce Type: new Abstract: Accurate monocular depth estimation serves as a core enabler for single camera scene understanding. However, existing self-supervised monocular depth e...