DeblurDiNAT: A Generalizable Transformer for Perceptual Image Deblurring
- URL: http://arxiv.org/abs/2403.13163v4
- Date: Mon, 04 Nov 2024 22:45:50 GMT
- Title: DeblurDiNAT: A Generalizable Transformer for Perceptual Image Deblurring
- Authors: Hanzhou Liu, Binghan Li, Chengkai Liu, Mi Lu,
- Abstract summary: DeblurDiNAT is a generalizable and efficient encoder-decoder Transformer which restores clean images visually close to the ground truth.
We present a linear feed-forward network and a non-linear dual-stage feature fusion module for faster feature propagation across the network.
- Score: 1.5124439914522694
- License:
- Abstract: Although prior state-of-the-art (SOTA) deblurring networks achieve high metric scores on synthetic datasets, there are two challenges which prevent them from perceptual image deblurring. First, a deblurring model overtrained on synthetic datasets may collapse in a broad range of unseen real-world scenarios. Second, the conventional metrics PSNR and SSIM may not correctly reflect the perceptual quality observed by human eyes. To this end, we propose DeblurDiNAT, a generalizable and efficient encoder-decoder Transformer which restores clean images visually close to the ground truth. We adopt an alternating dilation factor structure to capture local and global blur patterns. We propose a local cross-channel learner to assist self-attention layers to learn short-range cross-channel relationships. In addition, we present a linear feed-forward network and a non-linear dual-stage feature fusion module for faster feature propagation across the network. Compared to nearest competitors, our model demonstrates the strongest generalization ability and achieves the best perceptual quality on mainstream image deblurring datasets with 3%-68% fewer parameters.
Related papers
- Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers [59.0181939916084]
Traditional 3D networks mainly focus on local geometric details and ignore the topological structure between local geometries.
We propose a novel Priors Distillation (RPD) method to extract priors from the well-trained transformers on massive images.
Experiments on the PointDA-10 and the Sim-to-Real datasets verify that the proposed method consistently achieves the state-of-the-art performance of UDA for point cloud classification.
arXiv Detail & Related papers (2024-07-26T06:29:09Z) - Affine-based Deformable Attention and Selective Fusion for Semi-dense Matching [30.272791354494373]
We introduce affine-based local attention to model cross-view deformations.
We also present selective fusion to merge local and global messages from cross attention.
arXiv Detail & Related papers (2024-05-22T17:57:37Z) - Distance Weighted Trans Network for Image Completion [52.318730994423106]
We propose a new architecture that relies on Distance-based Weighted Transformer (DWT) to better understand the relationships between an image's components.
CNNs are used to augment the local texture information of coarse priors.
DWT blocks are used to recover certain coarse textures and coherent visual structures.
arXiv Detail & Related papers (2023-10-11T12:46:11Z) - Multi-scale Alternated Attention Transformer for Generalized Stereo
Matching [7.493797166406228]
We present a simple but highly effective network called Alternated Attention U-shaped Transformer (AAUformer) to balance the impact of epipolar line in dual and single view.
Compared to other models, our model has several main designs.
We performed a series of both comparative studies and ablation studies on several mainstream stereo matching datasets.
arXiv Detail & Related papers (2023-08-06T08:22:39Z) - Cross-Spatial Pixel Integration and Cross-Stage Feature Fusion Based
Transformer Network for Remote Sensing Image Super-Resolution [13.894645293832044]
Transformer-based models have shown competitive performance in remote sensing image super-resolution (RSISR)
We propose a novel transformer architecture called Cross-Spatial Pixel Integration and Cross-Stage Feature Fusion Based Transformer Network (SPIFFNet) for RSISR.
Our proposed model effectively enhances global cognition and understanding of the entire image, facilitating efficient integration of features cross-stages.
arXiv Detail & Related papers (2023-07-06T13:19:06Z) - Local-Global Transformer Enhanced Unfolding Network for Pan-sharpening [13.593522290577512]
Pan-sharpening aims to increase the spatial resolution of the low-resolution multispectral (LrMS) image with the guidance of the corresponding panchromatic (PAN) image.
Although deep learning (DL)-based pan-sharpening methods have achieved promising performance, most of them have a two-fold deficiency.
arXiv Detail & Related papers (2023-04-28T03:34:36Z) - Global-to-Local Modeling for Video-based 3D Human Pose and Shape
Estimation [53.04781510348416]
Video-based 3D human pose and shape estimations are evaluated by intra-frame accuracy and inter-frame smoothness.
We propose to structurally decouple the modeling of long-term and short-term correlations in an end-to-end framework, Global-to-Local Transformer (GLoT)
Our GLoT surpasses previous state-of-the-art methods with the lowest model parameters on popular benchmarks, i.e., 3DPW, MPI-INF-3DHP, and Human3.6M.
arXiv Detail & Related papers (2023-03-26T14:57:49Z) - Hierarchical Cross-modal Transformer for RGB-D Salient Object Detection [6.385624548310884]
We propose the Hierarchical Cross-modal Transformer (HCT), a new multi-modal transformer, to tackle this problem.
Unlike previous multi-modal transformers that directly connecting all patches from two modalities, we explore the cross-modal complementarity hierarchically.
We present a Feature Pyramid module for Transformer (FPT) to boost informative cross-scale integration as well as a consistency-complementarity module to disentangle the multi-modal integration path.
arXiv Detail & Related papers (2023-02-16T03:23:23Z) - Interpolation-based Correlation Reduction Network for Semi-Supervised
Graph Learning [49.94816548023729]
We propose a novel graph contrastive learning method, termed Interpolation-based Correlation Reduction Network (ICRN)
In our method, we improve the discriminative capability of the latent feature by enlarging the margin of decision boundaries.
By combining the two settings, we extract rich supervision information from both the abundant unlabeled nodes and the rare yet valuable labeled nodes for discnative representation learning.
arXiv Detail & Related papers (2022-06-06T14:26:34Z) - Activating More Pixels in Image Super-Resolution Transformer [53.87533738125943]
Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution.
We propose a novel Hybrid Attention Transformer (HAT) to activate more input pixels for better reconstruction.
Our overall method significantly outperforms the state-of-the-art methods by more than 1dB.
arXiv Detail & Related papers (2022-05-09T17:36:58Z) - Semantic Correspondence with Transformers [68.37049687360705]
We propose Cost Aggregation with Transformers (CATs) to find dense correspondences between semantically similar images.
We include appearance affinity modelling to disambiguate the initial correlation maps and multi-level aggregation.
We conduct experiments to demonstrate the effectiveness of the proposed model over the latest methods and provide extensive ablation studies.
arXiv Detail & Related papers (2021-06-04T14:39:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.