Reblurring-Guided Single Image Defocus Deblurring: A Learning Framework with Misaligned Training Pairs

• URL: http://arxiv.org/abs/2409.17792v2
• Date: Thu, 26 Jun 2025 22:05:39 GMT
• Title: Reblurring-Guided Single Image Defocus Deblurring: A Learning Framework with Misaligned Training Pairs
• Authors: Dongwei Ren, Xinya Shu, Yu Li, Xiaohe Wu, Jin Li, Wangmeng Zuo,
• Abstract summary: We introduce a reblurring-guided learning framework for single image defocus deblurring.<n>Our reblurring module ensures spatial consistency between the deblurred image, the reblurred image and the input blurry image.<n> spatially variant blur can be derived from the reblurring module, and serve as pseudo supervision for defocus blur map during training.
• Score: 65.25002116216771
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: For single image defocus deblurring, acquiring well-aligned training pairs (or training triplets), i.e., a defocus blurry image, an all-in-focus sharp image (and a defocus blur map), is a challenging task for developing effective deblurring models. Existing image defocus deblurring methods typically rely on training data collected by specialized imaging equipment, with the assumption that these pairs or triplets are perfectly aligned. However, in practical scenarios involving the collection of real-world data, direct acquisition of training triplets is infeasible, and training pairs inevitably encounter spatial misalignment issues. In this work, we introduce a reblurring-guided learning framework for single image defocus deblurring, enabling the learning of a deblurring network even with misaligned training pairs. By reconstructing spatially variant isotropic blur kernels, our reblurring module ensures spatial consistency between the deblurred image, the reblurred image and the input blurry image, thereby addressing the misalignment issue while effectively extracting sharp textures from the all-in-focus sharp image. Moreover, spatially variant blur can be derived from the reblurring module, and serve as pseudo supervision for defocus blur map during training, interestingly transforming training pairs into training triplets. To leverage this pseudo supervision, we propose a lightweight defocus blur estimator coupled with a fusion block, which enhances deblurring performance through seamless integration with state-of-the-art deblurring networks. Additionally, we have collected a new dataset for single image defocus deblurring (SDD) with typical misalignments, which not only validates our proposed method but also serves as a benchmark for future research.

Related papers

• DiffUHaul: A Training-Free Method for Object Dragging in Images [78.93531472479202]
  We propose a training-free method, dubbed DiffUHaul, for the object dragging task. We first apply attention masking in each denoising step to make the generation more disentangled across different objects. In the early denoising steps, we interpolate the attention features between source and target images to smoothly fuse new layouts with the original appearance.
  arXiv  Detail & Related papers  (2024-06-03T17:59:53Z)
• Learning Single Image Defocus Deblurring with Misaligned Training Pairs [80.13320797431487]
  We propose a joint deblurring and reblurring learning framework for single image defocus deblurring. Our framework can be applied to boost defocus deblurring networks in terms of both quantitative metrics and visual quality.
  arXiv  Detail & Related papers  (2022-11-26T07:36:33Z)
• Learnable Blur Kernel for Single-Image Defocus Deblurring in the Wild [9.246199263116067]
  We propose a novel defocus deblurring method that uses the guidance of the defocus map to implement image deblurring. The proposed method consists of a learnable blur kernel to estimate the defocus map, and a single-image defocus deblurring generative adversarial network (DefocusGAN) for the first time.
  arXiv  Detail & Related papers  (2022-11-25T10:47:19Z)
• Single-image Defocus Deblurring by Integration of Defocus Map Prediction Tracing the Inverse Problem Computation [25.438654895178686]
  We propose a simple but effective network with spatial modulation based on the defocus map. Experimental results show that our method can achieve better quantitative and qualitative evaluation performance than the existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-07-07T02:15:33Z)
• SVBR-NET: A Non-Blind Spatially Varying Defocus Blur Removal Network [2.4975981795360847]
  We propose a non-blind approach for image deblurring that can deal with spatially-varying kernels. We introduce two encoder-decoder sub-networks that are fed with the blurry image and the estimated blur map. The network is trained with synthetically blur kernels that are augmented to emulate blur maps produced by existing blur estimation methods.
  arXiv  Detail & Related papers  (2022-06-26T17:21:12Z)
• Learning to Deblur using Light Field Generated and Real Defocus Images [4.926805108788465]
  Defocus deblurring is a challenging task due to the spatially varying nature of defocus blur. We propose a novel deep defocus deblurring network that leverages the strength and overcomes the shortcoming of light fields.
  arXiv  Detail & Related papers  (2022-04-01T11:35:51Z)
• Pose Adaptive Dual Mixup for Few-Shot Single-View 3D Reconstruction [35.30827580375749]
  We present a pose adaptive few-shot learning procedure and a two-stage data regularization, termed PADMix, for single-image 3D reconstruction. PADMix significantly outperforms previous literature on few-shot settings over the ShapeNet dataset and sets new benchmarks on the more challenging real-world Pix3D dataset.
  arXiv  Detail & Related papers  (2021-12-23T12:22:08Z)
• Defocus Map Estimation and Deblurring from a Single Dual-Pixel Image [54.10957300181677]
  We present a method that takes as input a single dual-pixel image, and simultaneously estimates the image's defocus map. Our approach improves upon prior works for both defocus map estimation and blur removal, despite being entirely unsupervised.
  arXiv  Detail & Related papers  (2021-10-12T00:09:07Z)
• Learning Contrastive Representation for Semantic Correspondence [150.29135856909477]
  We propose a multi-level contrastive learning approach for semantic matching. We show that image-level contrastive learning is a key component to encourage the convolutional features to find correspondence between similar objects.
  arXiv  Detail & Related papers  (2021-09-22T18:34:14Z)
• Single image deep defocus estimation and its applications [82.93345261434943]
  We train a deep neural network to classify image patches into one of the 20 levels of blurriness. The trained model is used to determine the patch blurriness which is then refined by applying an iterative weighted guided filter. The result is a defocus map that carries the information of the degree of blurriness for each pixel.
  arXiv  Detail & Related papers  (2021-07-30T06:18:16Z)
• Rectifying the Shortcut Learning of Background: Shared Object Concentration for Few-Shot Image Recognition [101.59989523028264]
  Few-Shot image classification aims to utilize pretrained knowledge learned from a large-scale dataset to tackle a series of downstream classification tasks. We propose COSOC, a novel Few-Shot Learning framework, to automatically figure out foreground objects at both pretraining and evaluation stage.
  arXiv  Detail & Related papers  (2021-07-16T07:46:41Z)
• Rapid Whole Slide Imaging via Learning-based Two-shot Virtual Autofocusing [57.90239401665367]
  Whole slide imaging (WSI) is an emerging technology for digital pathology. We propose the concept of textitvirtual autofocusing, which does not rely on mechanical adjustment to conduct refocusing.
  arXiv  Detail & Related papers  (2020-03-14T13:40:33Z)
• Un-Mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning [108.999497144296]
  Recently advanced unsupervised learning approaches use the siamese-like framework to compare two "views" from the same image for learning representations. This work aims to involve the distance concept on label space in the unsupervised learning and let the model be aware of the soft degree of similarity between positive or negative pairs. Despite its conceptual simplicity, we show empirically that with the solution -- Unsupervised image mixtures (Un-Mix), we can learn subtler, more robust and generalized representations from the transformed input and corresponding new label space.
  arXiv  Detail & Related papers  (2020-03-11T17:59:04Z)

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.