MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting

• URL: http://arxiv.org/abs/2203.06304v1
• Date: Sat, 12 Mar 2022 01:32:39 GMT
• Title: MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting
• Authors: Xiaoguang Li and Qing Guo and Di Lin and Ping Li and Wei Feng and Song Wang
• Abstract summary: We study the advantages and challenges of image-level predictive filtering for image inpainting. We propose a novel filtering technique, i.e., Multilevel Interactive Siamese Filtering (MISF), which contains two branches: kernel prediction branch (KPB) and semantic & image filtering branch (SIFB) Our method outperforms state-of-the-art baselines on four metrics, i.e., L1, PSNR, SSIM, and LPIPS.
• Score: 35.79101039727397
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although achieving significant progress, existing deep generative inpainting methods are far from real-world applications due to the low generalization across different scenes. As a result, the generated images usually contain artifacts or the filled pixels differ greatly from the ground truth. Image-level predictive filtering is a widely used image restoration technique, predicting suitable kernels adaptively according to different input scenes. Inspired by this inherent advantage, we explore the possibility of addressing image inpainting as a filtering task. To this end, we first study the advantages and challenges of image-level predictive filtering for image inpainting: the method can preserve local structures and avoid artifacts but fails to fill large missing areas. Then, we propose semantic filtering by conducting filtering on the deep feature level, which fills the missing semantic information but fails to recover the details. To address the issues while adopting the respective advantages, we propose a novel filtering technique, i.e., Multilevel Interactive Siamese Filtering (MISF), which contains two branches: kernel prediction branch (KPB) and semantic & image filtering branch (SIFB). These two branches are interactively linked: SIFB provides multi-level features for KPB while KPB predicts dynamic kernels for SIFB. As a result, the final method takes the advantage of effective semantic & image-level filling for high-fidelity inpainting. We validate our method on three challenging datasets, i.e., Dunhuang, Places2, and CelebA. Our method outperforms state-of-the-art baselines on four metrics, i.e., L1, PSNR, SSIM, and LPIPS. Please try the released code and model at https://github.com/tsingqguo/misf.

Related papers

• Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach [104.2588068730834]
  This paper pushes the technical frontier of image outpainting in two directions that have not been resolved in literature. We develop a method that does not depend on a pre-trained backbone network. We evaluate the proposed approach (called PQDiff) on public benchmarks, demonstrating its superior performance over state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-01-28T13:00:38Z)
• Dual Structure-Aware Image Filterings for Semi-supervised Medical Image Segmentation [11.663088388838073]
  We propose novel dual structure-aware image filterings (DSAIF) as the image-level variations for semi-supervised medical image segmentation. Motivated by connected filtering that simplifies image via filtering in structure-aware tree-based image representation, we resort to the dual contrast invariant Max-tree and Min-tree representation. Applying the proposed DSAIF to mutually supervised networks decreases the consensus of their erroneous predictions on unlabeled images.
  arXiv  Detail & Related papers  (2023-12-12T13:44:53Z)
• Improving Human-Object Interaction Detection via Virtual Image Learning [68.56682347374422]
  Human-Object Interaction (HOI) detection aims to understand the interactions between humans and objects. In this paper, we propose to alleviate the impact of such an unbalanced distribution via Virtual Image Leaning (VIL) A novel label-to-image approach, Multiple Steps Image Creation (MUSIC), is proposed to create a high-quality dataset that has a consistent distribution with real images.
  arXiv  Detail & Related papers  (2023-08-04T10:28:48Z)
• Deep Neural Networks Fused with Textures for Image Classification [20.58839604333332]
  Fine-grained image classification is a challenging task in computer vision. We propose a fusion approach to address FGIC by combining global texture with local patch-based information. Our method has attained better classification accuracy over existing methods with notable margins.
  arXiv  Detail & Related papers  (2023-08-03T15:21:08Z)
• Image Completion via Dual-path Cooperative Filtering [17.62197747945094]
  We propose a predictive filtering method for restoring images based on the input scene. Deep feature-level semantic filtering is introduced to fill in missing information. Experiments on three challenging image completion datasets show that our proposed DCF outperforms state-of-art methods.
  arXiv  Detail & Related papers  (2023-04-30T03:54:53Z)
• High-fidelity Pseudo-labels for Boosting Weakly-Supervised Segmentation [17.804090651425955]
  Image-level weakly-supervised segmentation (WSSS) reduces the usually vast data annotation cost by surrogate segmentation masks during training. Our work is based on two techniques for improving CAMs; importance sampling, which is a substitute for GAP, and the feature similarity loss. We reformulate both techniques based on binomial posteriors of multiple independent binary problems. This has two benefits; their performance is improved and they become more general, resulting in an add-on method that can boost virtually any WSSS method.
  arXiv  Detail & Related papers  (2023-04-05T17:43:57Z)
• Adaptive Local Implicit Image Function for Arbitrary-scale Super-resolution [61.95533972380704]
  Local implicit image function (LIIF) denotes images as a continuous function where pixel values are expansion by using the corresponding coordinates as inputs. LIIF can be adopted for arbitrary-scale image super-resolution tasks, resulting in a single effective and efficient model for various up-scaling factors. We propose a novel adaptive local image function (A-LIIF) to alleviate this problem.
  arXiv  Detail & Related papers  (2022-08-07T11:23:23Z)
• Fully Context-Aware Image Inpainting with a Learned Semantic Pyramid [102.24539566851809]
  Restoring reasonable and realistic content for arbitrary missing regions in images is an important yet challenging task. Recent image inpainting models have made significant progress in generating vivid visual details, but they can still lead to texture blurring or structural distortions. We propose the Semantic Pyramid Network (SPN) motivated by the idea that learning multi-scale semantic priors can greatly benefit the recovery of locally missing content in images.
  arXiv  Detail & Related papers  (2021-12-08T04:33:33Z)
• JPGNet: Joint Predictive Filtering and Generative Network for Image Inpainting [21.936689731138213]
  Image inpainting aims to restore the missing regions and make the recovery results identical to the originally complete image. Existing works usually regard it as a pure generation problem and employ cutting-edge generative techniques to address it. In this paper, we formulate image inpainting as a mix of two problems, i.e., predictive filtering and deep generation.
  arXiv  Detail & Related papers  (2021-07-09T07:49:52Z)
• The Power of Triply Complementary Priors for Image Compressive Sensing [89.14144796591685]
  We propose a joint low-rank deep (LRD) image model, which contains a pair of complementaryly trip priors. We then propose a novel hybrid plug-and-play framework based on the LRD model for image CS. To make the optimization tractable, a simple yet effective algorithm is proposed to solve the proposed H-based image CS problem.
  arXiv  Detail & Related papers  (2020-05-16T08:17:44Z)

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.