Panoramic Image Inpainting With Gated Convolution And Contextual Reconstruction Loss

• URL: http://arxiv.org/abs/2402.02936v1
• Date: Mon, 5 Feb 2024 11:58:08 GMT
• Title: Panoramic Image Inpainting With Gated Convolution And Contextual Reconstruction Loss
• Authors: Li Yu, Yanjun Gao, Farhad Pakdaman, Moncef Gabbouj
• Abstract summary: We propose a panoramic image inpainting framework that consists of a Face Generator, a Cube Generator, a side branch, and two discriminators. The proposed method is compared with state-of-the-art (SOTA) methods on SUN360 Street View dataset in terms of PSNR and SSIM.
• Score: 19.659176149635417
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning-based methods have demonstrated encouraging results in tackling the task of panoramic image inpainting. However, it is challenging for existing methods to distinguish valid pixels from invalid pixels and find suitable references for corrupted areas, thus leading to artifacts in the inpainted results. In response to these challenges, we propose a panoramic image inpainting framework that consists of a Face Generator, a Cube Generator, a side branch, and two discriminators. We use the Cubemap Projection (CMP) format as network input. The generator employs gated convolutions to distinguish valid pixels from invalid ones, while a side branch is designed utilizing contextual reconstruction (CR) loss to guide the generators to find the most suitable reference patch for inpainting the missing region. The proposed method is compared with state-of-the-art (SOTA) methods on SUN360 Street View dataset in terms of PSNR and SSIM. Experimental results and ablation study demonstrate that the proposed method outperforms SOTA both quantitatively and qualitatively.

Related papers

• Sketch-guided Image Inpainting with Partial Discrete Diffusion Process [5.005162730122933]
  We introduce a novel partial discrete diffusion process (PDDP) for sketch-guided inpainting. PDDP corrupts the masked regions of the image and reconstructs these masked regions conditioned on hand-drawn sketches. The proposed novel transformer module accepts two inputs -- the image containing the masked region to be inpainted and the query sketch to model the reverse diffusion process.
  arXiv  Detail & Related papers  (2024-04-18T07:07:38Z)
• Image Deblurring using GAN [0.0]
  This project focuses on the application of Generative Adversarial Network (GAN) in image deblurring. The project defines a GAN model inflow and trains it with GoPRO dataset. The network can obtain sharper pixels in image, achieving an average of 29.3 Peak Signal-to-Noise Ratio (PSNR) and 0.72 Structural Similarity Assessment (SSIM)
  arXiv  Detail & Related papers  (2023-12-15T02:43:30Z)
• Inpainting borehole images using Generative Adversarial Networks [0.0]
  We propose a GAN-based approach for gap filling in borehole images created by wireline microresistivity imaging tools. The proposed method utilizes a generator, global discriminator, and local discriminator to inpaint the missing regions of the image.
  arXiv  Detail & Related papers  (2023-01-15T18:15:52Z)
• Cross-View Panorama Image Synthesis [68.35351563852335]
  PanoGAN is a novel adversarial feedback GAN framework named. PanoGAN enables high-quality panorama image generation with more convincing details than state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-03-22T15:59:44Z)
• Inverse Problems Leveraging Pre-trained Contrastive Representations [88.70821497369785]
  We study a new family of inverse problems for recovering representations of corrupted data. We propose a supervised inversion method that uses a contrastive objective to obtain excellent representations for highly corrupted images. Our method outperforms end-to-end baselines even with a fraction of the labeled data in a wide range of forward operators.
  arXiv  Detail & Related papers  (2021-10-14T15:06:30Z)
• FT-TDR: Frequency-guided Transformer and Top-Down Refinement Network for Blind Face Inpainting [77.78305705925376]
  Blind face inpainting refers to the task of reconstructing visual contents without explicitly indicating the corrupted regions in a face image. We propose a novel two-stage blind face inpainting method named Frequency-guided Transformer and Top-Down Refinement Network (FT-TDR) to tackle these challenges.
  arXiv  Detail & Related papers  (2021-08-10T03:12:01Z)
• ReGO: Reference-Guided Outpainting for Scenery Image [82.21559299694555]
  generative adversarial learning has advanced the image outpainting by producing semantic consistent content for the given image. This work investigates a principle way to synthesize texture-rich results by borrowing pixels from its neighbors. To prevent the style of the generated part from being affected by the reference images, a style ranking loss is proposed to augment the ReGO to synthesize style-consistent results.
  arXiv  Detail & Related papers  (2021-06-20T02:34:55Z)
• Image Inpainting with Edge-guided Learnable Bidirectional Attention Maps [85.67745220834718]
  We present an edge-guided learnable bidirectional attention map (Edge-LBAM) for improving image inpainting of irregular holes. Our Edge-LBAM method contains dual procedures,including structure-aware mask-updating guided by predict edges. Extensive experiments show that our Edge-LBAM is effective in generating coherent image structures and preventing color discrepancy and blurriness.
  arXiv  Detail & Related papers  (2021-04-25T07:25:16Z)
• Pixel-wise Dense Detector for Image Inpainting [34.721991959357425]
  Recent GAN-based image inpainting approaches adopt an average strategy to discriminate the generated image and output a scalar. We propose a novel detection-based generative framework for image inpainting, which adopts the min-max strategy in an adversarial process. Experiments on multiple public datasets show the superior performance of the proposed framework.
  arXiv  Detail & Related papers  (2020-11-04T13:45:27Z)
• High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling [122.06593036862611]
  Existing image inpainting methods often produce artifacts when dealing with large holes in real applications. We propose an iterative inpainting method with a feedback mechanism. Experiments show that our method significantly outperforms existing methods in both quantitative and qualitative evaluations.
  arXiv  Detail & Related papers  (2020-05-24T13:23:45Z)
• Pixel-wise Conditioned Generative Adversarial Networks for Image Synthesis and Completion [3.8807073304999355]
  Generative Adversarial Networks (GANs) have proven successful for unsupervised image generation. We investigate the effectiveness of conditioning GANs when very few pixel values are provided. We propose a modelling framework which results in adding an explicit cost term to the GAN objective function to enforce pixel-wise conditioning.
  arXiv  Detail & Related papers  (2020-02-04T13:49:15Z)

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.