mlsanityData to 14 Oct 2026

Improving Detail in Pluralistic Image Inpainting with Feature Dequantization

arXiv 2412.01046 ↗First posted 2 Dec 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Pluralistic Image Inpainting (PII) offers multiple plausible solutions for restoring missing parts of images and has been successfully applied to various applications including image editing and object removal. Recently, VQGAN-based methods have been proposed and have shown that they significantly improve the structural integrity in the generated images. Nevertheless, the state-of-the-art VQGAN-based model PUT faces a critical challenge: degradation of detail quality in output images due to feature quantization. Feature quantization restricts the latent space and causes information loss, which negatively affects the detail quality essential for image inpainting. To tackle the problem, we propose the FDM (Feature Dequantization Module) specifically designed to restore the detail quality of images by compensating for the information loss. Furthermore, we develop an efficient training method for FDM which drastically reduces training costs. We empirically demonstrate that our method significantly enhances the detail quality of the generated images with negligible training and inference overheads.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 38 references that are in the map. First posted on arXiv 2 Dec 2024.

Builds on

25 of 38 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  5. 2017Neural Discrete Representation Learningcited by 4,712
  6. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  7. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  8. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  9. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  10. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 738
  11. 2022Autoregressive Image Generation using Residual Quantizationcited by 722
  12. 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
13 more
  1. 2022MAT: Mask-Aware Transformer for Large Hole Image Inpaintingcited by 218
  2. 2016EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesiscited by 178
  3. 2019Pluralistic Image Completioncited by 162
  4. 2021High-Fidelity Pluralistic Image Completion with Transformerscited by 134
  5. 2019SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Colorcited by 106
  6. 2021PD-GAN: Probabilistic Diverse GAN for Image Inpaintingcited by 80
  7. 2023Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantizationcited by 60
  8. 2022Reduce Information Loss in Transformers for Pluralistic Image Inpaintingcited by 36
  9. 2023Efficient-VQGAN: Towards High-Resolution Image Generation with Efficient Vision Transformerscited by 33
  10. 2022Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformercited by 30
  11. 2023Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generationcited by 28
  12. 2018Adversarial Scene Editing: Automatic Object Removal from Weak Supervisioncited by 27
  13. 2023Catch Missing Details: Image Reconstruction with Frequency Augmented Variational Autoencodercited by 18

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE
  2. 2023Designing a Better Asymmetric VQGAN for StableDiffusion
  3. 2023Inst-Inpaint: Instructing to Remove Objects with Diffusion Models
  4. 2023Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency
  5. 2024BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion
  6. 2025Towards Seamless Borders: A Method for Mitigating Inconsistencies in Image Inpainting and Outpainting
  7. 2023Magicremover: Tuning-free Text-guided Image inpainting with Diffusion Models
  8. 2025PixPerfect: Seamless Latent Diffusion Local Editing with Discriminative Pixel-Space Refinement