PixelHacker: Image Inpainting with Structural and Semantic Consistency

• URL: http://arxiv.org/abs/2504.20438v2
• Date: Wed, 30 Apr 2025 14:37:05 GMT
• Title: PixelHacker: Image Inpainting with Structural and Semantic Consistency
• Authors: Ziyang Xu, Kangsheng Duan, Xiaolei Shen, Zhifeng Ding, Wenyu Liu, Xiaohu Ruan, Xiaoxin Chen, Xinggang Wang,
• Abstract summary: Inpainting is a fundamental research area between image editing and image generation.<n>Recent state-of-the-art (SOTA) methods have explored novel attention mechanisms, lightweight architectures, and context-aware modeling.<n>We design a simple yet effective inpainting paradigm called latent categories guidance, and propose a diffusion-based model named PixelHacker.
• Score: 28.984953143157107
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Image inpainting is a fundamental research area between image editing and image generation. Recent state-of-the-art (SOTA) methods have explored novel attention mechanisms, lightweight architectures, and context-aware modeling, demonstrating impressive performance. However, they often struggle with complex structure (e.g., texture, shape, spatial relations) and semantics (e.g., color consistency, object restoration, and logical correctness), leading to artifacts and inappropriate generation. To address this challenge, we design a simple yet effective inpainting paradigm called latent categories guidance, and further propose a diffusion-based model named PixelHacker. Specifically, we first construct a large dataset containing 14 million image-mask pairs by annotating foreground and background (potential 116 and 21 categories, respectively). Then, we encode potential foreground and background representations separately through two fixed-size embeddings, and intermittently inject these features into the denoising process via linear attention. Finally, by pre-training on our dataset and fine-tuning on open-source benchmarks, we obtain PixelHacker. Extensive experiments show that PixelHacker comprehensively outperforms the SOTA on a wide range of datasets (Places2, CelebA-HQ, and FFHQ) and exhibits remarkable consistency in both structure and semantics. Project page at https://hustvl.github.io/PixelHacker.

Related papers

• T-former: An Efficient Transformer for Image Inpainting [50.43302925662507]
  A class of attention-based network architectures, called transformer, has shown significant performance on natural language processing fields. In this paper, we design a novel attention linearly related to the resolution according to Taylor expansion, and based on this attention, a network called $T$-former is designed for image inpainting. Experiments on several benchmark datasets demonstrate that our proposed method achieves state-of-the-art accuracy while maintaining a relatively low number of parameters and computational complexity.
  arXiv  Detail & Related papers  (2023-05-12T04:10:42Z)
• High-Quality Entity Segmentation [110.55724145851725]
  CropFormer is designed to tackle the intractability of instance-level segmentation on high-resolution images. It improves mask prediction by fusing high-res image crops that provide more fine-grained image details and the full image. With CropFormer, we achieve a significant AP gain of $1.9$ on the challenging entity segmentation task.
  arXiv  Detail & Related papers  (2022-11-10T18:58:22Z)
• Modeling Image Composition for Complex Scene Generation [77.10533862854706]
  We present a method that achieves state-of-the-art results on layout-to-image generation tasks. After compressing RGB images into patch tokens, we propose the Transformer with Focal Attention (TwFA) for exploring dependencies of object-to-object, object-to-patch and patch-to-patch.
  arXiv  Detail & Related papers  (2022-06-02T08:34:25Z)
• 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)
• Boosting Image Outpainting with Semantic Layout Prediction [18.819765707811904]
  We train a GAN to extend regions in semantic segmentation domain instead of image domain. Another GAN model is trained to synthesize real images based on the extended semantic layouts. Our approach can handle semantic clues more easily and hence works better in complex scenarios.
  arXiv  Detail & Related papers  (2021-10-18T13:09:31Z)
• Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization [112.68171734288237]
  We propose a novel framework for discriminative pixel-level tasks using a generative model of both images and labels. We learn a generative adversarial network that captures the joint image-label distribution and is trained efficiently using a large set of unlabeled images. We demonstrate strong in-domain performance compared to several baselines, and are the first to showcase extreme out-of-domain generalization.
  arXiv  Detail & Related papers  (2021-04-12T21:41:25Z)
• Combining Semantic Guidance and Deep Reinforcement Learning For Generating Human Level Paintings [22.889059874754242]
  Generation of stroke-based non-photorealistic imagery is an important problem in the computer vision community. Previous methods have been limited to datasets with little variation in position, scale and saliency of the foreground object. We propose a Semantic Guidance pipeline with 1) a bi-level painting procedure for learning the distinction between foreground and background brush strokes at training time.
  arXiv  Detail & Related papers  (2020-11-25T09:00:04Z)
• Object-Based Image Coding: A Learning-Driven Revisit [30.550019759674477]
  A fundamental issue behind is how to efficiently process the arbitrary-shaped objects at a fine granularity. We have proposed an object segmentation network for image layer decomposition, and parallel convolution-based neural image compression networks to process masked foreground objects and background scene separately. All components are optimized in an end-to-end learning framework to intelligently weigh their contributions for visually pleasant reconstruction.
  arXiv  Detail & Related papers  (2020-03-18T04:00:17Z)
• Very Long Natural Scenery Image Prediction by Outpainting [96.8509015981031]
  Outpainting receives less attention due to two challenges in it. First challenge is how to keep the spatial and content consistency between generated images and original input. Second challenge is how to maintain high quality in generated results.
  arXiv  Detail & Related papers  (2019-12-29T16:29:01Z)

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.