# PixelHacker: Image Inpainting with Structural and Semantic Consistency

arXiv: https://arxiv.org/abs/2504.20438 · HTML: https://mlsanity.com/paper/2504.20438/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 40 references that are in the map.
- First posted on arXiv 29 Apr 2025.

## Builds on (most cited first, 30 of 32)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Gated Linear Attention Transformers with Hardware-Efficient Training](https://mlsanity.com/paper/2312.06635/) (2023)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model](https://mlsanity.com/paper/2212.05034/) (2022)
- [Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting](https://mlsanity.com/paper/2212.06909/) (2022)
- [Large Scale Image Completion via Co-Modulated Generative Adversarial Networks](https://mlsanity.com/paper/2103.10428/) (2021)
- [MAT: Mask-Aware Transformer for Large Hole Image Inpainting](https://mlsanity.com/paper/2203.15270/) (2022)
- [A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting](https://mlsanity.com/paper/2312.03594/) (2023)
- [Alpha-CLIP: A CLIP Model Focusing on Wherever You Want](https://mlsanity.com/paper/2312.03818/) (2023)
- [High-Fidelity Pluralistic Image Completion with Transformers](https://mlsanity.com/paper/2103.14031/) (2021)
- [Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting](https://mlsanity.com/paper/2005.09704/) (2020)
- [Aggregated Contextual Transformations for High-Resolution Image Inpainting](https://mlsanity.com/paper/2104.01431/) (2021)
- [Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding](https://mlsanity.com/paper/2203.00867/) (2022)
- [Image Inpainting by End-to-End Cascaded Refinement with Mask Awareness](https://mlsanity.com/paper/2104.13743/) (2021)

## Built on by (most cited first, 8 of 8)

- [DiffDecompose: Layer-Wise Decomposition of Alpha-Composited Images via Diffusion Transformers](https://mlsanity.com/paper/2505.21541/) (2025)
- [2D Instance Editing in 3D Space](https://mlsanity.com/paper/2507.05819/) (2025)
- [ClickRemoval: An Interactive Open-Source Tool for Object Removal in Diffusion Models](https://mlsanity.com/paper/2605.14461/) (2026)
- [Aligned Stable Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency](https://mlsanity.com/paper/2601.15368/) (2026)
- [ObjectMorpher: 3D-Aware Image Editing via Deformable 3DGS Models](https://mlsanity.com/paper/2603.28152/) (2026)
- [Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance](https://mlsanity.com/paper/2606.19195/) (2026)
- [Training-Free Inpainting Across Domains with a Frozen Text-to-Image Diffusion Model](https://mlsanity.com/paper/2609.00862/) (2026)
- [Beyond Pixel Reconstruction: Retrieval-Guided Glyph-Aware Restoration for Low-Resource Manchu Historical Documents](https://mlsanity.com/paper/2610.00315/) (2026)

## Abstract (arXiv)

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.