# Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations

arXiv: https://arxiv.org/abs/2007.06929 · HTML: https://mlsanity.com/paper/2007.06929/

## Key facts

- Cited by 102 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jul 2020.

## Built on by (most cited first, 30 of 102)

- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models](https://mlsanity.com/paper/2301.12661/) (2023)
- [TextDiffuser: Diffusion Models as Text Painters](https://mlsanity.com/paper/2305.10855/) (2023)
- [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)
- [VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples](https://mlsanity.com/paper/2103.05905/) (2021)
- [Parser-Free Virtual Try-on via Distilling Appearance Flows](https://mlsanity.com/paper/2103.04559/) (2021)
- [High-Fidelity Pluralistic Image Completion with Transformers](https://mlsanity.com/paper/2103.14031/) (2021)
- [ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows](https://mlsanity.com/paper/2103.16877/) (2021)
- [Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE](https://mlsanity.com/paper/2103.10022/) (2021)
- [Diverse Image Inpainting with Bidirectional and Autoregressive Transformers](https://mlsanity.com/paper/2104.12335/) (2021)
- [PD-GAN: Probabilistic Diverse GAN for Image Inpainting](https://mlsanity.com/paper/2105.02201/) (2021)
- [ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion](https://mlsanity.com/paper/2403.18818/) (2024)
- [Image Inpainting via Conditional Texture and Structure Dual Generation](https://mlsanity.com/paper/2108.09760/) (2021)
- [AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors](https://mlsanity.com/paper/2310.17419/) (2023)
- [Disentangled Cycle Consistency for Highly-realistic Virtual Try-On](https://mlsanity.com/paper/2103.09479/) (2021)
- [Follow-Your-Creation: Empowering 4D Creation through Video Inpainting](https://mlsanity.com/paper/2506.04590/) (2025)
- [CM-GAN: Image Inpainting with Cascaded Modulation GAN and Object-Aware Training](https://mlsanity.com/paper/2203.11947/) (2022)
- [WaveFill: A Wavelet-based Generation Network for Image Inpainting](https://mlsanity.com/paper/2107.11027/) (2021)
- [Deep Learning-based Image and Video Inpainting: A Survey](https://mlsanity.com/paper/2401.03395/) (2024)
- [Bridging Global Context Interactions for High-Fidelity Image Completion](https://mlsanity.com/paper/2104.00845/) (2021)
- [Reduce Information Loss in Transformers for Pluralistic Image Inpainting](https://mlsanity.com/paper/2205.05076/) (2022)
- [CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying](https://mlsanity.com/paper/2303.08524/) (2023)
- [SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches](https://mlsanity.com/paper/2111.15078/) (2021)
- [DeFLOCNet: Deep Image Editing via Flexible Low-level Controls](https://mlsanity.com/paper/2103.12723/) (2021)
- [Learning a Sketch Tensor Space for Image Inpainting of Man-made Scenes](https://mlsanity.com/paper/2103.15087/) (2021)
- [De-rendering Stylized Texts](https://mlsanity.com/paper/2110.01890/) (2021)
- [RORem: Training a Robust Object Remover with Human-in-the-Loop](https://mlsanity.com/paper/2501.00740/) (2025)

## Abstract (arXiv)

Deep encoder-decoder based CNNs have advanced image inpainting methods for hole filling. While existing methods recover structures and textures step-by-step in the hole regions, they typically use two encoder-decoders for separate recovery. The CNN features of each encoder are learned to capture either missing structures or textures without considering them as a whole. The insufficient utilization of these encoder features limit the performance of recovering both structures and textures. In this paper, we propose a mutual encoder-decoder CNN for joint recovery of both. We use CNN features from the deep and shallow layers of the encoder to represent structures and textures of an input image, respectively. The deep layer features are sent to a structure branch and the shallow layer features are sent to a texture branch. In each branch, we fill holes in multiple scales of the CNN features. The filled CNN features from both branches are concatenated and then equalized. During feature equalization, we reweigh channel attentions first and propose a bilateral propagation activation function to enable spatial equalization. To this end, the filled CNN features of structure and texture mutually benefit each other to represent image content at all feature levels. We use the equalized feature to supplement decoder features for output image generation through skip connections. Experiments on the benchmark datasets show the proposed method is effective to recover structures and textures and performs favorably against state-of-the-art approaches.