# VCNet: A Robust Approach to Blind Image Inpainting

arXiv: https://arxiv.org/abs/2003.06816 · HTML: https://mlsanity.com/paper/2003.06816/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Mar 2020.

## Built on by (most cited first, 25 of 25)

- [Image Inpainting via Conditional Texture and Structure Dual Generation](https://mlsanity.com/paper/2108.09760/) (2021)
- [Image Synthesis via Semantic Composition](https://mlsanity.com/paper/2109.07053/) (2021)
- [Deep Learning-based Image and Video Inpainting: A Survey](https://mlsanity.com/paper/2401.03395/) (2024)
- [SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches](https://mlsanity.com/paper/2111.15078/) (2021)
- [Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing](https://mlsanity.com/paper/2207.09935/) (2022)
- [DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology](https://mlsanity.com/paper/2306.13384/) (2023)
- [Keys to Better Image Inpainting: Structure and Texture Go Hand in Hand](https://mlsanity.com/paper/2208.03382/) (2022)
- [PalGAN: Image Colorization with Palette Generative Adversarial Networks](https://mlsanity.com/paper/2210.11204/) (2022)
- [RGI: robust GAN-inversion for mask-free image inpainting and unsupervised pixel-wise anomaly detection](https://mlsanity.com/paper/2302.12464/) (2023)
- [FT-TDR: Frequency-guided Transformer and Top-Down Refinement Network for Blind Face Inpainting](https://mlsanity.com/paper/2108.04424/) (2021)
- [Semi-Supervised Video Inpainting with Cycle Consistency Constraints](https://mlsanity.com/paper/2208.06807/) (2022)
- [Text Image Inpainting via Global Structure-Guided Diffusion Models](https://mlsanity.com/paper/2401.14832/) (2024)
- [Coarse-to-fine Task-driven Inpainting for Geoscience Images](https://mlsanity.com/paper/2211.11059/) (2022)
- [BVINet: Unlocking Blind Video Inpainting with Zero Annotations](https://mlsanity.com/paper/2502.01181/) (2025)
- [Simulating analogue film damage to analyse and improve artefact restoration on high-resolution scans](https://mlsanity.com/paper/2302.10004/) (2023)
- [Hierarchical Contrastive Learning for Pattern-Generalizable Image Corruption Detection](https://mlsanity.com/paper/2308.14061/) (2023)
- [Blind Image Inpainting with Sparse Directional Filter Dictionaries for Lightweight CNNs](https://mlsanity.com/paper/2205.06597/) (2022)
- [Masked Face Inpainting Through Residual Attention UNet](https://mlsanity.com/paper/2209.08850/) (2022)
- [Blind Inpainting with Object-aware Discrimination for Artificial Marker Removal](https://mlsanity.com/paper/2303.15124/) (2023)
- [Defending Adversarial Patches via Joint Region Localizing and Inpainting](https://mlsanity.com/paper/2307.14242/) (2023)
- [AURA : Automatic Mask Generator using Randomized Input Sampling for Object Removal](https://mlsanity.com/paper/2305.07857/) (2023)
- [Task-Decoupled Image Inpainting Framework for Class-specific Object Remover](https://mlsanity.com/paper/2410.02894/) (2024)
- [ARTeFACT: Benchmarking Segmentation Models on Diverse Analogue Media Damage](https://mlsanity.com/paper/2412.04580/) (2024)
- [Echo-DM: Ultrasound Marker Removal via Conditional Latent Diffusion and Region-Aware Fusion](https://mlsanity.com/paper/2606.09378/) (2026)
- [Context-Aware Mutual Learning for Blind Image Inpainting and Beyond](https://mlsanity.com/paper/2609.14439/) (2026)

## Abstract (arXiv)

Blind inpainting is a task to automatically complete visual contents without specifying masks for missing areas in an image. Previous works assume missing region patterns are known, limiting its application scope. In this paper, we relax the assumption by defining a new blind inpainting setting, making training a blind inpainting neural system robust against various unknown missing region patterns. Specifically, we propose a two-stage visual consistency network (VCN), meant to estimate where to fill (via masks) and generate what to fill. In this procedure, the unavoidable potential mask prediction errors lead to severe artifacts in the subsequent repairing. To address it, our VCN predicts semantically inconsistent regions first, making mask prediction more tractable. Then it repairs these estimated missing regions using a new spatial normalization, enabling VCN to be robust to the mask prediction errors. In this way, semantically convincing and visually compelling content is thus generated. Extensive experiments are conducted, showing our method is effective and robust in blind image inpainting. And our VCN allows for a wide spectrum of applications.