Awesome-Inpainting-Tech

A curated list of inpainting papers and resources, inspired by awesome-computer-vision.

This README.md is automatically generated from .dev_scripts/collection.csv.

We provide scripts to automatically generate README.md from CSV file or vice versa.

Welcome to pull request to update or correct this collection. 🥰

Year 2026

• AAAI (image) FreeInpaint: Tuning-free Prompt Alignment and Visual Rationality Enhancement in Image Inpainting. [code]

Year 2025

• CVPR (image) RAD: Region-Aware Diffusion Models for Image Inpainting. [code] [project]

Year 2024

• ECCV (image) A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting. [code] [project]
• ECCV (image) Improving Text-guided Object Inpainting with Semantic Pre-inpainting. [code]
• ECCV (image) Placing Objects in Context via Inpainting for Out-of-distribution Segmentation. [code]
• ECCV (image) BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion. [code]
• WACV (image) LatentPaint: Image Inpainting in Latent Space with Diffusion Models.
• WACV (image) Personalized Face Inpainting with Diffusion Models by Parallel Visual Attention.
• CVPR (video) AVID: Any-Length Video Inpainting with Diffusion Model.
• CVPR (video) Towards Language-Driven Video Inpainting via Multimodal Large Language Models. [code] [project]
• CVPR (image) Don’t Look into the Dark: Latent Codes for Pluralistic Image Inpainting.
• CVPR (image) Brush2Prompt: Contextual Prompt Generator for Object Inpainting.

Year 2023

• ICCV (video) ProPainter: Improving Propagation and Transformer for Video Inpainting. [code] [project]
• ICCV (image) MI-GAN: A Simple Baseline for Image Inpainting on Mobile Devices. [code]
• ICCV (image) Semantic-Aware Dynamic Parameter for Video Inpainting Transformer.
• ICCV (image) Virtual Try-On with Pose-Garment Keypoints Guided Inpainting. [code]
• CVPR (video) Deep Stereo Video Inpainting.
• CVPR (video) Semi-Supervised Video Inpainting With Cycle Consistency Constraints.
• CVPR (image) NUWA-LIP: Language-Guided Image Inpainting With Defect-Free VQGAN. [code]
• CVPR (image) SmartBrush: Text and Shape Guided Object Inpainting With Diffusion Model.
• CVPR (image) Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting. [project]

Year 2022

• WACV (image) Resolution-robust Large Mask Inpainting with Fourier Convolutions. [code] [project]
• ECCV (video) Flow-Guided Transformer for Video Inpainting. [code] [project]
• ECCV (video) Error Compensation Framework for Flow-Guided Video Inpainting. [code]
• ECCV (image) Diverse Image Inpainting with Normalizing Flow.
• ECCV (image) Learning Prior Feature and Attention Enhanced Image Inpainting. [code]
• ECCV (image) High-Fidelity Image Inpainting with GAN Inversion. [code]
• ECCV (image) Image Inpainting with Cascaded Modulation GAN and Object-Aware Training. [code]
• ECCV (image) Unbiased Multi-Modality Guidance for Image Inpainting. [code]
• ECCV (image) Inpainting at Modern Camera Resolution by Guided PatchMatch with Auto-Curation. [code]
• ECCV (image) Hourglass Attention Network for Image Inpainting. [code]
• ECCV (image) Perceptual Artifacts Localization for Inpainting. [code]
• CVPR (video) Towards An End-to-End Framework for Flow-Guided Video Inpainting. [code]
• CVPR (video) Inertia-Guided Flow Completion and Style Fusion for Video Inpainting. [code] [project]
• CVPR (video) DLFormer: Discrete Latent Transformer for Video Inpainting.
• CVPR (video) The DEVIL is in the Details: A Diagnostic Evaluation Benchmark for Video Inpainting. [code]
• CVPR (image) Dual-path Image Inpainting with Auxiliary GAN Inversion.
• CVPR (image) MAT: Mask-Aware Transformer for Large Hole Image Inpainting. [code]
• CVPR (image) RePaint: Inpainting using Denoising Diffusion Probabilistic Models. [code]
• CVPR (image) MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting. [code]
• CVPR (image) Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding. [code]
• CVPR (image) Reduce Information Loss in Transformers for Pluralistic Image Inpainting. [code]

Year 2021

• WACV (image) Hyperrealistic Image Inpainting with Hypergraphs. [code]
• MangoTV (challenge) Video Inpainting Challenge - MangoTV International Video Inpainting Challenge.
• ICLR (image) Large Scale Image Completion via Co-Modulated Generative Adversarial Networks. [code]
• ICCV (video) Internal Video Inpainting by Implicit Long-range Propagation. [code] [project]
• ICCV (video) FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting. [code]
• ICCV (video) Flow-Guided Video Inpainting With Scene Templates. [code]
• ICCV (video) Frequency-Aware Spatiotemporal Transformers for Video Inpainting Detection.
• ICCV (video) Occlusion-Aware Video Object Inpainting. [project]
• ICCV (image) Image Inpainting via Conditional Texture and Structure Dual Generation. [code]
• ICCV (image) CR-Fill: Generative Image Inpainting With Auxiliary Contextual Reconstruction. [code]
• ICCV (image) Parallel Multi-Resolution Fusion Network for Image Inpainting.
• ICCV (image) WaveFill: A Wavelet-Based Generation Network for Image Inpainting.
• ICCV (image) SLIDE: Single Image 3D Photography With Soft Layering and Depth-Aware Inpainting. [project]
• ICCV (image) Distillation-Guided Image Inpainting.
• ICCV (image) High-Fidelity Pluralistic Image Completion With Transformers. [code] [project]
• ICCV (image) Learning a Sketch Tensor Space for Image Inpainting of Man-Made Scenes. [code] [project]
• ICCV (image) Learning High-Fidelity Face Texture Completion Without Complete Face Texture.
• CVPR (video) Progressive Temporal Feature Alignment Network for Video Inpainting. [code]
• CVPR (image) Image Inpainting with External-internal Learning and Monochromic Bottleneck. [code] [project]
• CVPR (image) Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE. [code]
• CVPR (image) PD-GAN: Probabilistic Diverse GAN for Image Inpainting. [code]
• CVPR (image) Image Inpainting Guided by Coherence Priors of Semantics and Textures.
• CVPR (image) TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations. [code] [project]
• CVPR (image) FaceInpainter: High Fidelity Face Adaptation to Heterogeneous Domains.

Year 2020

• IJCV (image) Deep Image Prior. [code] [project]
• ECCV (video) Short-Term and Long-Term Context Aggregation Network for Video Inpainting.
• ECCV (video) Proposal-based Video Completion.
• ECCV (video) DVI: Depth Guided Video Inpainting for Autonomous Driving. [project]
• ECCV (video) Learning Joint Spatial-Temporal Transformations for Video Inpainting. [project]
• ECCV (video) Flow-edge Guided Video Completion. [project]
• ECCV (image) Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations. [code]
• ECCV (image) Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes.
• ECCV (image) VCNet: A Robust Approach to Blind Image Inpainting. [code]
• ECCV (image) High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling. [project]
• ECCV (challenge) Image Inpainting Challenge - AIM Workshop and Challenges.
• CVPR (image) Prior Guided GAN Based Semantic Inpainting.
• CVPR (image) UCTGAN: Diverse Image Inpainting based on Unsupervised Cross-Space Translation.
• CVPR (image) Recurrent Feature Reasoning for Image Inpainting. [code]
• CVPR (image) Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting. [code]
• CVPR (image) 3D Photography using Context-aware Layered Depth Inpainting. [code]
• ACCV (image) Image Inpainting with Onion Convolution.
• AAAI (image) Region Normalization for Image Inpainting. [code]
• AAAI (image) Learning to Incorporate Structure Knowledge for Image Inpainting. [code]

Year 2019

• IJCAI (image) Generative Image Inpainting with Submanifold Alignment.
• IJCAI (image) MUSICAL: Multi-Scale Image Contextual Attention Learning for Inpainting.
• IJCAI (image) Coarse-to-Fine Image Inpainting via Region-wise Convolutions and Non-Local Correlation.
• ICME (challenge) ICME Grand Challenge Learning-Based Image Inpainting.
• ICCVW (image) EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning. [code]
• ICCV (video) Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN. [code]
• ICCV (video) Onion-Peel Networks for Deep Video Completion. [code] [project]
• ICCV (video) Copy-and-Paste Networks for Deep Video Inpainting. [code] [project]
• ICCV (video) An Internal Learning Approach to Video Inpainting. [project]
• ICCV (image) StructureFlow: Image Inpainting via Structure-aware Appearance Flow. [code]
• ICCV (image) Image Inpainting with Learnable Bidirectional Attention Maps. [code]
• ICCV (image) Coherent Semantic Attention for Image Inpainting. [code]
• ICCV (image) Free-form image inpainting with gated convolution. [project]
• CVPRW (video) VORNet: Spatio-temporally Consistent Video Inpainting for Object Removal. [code]
• CVPR (video) Deep Flow-Guided Video Inpainting. [code] [project]
• CVPR (video) Deep Video Inpainting. [code] [project]
• CVPR (video) Deep Blind Video Decaptioning by Temporal Aggregation and Recurrence. [project]
• CVPR (image) Pluralistic Image Completion. [code] [project]
• CVPR (image) Learning Pyramid-Context Encoder Network for High-Quality Image Inpainting. [code]
• CVPR (image) Foreground-aware Image Inpainting.
• CVPR (image) Deep Reinforcement Learning of Volume-guided Progressive View Inpainting for 3D Point Scene Completion from a Single Depth Image.
• CVPR (image) PEPSI: Fast Image Inpainting With Parallel Decoding Network.
• CVPR (image) Coordinate-Based Texture Inpainting for Pose-Guided Human Image Generation.
• BMVC (video) Learnable Gated Temporal Shift Module for Deep Video Inpainting. [code]
• Arxiv (video) Align-and-Attend Network for Globally and Locally Coherent Video Inpainting.
• Arxiv (video) Frame-Recurrent Video Inpainting by Robust Optical Flow Inference.
• Arxiv (image) Deep Inception Generative Network for Cognitive Image Inpainting.
• Arxiv (image) Detecting Overfitting of Deep Generative Networks via Latent Recovery.
• Arxiv (image) SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Color. [code]
• Arxiv (image) Deep Fusion Network for Image Completion. [code]
• Arxiv (image) PEPSI++: Fast and Lightweight Network for Image Inpainting.
• AAAI (video) Video inpainting by jointly learning temporal structure and spatial details.

Year 2018

• TOG (image) Faceshop: Deep sketch-based face image editing.
• NeurIPS (image) Image Inpainting via Generative Multi-column Convolutional Neural Networks. [code]
• MM (image) Structural inpainting.
• MM (image) Semantic Image Inpainting with Progressive Generative Networks. [code]
• ICASPP (image) Edge-Aware Context Encoder for Image Inpainting.
• ECCVW (challenge) Looking at People ECCV Satellite Challenge.
• ECCV (image) Image inpainting for irregular holes using partial convolutions. [project]
• ECCV (image) Contextual-based image inpainting: Infer, match, and translate.
• ECCV (image) Shift-net: Image inpainting via deep feature rearrangement. [code]
• CVPR (image) Generative image inpainting with contextual attention. [code] [project]
• CVPR (image) Natural and effective obfuscation by head inpainting.
• CVPR (image) Eye in-painting with exemplar generative adversarial networks. [code] [project]
• CVPR (image) Uv-gan: Adversarial facial uv map completion for pose-invariant face recognition.
• CVPR (image) Disentangling Structure and Aesthetics for Style-aware Image Completion.
• BMVC (image) SPG-Net: Segmentation prediction and guidance network for image inpainting.
• Arxiv (image) High resolution face completion with multiple controllable attributes via fully end-to-end progressive generative adversarial networks.
• Arxiv (image) On Hallucinating Context and Background Pixels from a Face Mask using Multi-scale GANs.
• ACCV (image) Face Completion with Semantic Knowledge and Collaborative Adversarial Learning.

Year 2017

• TOG (image) Globally and locally consistent image completion. [code] [project]
• CVPR (image) High-resolution image inpainting using multi-scale neural patch synthesis. [code]
• CVPR (image) Generative face completion. [code]
• CVPR (image) Semantic image inpainting with deep generative models. [code] [project]

Year 2016

• TOG (video) Temporally coherent completion of dynamic video. [code] [project]
• CVPR (image) Context encoders: Feature learning by inpainting. [code]

Year 2015

• TIP (video) Video inpainting with short-term windows: application to object removal and error concealment.
• NeurIPS (image) Shepard convolutional neural networks. [code]

Year 2014

• TOG (image) Image completion using planar structure guidance. [code] [project]
• SIAM Journal on Imaging Sciences (video) Video inpainting of complex scenes. [project]

Year 2012

• ECCV (video) Background inpainting for videos with dynamic objects and a free-moving camera. [project]
• Computer Graphics Forum (video) How not to be seen-object removal from videos of crowded scenes. [project]

Year 2009

• TOG (image) PatchMatch: A randomized correspondence algorithm for structural image editing. [project]

Year 2007

• TPAMI (video) Space-time completion of video. [project]
• TIP (video) Video inpainting under constrained camera motion.

Year 2006

• TPAMI (video) Full-frame video stabilization with motion inpainting. [project]
• CVPR (video) Video completion by motion field transfer. [project]

Year 2005

• TOG (image) Image completion with structure propagation.
• ICIP (video) Video inpainting of occluding and occluded objects.

Year 2004

• TIP (image) Region filling and object removal by exemplar-based image inpainting.

Year 2003

• TIP (image) Simultaneous structure and texture image inpainting.

Year 2001

• CVPR (video) Navier-stokes, fluid dynamics, and image and video inpainting.

Year 2000

• SIGGRAPH (image) Image inpainting.