This GitHub repository summarizes papers and resources related to the image inpainting task.
If you have any suggestions about this repository, please feel free to start a new issue or pull requests.
🔥 [Nov. 19th] We have released our latest paper titled "StableV2V: Stablizing Shape Consistency in Video-to-Video Editing", with the correponding code, model weights, and a testing benchmark DAVIS-Edit
open-sourced. Feel free to check them out from the links!
- [May 29th] Papers with "⚠" are updated.
- [May 17th] Our paper titled "Towards Interactive Image Inpainting via Robust Sketch Refinement" is accepted by TMM 2024!
- [Mar. 7th] CVPR 2024, AAAI 2024, ICLR 2024 papers are updated. PDFs and references will be updated as soon as they are released.
- To-Do Lists
- Papers (Mainly Deep Learning-Based)
- Survey Papers
- Datasets
- Q&A
- References
- Star History
- Recent Papers
- Update ECCV 2024 Papers
- Update CVPR 2024 Papers
- Update AAAI 2024 Papers
- Update PDFs and References
- Update ICLR 2024 Papers
- Update NeurIPS 2024 Papers
- Regular Maintenance of Preprint arXiv Papers and Missed Papers
- Previous Papers
- Published Papers on Conferences
- Update CVPR papers
- Update CVPRW papers
- Update ICCV papers
- Update ICCVW papers
- Update ECCV papers
- Update AAAI papers
- Update IJCAI papers
- Update ACM MM papers
- Update WACV papers
- Update NeurIPS papers
- Update ICLR papers
- Published Papers on Journals
- Update TMM papers
- Update TIP papers
- Update TPAMI papers
- Update TCSVT papers
- Published Papers on Conferences
- Year 2024
- CVPR
- ECCV
- ICLR
- SIGGRAPH
- arXiv
- Outline-Guided Object Inpainting with Diffusion Models [Paper]
- DesignEdit: Multi-Layered Latent Decomposition and Fusion for Unified & Accurate Image Editing [Paper] [Code] [Project]
- Anywhere: A Multi-Agent Framework for Reliable and Diverse Foreground-Conditioned Image Inpainting [Paper] [Code] [Project]
- Year 2023
- CVPR
- NÜWA-LIP: Language-guided Image Inpainting with Defect-free VQGAN [Paper] [Code]
- Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting [Paper]
- SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model [Paper]
- Paint by Example: Exemplar-based Image Editing with Diffusion Models [Paper] [Code] [Demo]
- CVPRW
- Scene Graph Driven Text-Prompt Generation for Image Inpainting [Paper]
- ACM MM
- SIGGRAPH
- WACV
- CVPR
- Year 2022
- Year 2021
- Year 2020
- Year 2024
- Year 2023
- Year 2022
- CVPR
- MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting [Paper] [Code]
- MAT: Mask-Aware Transformer for Large Hole Image Inpainting [Paper] [Code]
- Reduce Information Loss in Transformers for Pluralistic Image Inpainting [Paper] [Code]
- Dual-path Image Inpainting with Auxiliary GAN Inversion [Paper]
- RePaint: Inpainting using Denoising Diffusion Probabilistic Models [Paper] [Code]
- TFill: Bridging Global Context Interactions for High-Fidelity Image Completion [Paper] [Code] [Project] [Video]
- CVPRW
- Zoom-to-Inpaint: Image Inpainting with High-Frequency Details [Paper] [Code]
- Boundary-aware Image Inpainting with Multiple Auxiliary Cues [Paper] [Code]
- Comparison of CoModGANs, LaMa and GLIDE for Art Inpainting Completing M.C Escher's Print Gallery [Paper]
- Image Multi-Inpainting via Progressive Generative Adversarial Networks [Paper]
- NTIRE 2022 Image Inpainting Challenge: Report [Paper] [Code]
- GLaMa: Joint Spatial and Frequency Loss for General Image Inpainting [Paper]
- PersonGONE: Image Inpainting for Automated Checkout Solution [Paper] [Code]
- ECCV
- MAE-FAR: Learning Prior Feature and Attention Enhanced Image Inpainting [Paper] [Code]
- InvertFill: High-Fidelity Image Inpainting with GAN Inversion [Paper] [Code]
- CM-GAN: Image Inpainting with Cascaded Modulation GAN and Object-Aware Training [Paper] [Code]
- Unbiased Multi-Modality Guidance for Image Inpainting [Paper] [Code]
- Inpainting at Modern Camera Resolution by Guided PatchMatch with Auto-Curation [Paper] [Code]
- Hourglass Attention Network for Image Inpainting [Paper] [Code]
- Diverse Image Inpainting with Normalizing Flow [Paper]
- Perceptual Artifacts Localization for Inpainting [Paper] [Code]
- Iterative Geometry-Aware Cross Guidance Network for Stereo Image Inpainting [Paper]
- ACM MM
- WACV
- NeurIPS
- Cross-Image Context for Single Image Inpainting [Paper]
- TMM
- TIP
- TPAMI
- TCSVT
- Dual-Pyramidal Image Inpainting With Dynamic Normalization [Paper]
- arXiv
- CVPR
- Year 2021
- CVPR
- TransFill: Reference-Guided Image Inpainting by Merging Multiple Color and Spatial Transformations [Paper] [Code]
- Image Inpainting With External-Internal Learning and Monochromic Bottleneck [Paper] [Code]
- Image Inpainting Guided by Coherence Priors of Semantics and Textures [Paper]
- PD-GAN: Probabilistic Diverse GAN for Image Inpainting [Paper] [Code]
- Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE [Paper] [Code]
- ICCV
- Distillation-guided Image Inpainting [Paper]
- WaveFill: A Wavelet-based Generation Network for Image Inpainting [Paper] [Code]
- CR-Fill: Generative Image Inpainting with Auxiliary Contextual Reconstruction [Paper] [Code]
- Parallel Multi-Resolution Fusion Network for Image Inpainting [Paper]
- ICT: High-Fidelity Pluralistic Image Completion with Transformers [Paper] [Code] [Project]
- IJCAI
- ACM MM
- BAT-Fill: Diverse Image Inpainting with Bidirectional and Autoregressive Transformers [Paper] [Code]
- JPGNet: Joint Predictive Filtering and Generative Network for Image Inpainting [Paper] [Code]
- Learning Contextual Transformer Network for Image Inpainting [Paper]
- GCM-Net: Towards Effective Global Context Modeling for Image Inpainting [Paper] [Code]
- An Adaptive Iterative Inpainting Method with More Information Exploration [Paper]
- Large Scale Image Completion via Co-Modulated Generative Adversarial Networks [[Paper]](Large Scale Image Completion via Co-Modulated Generative Adversarial Networks) [Code]
- WACV
- TIP
- Dynamic Selection Network for Image Inpainting [Paper] [Code]
- Thanka Mural Inpainting Based on Multi-Scale Adaptive Partial Convolution and Stroke-Like Mask [Paper]
- Image Inpainting by End-to-End Cascaded Refinement With Mask Awareness [Paper] [Code]
- Texture Memory-Augmented Deep Patch-Based Image Inpainting [Paper]
- TCSVT
- CVPR
- Year 2020
- CVPR
- UCTGAN: Diverse Image Inpainting Based on Unsupervised Cross-Space Translation [Paper]
- Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting [Paper] [Code]
- RFR-Net: Recurrent Feature Reasoning for Image Inpainting [Paper] [Code]
- Prior Guided GAN Based Semantic Inpainting [Paper]
- Semantic Image Manipulation Using Scene Graph [Paper] [Code]
- ECCV
- MEDFE: Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations [Paper] [Code]
- High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling [Paper]
- Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes [Paper]
- Deep Generative Prior: Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation [Paper] [Code] [Video]
- AAAI
- ACM MM
- Image Inpainting Based on Multi-frequency Probabilistic Inference Model [Paper]
- CVPR
- Year 2019
- CVPR
- ICCV
- ICCVW
- IJCAI
- Generative Image Inpainting with Submanifold Alignment [Paper]
- Coarse-to-Fine Image Inpainting via Region-wise Convolutions and Non-Local Correlation [Paper]
- MUSICAL: Multi-Scale Image Contextual Attention Learning for Inpainting [Paper] [Code]
- Single-shot Semantic Image Inpainting with Densely Connected Generative Networks [Paper]
- GAIN: Gradient Augmented Inpainting Network for Irregular Holes [Paper]
- Progressive Image Inpainting with Full-Resolution Residual Network [Paper] [Code]
- Deep Fusion Network for Image Completion [Paper] [Code]
- Year 2018
- CVPR
- ECCV
- ACM MM
- NeurIPS
- Photo Realistic Image Completion via Dense Correspondence [Paper]
- Year 2017
- Year 2023
- Year 2022
- Year 2020
- ECCV
- VCNet: A Robust Approach to Blind Image Inpainting [Paper] [Reproduced Code]
- ECCV
- Year 2023
- Year 2022
- Year 2021
- Year 2019
- Year 2024
- Year 2023
- Year 2022
- Year 2021
- Year 2020
- Year 2019
- Year 2024
- Year 2023
- Year 2022
- Year 2021
- Year 2020
- Year 2017
- Year 2024
- TexFit: Text-Driven Fashion Image Editing with Diffusion Models [Paper]
- Year 2019
- Year 2024
- arXiv
- HySim: An Efficient Hybrid Similarity Measure for Patch Matching in Image Inpainting [Paper]
- arXiv
- Year 2020
- Year 2019
- Multiple Pyramids Based Image Inpainting Using Local Patch Statistics and Steering Kernel Feature [Paper]
- Year 2018
- TIP
- A Group-Based Image Inpainting Using Patch Refinement in MRF Framework [Paper]
- TIP
- Year 2016
- Year 2011
- ICIG
- Structure-Aware Image Completion with Texture Propagation [Paper]
- ICIG
- Year 2005
- Year 2004
- TIP
- Region Filling and Object Removal by Exemplar-Based Image Inpainting [Paper]
- TIP
- Year 2000
- SIGGRAPH
- Image Inpainting [Paper]
- SIGGRAPH
- [IJCV 2024] Deep Learning-based Image and Video Inpainting: A Survey [Paper]
- [Pattern Recognit. 2023] Deep Learning for Image Inpainting: A Survey [Paper]
- Paris StreetView: Context Encoders: Feature Learning by Inpainting [Paper] [Code] (Since Google's terms of service has forbidden anyone from creating repositories of streetview data, the dataset is currently not available.)
- Places: A 10 Million Image Database for Scene Recognition [Paper] [Dataset]
- ImageNet: A Large-Scale Hierarchical Image Database [Paper] [Dataset]
- CelebA-HQ: Progressive Growing of GANs for Improved Quality, Stability, and Variation [Paper] [Dataset]
- FFHQ: A Style-Based Generator Architecture for Generative Adversarial Networks [Paper] [Dataset]
- Q: The conference sequence of this paper list?
- This paper list is organized according to the following sequence:
- Conferences
- CVPR
- CVPRW
- ICCV
- ICCVW
- ECCV
- AAAI
- IJCAI
- WACV
- NeurIPS
- ICLR
- ACM MM
- SIGGRAPH
- IPTA
- Journals
- TMM
- TIP
- TPAMI
- TCSVT
- arXiv
- Conferences
- This paper list is organized according to the following sequence:
The reference.bib
file summarizes bibtex references of up-to-date image inpainting papers, widely used datasets, and toolkits.
Based on the original references, I have made the following modifications to make their results look nice in the LaTeX
manuscripts:
- Refereces are normally constructed in the form of
author-etal-year-nickname
. Particularly, references of datasets and toolkits are directly constructed asnickname
, e.g.,imagenet
. - In each reference, all names of conferences/journals are converted into abbreviations, e.g.,
Computer Vision and Pattern Recognition -> CVPR
. - The
url
,doi
,publisher
,organization
,editor
,series
in all references are removed. - The
pages
of all references are added if they are missing. - All paper names are in title case. Besides, I have added an additional
{}
to make sure that the title case would also work well in some particular templates.
If you have other demands of reference formats, you may refer to the original references of papers by searching their names in DBLP or Google Scholar.