{"url":"/method/pixel-prediction","slug":"pixel-prediction","name":"Inpainting","full_name":"Inpainting","full_name_withheld":false,"description_markdown":"Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Context Encoders: Feature Learning by Inpainting","paper":"/paper/context-encoders-feature-learning-by","first_author":"Deepak Pathak","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/context-encoders-feature-learning-by"},"source":{"url":"http://arxiv.org/abs/1604.07379v2","title":"Context Encoders: Feature Learning by Inpainting","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Self-Supervised Learning","url":"/methods/category/self-supervised-learning","pwc_aliases":[]}],"n_papers_tagged":998,"archive_num_papers":998,"papers_newest_first":[{"paper":"/paper/mfgdiffusion-mask-guided-smoke-synthesis-for","title":"MFGDiffusion: Mask-Guided Smoke Synthesis for Enhanced Forest Fire Detection","date":"2025-07-15","arxiv_id":"2507.11252","n_code_links":1,"syntology":null},{"paper":null,"title":"The model is the message: Lightweight convolutional autoencoders applied to noisy imaging data for planetary science and astrobiology","date":"2025-07-15","arxiv_id":"2507.11400","n_code_links":0,"syntology":null},{"paper":null,"title":"RePaintGS: Reference-Guided Gaussian Splatting for Realistic and View-Consistent 3D Scene Inpainting","date":"2025-07-11","arxiv_id":"2507.08434","n_code_links":0,"syntology":null},{"paper":null,"title":"Rethinking Layered Graphic Design Generation with a Top-Down Approach","date":"2025-07-08","arxiv_id":"2507.05601","n_code_links":0,"syntology":null},{"paper":null,"title":"MTADiffusion: Mask Text Alignment Diffusion Model for Object Inpainting","date":"2025-06-30","arxiv_id":"2506.23482","n_code_links":0,"syntology":null},{"paper":null,"title":"Controllable 3D Placement of Objects with Scene-Aware Diffusion Models","date":"2025-06-26","arxiv_id":"2506.21446","n_code_links":0,"syntology":null},{"paper":"/paper/deocc-1-to-3-3d-de-occlusion-from-a-single","title":"DeOcc-1-to-3: 3D De-Occlusion from a Single Image via Self-Supervised Multi-View Diffusion","date":"2025-06-26","arxiv_id":"2506.21544","n_code_links":1,"syntology":null},{"paper":null,"title":"Video Virtual Try-on with Conditional Diffusion Transformer Inpainter","date":"2025-06-26","arxiv_id":"2506.21270","n_code_links":0,"syntology":null},{"paper":null,"title":"Let Your Video Listen to Your Music!","date":"2025-06-23","arxiv_id":"2506.18881","n_code_links":0,"syntology":null},{"paper":null,"title":"3DeepRep: 3D Deep Low-rank Tensor Representation for Hyperspectral Image Inpainting","date":"2025-06-20","arxiv_id":"2506.16735","n_code_links":0,"syntology":null},{"paper":null,"title":"Exploring Diffusion with Test-Time Training on Efficient Image Restoration","date":"2025-06-17","arxiv_id":"2506.14541","n_code_links":0,"syntology":null},{"paper":null,"title":"orGAN: A Synthetic Data Augmentation Pipeline for Simultaneous Generation of Surgical Images and Ground Truth Labels","date":"2025-06-17","arxiv_id":"2506.14303","n_code_links":0,"syntology":null},{"paper":null,"title":"VideoPDE: Unified Generative PDE Solving via Video Inpainting Diffusion Models","date":"2025-06-16","arxiv_id":"2506.13754","n_code_links":0,"syntology":null},{"paper":null,"title":"3D Hand Mesh-Guided AI-Generated Malformed Hand Refinement with Hand Pose Transformation via Diffusion Model","date":"2025-06-15","arxiv_id":"2506.12680","n_code_links":0,"syntology":null},{"paper":null,"title":"Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation","date":"2025-06-13","arxiv_id":"2506.11924","n_code_links":0,"syntology":null},{"paper":null,"title":"VEIGAR: View-consistent Explicit Inpainting and Geometry Alignment for 3D object Removal","date":"2025-06-13","arxiv_id":"2506.15821","n_code_links":0,"syntology":null},{"paper":null,"title":"InstaInpaint: Instant 3D-Scene Inpainting with Masked Large Reconstruction Model","date":"2025-06-12","arxiv_id":"2506.10980","n_code_links":0,"syntology":null},{"paper":null,"title":"Conditional diffusion models for guided anomaly detection in brain images using fluid-driven anomaly randomization","date":"2025-06-11","arxiv_id":"2506.10233","n_code_links":0,"syntology":null},{"paper":null,"title":"HiSin: Efficient High-Resolution Sinogram Inpainting via Resolution-Guided Progressive Inference","date":"2025-06-10","arxiv_id":"2506.08809","n_code_links":0,"syntology":null},{"paper":null,"title":"Difference Inversion: Interpolate and Isolate the Difference with Token Consistency for Image Analogy Generation","date":"2025-06-09","arxiv_id":"2506.07750","n_code_links":0,"syntology":null},{"paper":null,"title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","date":"2025-06-09","arxiv_id":"2506.07740","n_code_links":0,"syntology":null},{"paper":"/paper/highly-compressed-tokenizer-can-generate","title":"Highly Compressed Tokenizer Can Generate Without Training","date":"2025-06-09","arxiv_id":"2506.08257","n_code_links":1,"syntology":null},{"paper":null,"title":"MARS: Radio Map Super-resolution and Reconstruction Method under Sparse Channel Measurements","date":"2025-06-05","arxiv_id":"2506.04682","n_code_links":0,"syntology":null},{"paper":null,"title":"Follow-Your-Creation: Empowering 4D Creation through Video Inpainting","date":"2025-06-05","arxiv_id":"2506.04590","n_code_links":0,"syntology":null},{"paper":null,"title":"Geological Field Restoration through the Lens of Image Inpainting","date":"2025-06-05","arxiv_id":"2506.04869","n_code_links":0,"syntology":null},{"paper":"/paper/oggsplat-open-gaussian-growing-for","title":"OGGSplat: Open Gaussian Growing for Generalizable Reconstruction with Expanded Field-of-View","date":"2025-06-05","arxiv_id":"2506.05204","n_code_links":1,"syntology":null},{"paper":null,"title":"DreamDance: Animating Character Art via Inpainting Stable Gaussian Worlds","date":"2025-05-30","arxiv_id":"2505.24733","n_code_links":0,"syntology":null},{"paper":null,"title":"MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction","date":"2025-05-29","arxiv_id":"2505.23305","n_code_links":0,"syntology":null},{"paper":"/paper/unitex-universal-high-fidelity-generative","title":"UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes","date":"2025-05-29","arxiv_id":"2505.23253","n_code_links":1,"syntology":null},{"paper":"/paper/video-editing-for-audio-visual-dubbing","title":"Video Editing for Audio-Visual Dubbing","date":"2025-05-29","arxiv_id":"2505.23406","n_code_links":1,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/image-inpainting","name":"Image Inpainting","papers":361},{"task":"/task/image-generation","name":"Image Generation","papers":113},{"task":"/task/denoising","name":"Denoising","papers":108},{"task":"/task/video-inpainting","name":"Video Inpainting","papers":90},{"task":"/task/object","name":"Object","papers":70},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":47},{"task":"/task/decoder","name":"Decoder","papers":39},{"task":"/task/image-restoration","name":"Image Restoration","papers":37},{"task":"/task/segmentation","name":"Segmentation","papers":37},{"task":"/task/super-resolution","name":"Super-Resolution","papers":36},{"task":"/task/novel-view-synthesis","name":"Novel View Synthesis","papers":31},{"task":"/task/nerf","name":"NeRF","papers":29},{"task":"/task/optical-flow-estimation","name":"Optical Flow Estimation","papers":29},{"task":null,"name":"Generative Adversarial Network","papers":27},{"task":"/task/diversity","name":"Diversity","papers":26},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":24},{"task":"/task/facial-inpainting","name":"Facial Inpainting","papers":23},{"task":"/task/image-reconstruction","name":"Image Reconstruction","papers":21},{"task":"/task/virtual-try-on","name":"Virtual Try-on","papers":21},{"task":"/task/depth-estimation","name":"Depth Estimation","papers":19}],"tasks_shown":20,"n_tasks":444,"usage_by_year":[{"year":"2016","papers":1},{"year":"2020","papers":38},{"year":"2021","papers":121},{"year":"2022","papers":153},{"year":"2023","papers":220},{"year":"2024","papers":331},{"year":"2025","papers":134}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/pixel-prediction"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}