{"url":"/task/image-manipulation","name":"Image Manipulation","slug":"image-manipulation","description_markdown":"Image Manipulation is the process of altering or transforming an existing image to achieve a desired effect or to modify its content. This can involve various techniques and tools to enhance, modify, or create images based on specific requirements.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":427,"papers_with_code":201,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":7,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/image-manipulation-on-lrs2","slug":"image-manipulation-on-lrs2","dataset":"LRS2","dataset_url":"/dataset/lrs2","rows_in_archive":2,"metrics":["LPIPS (S1)","LPIPS (S2)","LPIPS (S3)","LPIPS (S4)","LPIPS (S5)","SIFID (S1)","SIFID (S2)","SIFID (S3)","SIFID (S4)","SIFID (S5)"],"first_row_in_archive_order":{"model":"TPS","paper_title":"Image Shape Manipulation from a Single Augmented Training Sample","paper_url":"/paper/image-shape-manipulation-from-a-single","paper_date":"2021-09-13","arxiv_id":"2109.06151","code_links":[{"title":"eliahuhorwitz/DeepSIM","url":"https://github.com/eliahuhorwitz/DeepSIM"}],"syntology":null}}],"datasets":[{"url":"/dataset/celebamask-hq","name":"CelebAMask-HQ","full_name":"","num_papers_in_archive":164},{"url":"/dataset/lrs2","name":"LRS2","full_name":"Lip Reading Sentences 2","num_papers_in_archive":115},{"url":"/dataset/casia-v2","name":"CASIA V2","full_name":"CASIA V2","num_papers_in_archive":15},{"url":"/dataset/casia-osn-transmitted-weibo","name":"CASIA (OSN-transmitted - Weibo)","full_name":"","num_papers_in_archive":4},{"url":"/dataset/casia-osn-transmitted-whatsapp","name":"CASIA (OSN-transmitted - Whatsapp)","full_name":"","num_papers_in_archive":4},{"url":"/dataset/satire-dataset","name":"Satire Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/image-manipulation-dataset-df2023","name":"Digital Forensics 2023 dataset - DF2023","full_name":"","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/image-generation","name":"Image Generation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":201,"tagged_in_all":427,"items":[{"url":"/paper/singan-learning-a-generative-model-from-a","title":"SinGAN: Learning a Generative Model from a Single Natural Image","date":"2019-05-02","arxiv_id":"1905.01164","repositories_listed":47,"syntology":{"n":11,"n_ran":2,"n_unverified":9,"n_pointer_only":3}},{"url":"/paper/closed-form-factorization-of-latent-semantics","title":"Closed-Form Factorization of Latent Semantics in GANs","date":"2020-07-13","arxiv_id":"2007.06600","repositories_listed":11,"syntology":{"n":14,"n_ran":7,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/maskgit-masked-generative-image-transformer","title":"MaskGIT: Masked Generative Image Transformer","date":"2022-02-08","arxiv_id":"2202.04200","repositories_listed":9,"syntology":{"n":21,"n_ran":14,"n_unverified":7,"n_pointer_only":4}},{"url":"/paper/designing-an-encoder-for-stylegan-image","title":"Designing an Encoder for StyleGAN Image Manipulation","date":"2021-02-04","arxiv_id":"2102.02766","repositories_listed":8,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/srflow-learning-the-super-resolution-space","title":"SRFlow: Learning the Super-Resolution Space with Normalizing Flow","date":"2020-06-25","arxiv_id":"2006.14200","repositories_listed":8,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/drag-your-gan-interactive-point-based","title":"Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold","date":"2023-05-18","arxiv_id":"2305.10973","repositories_listed":7,"syntology":{"n":16,"n_ran":7,"n_unverified":9,"n_pointer_only":3}},{"url":"/paper/maskgan-towards-diverse-and-interactive","title":"MaskGAN: Towards Diverse and Interactive Facial Image Manipulation","date":"2019-07-27","arxiv_id":"1907.11922","repositories_listed":7,"syntology":null},{"url":"/paper/controlling-perceptual-factors-in-neural","title":"Controlling Perceptual Factors in Neural Style Transfer","date":"2016-11-23","arxiv_id":"1611.07865","repositories_listed":6,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/styleclip-text-driven-manipulation-of","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","date":"2021-03-31","arxiv_id":"2103.17249","repositories_listed":5,"syntology":{"n":11,"n_ran":7,"n_unverified":4,"n_pointer_only":1}},{"url":"/paper/kornia-an-open-source-differentiable-computer","title":"Kornia: an Open Source Differentiable Computer Vision Library for PyTorch","date":"2019-10-05","arxiv_id":"1910.02190","repositories_listed":5,"syntology":{"n":20,"n_ran":0,"n_unverified":20,"n_pointer_only":0}},{"url":"/paper/learning-accurate-dense-correspondences-and","title":"Learning Accurate Dense Correspondences and When to Trust Them","date":"2021-01-05","arxiv_id":"2101.01710","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/swapping-autoencoder-for-deep-image","title":"Swapping Autoencoder for Deep Image Manipulation","date":"2020-07-01","arxiv_id":"2007.00653","repositories_listed":4,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":7}},{"url":"/paper/interpreting-the-latent-space-of-gans-for","title":"Interpreting the Latent Space of GANs for Semantic Face Editing","date":"2019-07-25","arxiv_id":"1907.10786","repositories_listed":4,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":5}},{"url":"/paper/dreamsampler-unifying-diffusion-sampling-and","title":"DreamSampler: Unifying Diffusion Sampling and Score Distillation for Image Manipulation","date":"2024-03-18","arxiv_id":"2403.11415","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/a-unified-prompt-guided-in-context-inpainting","title":"LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model","date":"2023-05-19","arxiv_id":"2305.11577","repositories_listed":3,"syntology":null},{"url":"/paper/versatile-diffusion-text-images-and","title":"Versatile Diffusion: Text, Images and Variations All in One Diffusion Model","date":"2022-11-15","arxiv_id":"2211.08332","repositories_listed":3,"syntology":null},{"url":"/paper/stylegan-nada-clip-guided-domain-adaptation","title":"StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators","date":"2021-08-02","arxiv_id":"2108.00946","repositories_listed":3,"syntology":{"n":10,"n_ran":4,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/d2c-diffusion-denoising-models-for-few-shot","title":"D2C: Diffusion-Denoising Models for Few-shot Conditional Generation","date":"2021-06-12","arxiv_id":"2106.06819","repositories_listed":3,"syntology":{"n":20,"n_ran":13,"n_unverified":7,"n_pointer_only":3}},{"url":"/paper/pivotal-tuning-for-latent-based-editing-of","title":"Pivotal Tuning for Latent-based Editing of Real Images","date":"2021-06-10","arxiv_id":"2106.05744","repositories_listed":3,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/conditional-image-generation-and-manipulation","title":"Conditional Image Generation and Manipulation for User-Specified Content","date":"2020-05-11","arxiv_id":"2005.04909","repositories_listed":3,"syntology":null},{"url":"/paper/stylegan2-distillation-for-feed-forward-image","title":"StyleGAN2 Distillation for Feed-forward Image Manipulation","date":"2020-03-07","arxiv_id":"2003.03581","repositories_listed":3,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/manigan-text-guided-image-manipulation","title":"ManiGAN: Text-Guided Image Manipulation","date":"2019-12-12","arxiv_id":"1912.06203","repositories_listed":3,"syntology":null},{"url":"/paper/mantra-net-manipulation-tracing-network-for","title":"ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features","date":"2019-06-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/point-to-point-video-generation","title":"Point-to-Point Video Generation","date":"2019-04-05","arxiv_id":"1904.02912","repositories_listed":3,"syntology":null},{"url":"/paper/uniworld-v1-high-resolution-semantic-encoders","title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation","date":"2025-06-03","arxiv_id":"2506.03147","repositories_listed":2,"syntology":null},{"url":"/paper/emerging-properties-in-unified-multimodal","title":"Emerging Properties in Unified Multimodal Pretraining","date":"2025-05-20","arxiv_id":"2505.14683","repositories_listed":2,"syntology":{"n":21,"n_ran":9,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/visual-text-processing-a-comprehensive-review","title":"Visual Text Processing: A Comprehensive Review and Unified Evaluation","date":"2025-04-30","arxiv_id":"2504.21682","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/fakeshield-explainable-image-forgery","title":"FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models","date":"2024-10-03","arxiv_id":"2410.02761","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":4}},{"url":"/paper/guiding-instruction-based-image-editing-via","title":"Guiding Instruction-based Image Editing via Multimodal Large Language Models","date":"2023-09-29","arxiv_id":"2309.17102","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":6}},{"url":"/paper/paint-by-example-exemplar-based-image-editing","title":"Paint by Example: Exemplar-based Image Editing with Diffusion Models","date":"2022-11-23","arxiv_id":"2211.13227","repositories_listed":2,"syntology":{"n":20,"n_ran":7,"n_unverified":13,"n_pointer_only":3}}],"syntology_records":22,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}