{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/deep-image-harmonization","title":"Deep Image Harmonization","arxiv_id":"1703.00069","date":"2017-02-28","proceeding":"CVPR 2017 7","authors":["Yi-Hsuan Tsai","Xiaohui Shen","Zhe Lin","Kalyan Sunkavalli","Xin Lu","Ming-Hsuan Yang"],"abstract":"Compositing is one of the most common operations in photo editing. To\ngenerate realistic composites, the appearances of foreground and background\nneed to be adjusted to make them compatible. Previous approaches to harmonize\ncomposites have focused on learning statistical relationships between\nhand-crafted appearance features of the foreground and background, which is\nunreliable especially when the contents in the two layers are vastly different.\nIn this work, we propose an end-to-end deep convolutional neural network for\nimage harmonization, which can capture both the context and semantic\ninformation of the composite images during harmonization. We also introduce an\nefficient way to collect large-scale and high-quality training data that can\nfacilitate the training process. Experiments on the synthesized dataset and\nreal composite images show that the proposed network outperforms previous\nstate-of-the-art methods.","url_abs":"http://arxiv.org/abs/1703.00069v1","url_pdf":"http://arxiv.org/pdf/1703.00069v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-image-harmonization","repo_url":"https://github.com/wasidennis/DeepHarmonization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":{"status":"ok"}},{"paper_slug":"deep-image-harmonization","repo_url":"https://github.com/isaaccorley/deep-image-harmonization-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-harmonization","task_name":"Image Harmonization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1703.00069","atlas_url":"https://app.syntology.ai/?focus=1703.00069","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1703.00069"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1703.00069\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1703.00069"},"call":"get_concepts_for_paper(arxiv_id=\"1703.00069\")"}],"by_repo":[{"repo":"wasidennis/DeepHarmonization","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"isaaccorley/deep-image-harmonization-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"bf5743051dfc81c07e442d71ff3e4a4c1715dec27d04558875a850504c3b3c88","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}