{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/learning-hierarchical-semantic-image","title":"Learning Hierarchical Semantic Image Manipulation through Structured Representations","arxiv_id":"1808.07535","date":"2018-08-22","proceeding":"NeurIPS 2018 12","authors":["Seunghoon Hong","Xinchen Yan","Thomas Huang","Honglak Lee"],"abstract":"Understanding, reasoning, and manipulating semantic concepts of images have\nbeen a fundamental research problem for decades. Previous work mainly focused\non direct manipulation on natural image manifold through color strokes,\nkey-points, textures, and holes-to-fill. In this work, we present a novel\nhierarchical framework for semantic image manipulation. Key to our hierarchical\nframework is that we employ a structured semantic layout as our intermediate\nrepresentation for manipulation. Initialized with coarse-level bounding boxes,\nour structure generator first creates pixel-wise semantic layout capturing the\nobject shape, object-object interactions, and object-scene relations. Then our\nimage generator fills in the pixel-level textures guided by the semantic\nlayout. Such framework allows a user to manipulate images at object-level by\nadding, removing, and moving one bounding box at a time. Experimental\nevaluations demonstrate the advantages of the hierarchical manipulation\nframework over existing image generation and context hole-filing models, both\nqualitatively and quantitatively. Benefits of the hierarchical framework are\nfurther demonstrated in applications such as semantic object manipulation,\ninteractive image editing, and data-driven image manipulation.","url_abs":"http://arxiv.org/abs/1808.07535v2","url_pdf":"http://arxiv.org/pdf/1808.07535v2.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":"learning-hierarchical-semantic-image","repo_url":"https://github.com/xcyan/neurips18_hierchical_image_manipulation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-manipulation","task_name":"Image Manipulation"},{"task_slug":"object","task_name":"Object"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.07535","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.07535"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xcyan/neurips18_hierchical_image_manipulation","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"listed":{"samples":5,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"0e722c9ff0920473","entry":"conv3x3","repo":"xcyan/neurips18_hierchical_image_manipulation","repo_kind":"listed","path":"models/layer_util.py","file_url":"https://github.com/xcyan/neurips18_hierchical_image_manipulation/blob/HEAD/models/layer_util.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0e722c9ff0920473"}},{"code_sha256_prefix":"29bb0088c8c38ae4","entry":"get_norm_layer","repo":"xcyan/neurips18_hierchical_image_manipulation","repo_kind":"listed","path":"models/layer_util.py","file_url":"https://github.com/xcyan/neurips18_hierchical_image_manipulation/blob/HEAD/models/layer_util.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"29bb0088c8c38ae4"}},{"code_sha256_prefix":"e874376a7e1429d4","entry":"compute_gan_loss","repo":"xcyan/neurips18_hierchical_image_manipulation","repo_kind":"listed","path":"models/losses.py","file_url":"https://github.com/xcyan/neurips18_hierchical_image_manipulation/blob/HEAD/models/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e874376a7e1429d4"}},{"code_sha256_prefix":"8ab5f104f9317376","entry":"conv3x3","repo":"xcyan/neurips18_hierchical_image_manipulation","repo_kind":"listed","path":"models/Discriminator_NET.py","file_url":"https://github.com/xcyan/neurips18_hierchical_image_manipulation/blob/HEAD/models/Discriminator_NET.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ab5f104f9317376"}},{"code_sha256_prefix":"4d39f0d4ec405775","entry":"lr_control","repo":"xcyan/neurips18_hierchical_image_manipulation","repo_kind":"listed","path":"models/Discriminator_NET.py","file_url":"https://github.com/xcyan/neurips18_hierchical_image_manipulation/blob/HEAD/models/Discriminator_NET.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4d39f0d4ec405775"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}