{"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/generating-visual-spatial-description-via","title":"Generating Visual Spatial Description via Holistic 3D Scene Understanding","arxiv_id":"2305.11768","date":"2023-05-19","proceeding":null,"authors":["Yu Zhao","Hao Fei","Wei Ji","Jianguo Wei","Meishan Zhang","Min Zhang","Tat-Seng Chua"],"abstract":"Visual spatial description (VSD) aims to generate texts that describe the spatial relations of the given objects within images. Existing VSD work merely models the 2D geometrical vision features, thus inevitably falling prey to the problem of skewed spatial understanding of target objects. In this work, we investigate the incorporation of 3D scene features for VSD. With an external 3D scene extractor, we obtain the 3D objects and scene features for input images, based on which we construct a target object-centered 3D spatial scene graph (Go3D-S2G), such that we model the spatial semantics of target objects within the holistic 3D scenes. Besides, we propose a scene subgraph selecting mechanism, sampling topologically-diverse subgraphs from Go3D-S2G, where the diverse local structure features are navigated to yield spatially-diversified text generation. Experimental results on two VSD datasets demonstrate that our framework outperforms the baselines significantly, especially improving on the cases with complex visual spatial relations. Meanwhile, our method can produce more spatially-diversified generation. Code is available at https://github.com/zhaoyucs/VSD.","url_abs":"https://arxiv.org/abs/2305.11768v2","url_pdf":"https://arxiv.org/pdf/2305.11768v2.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":"generating-visual-spatial-description-via","repo_url":"https://github.com/zhaoyucs/vsd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.11768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11768"}},"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/zhaoyucs/vsd","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/zhaoyucs/VSD","reach":{"status":"ok"}}],"summary":{"ran":2,"unverified":3},"by_repo_kind":{"official":{"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":5,"samples":[{"code_sha256_prefix":"8a6d1e6ed3c5539b","entry":"VLSeq2SeqLMOutput","repo":"zhaoyucs/VSD","repo_kind":"official","path":"VLModel/src/vrd_caption_model.py","file_url":"https://github.com/zhaoyucs/VSD/blob/HEAD/VLModel/src/vrd_caption_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8a6d1e6ed3c5539b"}},{"code_sha256_prefix":"d6fc067aa95356b6","entry":"VisualEmbedding","repo":"zhaoyucs/VSD","repo_kind":"official","path":"VLModel/src/vrd_caption_model.py","file_url":"https://github.com/zhaoyucs/VSD/blob/HEAD/VLModel/src/vrd_caption_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d6fc067aa95356b6"}},{"code_sha256_prefix":"28a9a789cd1a7c8e","entry":"JointEncoder","repo":"zhaoyucs/VSD","repo_kind":"official","path":"VLModel/src/vrd_caption_model.py","file_url":"https://github.com/zhaoyucs/VSD/blob/HEAD/VLModel/src/vrd_caption_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"28a9a789cd1a7c8e"}},{"code_sha256_prefix":"98f31b6be0744d86","entry":"VLT5","repo":"zhaoyucs/VSD","repo_kind":"official","path":"VLModel/src/vrd_caption_model.py","file_url":"https://github.com/zhaoyucs/VSD/blob/HEAD/VLModel/src/vrd_caption_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"98f31b6be0744d86"}},{"code_sha256_prefix":"663cd9cef7841064","entry":"VLT5VRDCaptionEx","repo":"zhaoyucs/VSD","repo_kind":"official","path":"VLModel/src/vrd_caption_model.py","file_url":"https://github.com/zhaoyucs/VSD/blob/HEAD/VLModel/src/vrd_caption_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"663cd9cef7841064"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}