{"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/language-driven-scene-synthesis-using-multi-1","title":"Language-driven Scene Synthesis using Multi-conditional Diffusion Model","arxiv_id":"2310.15948","date":"2023-10-24","proceeding":"NeurIPS 2023 11","authors":["An Vuong","Minh Nhat Vu","Toan Tien Nguyen","Baoru Huang","Dzung Nguyen","Thieu Vo","Anh Nguyen"],"abstract":"Scene synthesis is a challenging problem with several industrial applications. Recently, substantial efforts have been directed to synthesize the scene using human motions, room layouts, or spatial graphs as the input. However, few studies have addressed this problem from multiple modalities, especially combining text prompts. In this paper, we propose a language-driven scene synthesis task, which is a new task that integrates text prompts, human motion, and existing objects for scene synthesis. Unlike other single-condition synthesis tasks, our problem involves multiple conditions and requires a strategy for processing and encoding them into a unified space. To address the challenge, we present a multi-conditional diffusion model, which differs from the implicit unification approach of other diffusion literature by explicitly predicting the guiding points for the original data distribution. We demonstrate that our approach is theoretically supportive. The intensive experiment results illustrate that our method outperforms state-of-the-art benchmarks and enables natural scene editing applications. The source code and dataset can be accessed at https://lang-scene-synth.github.io/.","url_abs":"https://arxiv.org/abs/2310.15948v1","url_pdf":"https://arxiv.org/pdf/2310.15948v1.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":"language-driven-scene-synthesis-using-multi-1","repo_url":"https://github.com/andvg3/LSDM","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/indoor-scene-synthesis-on-pro-text","task":"Indoor Scene Synthesis","dataset":"PRO-teXt","model":"LSDM","rank_in_archive_order":1,"of":4,"metrics":{"CD":"0.5365","EMD":"0.5906","F1":"0.5160"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.15948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.15948"}},"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/andvg3/LSDM","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran_honours":2,"ran":2},"by_repo_kind":{"official":{"samples":6,"ran":6,"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":"cfd76fd0d89574a4","entry":"approx_standard_normal_cdf","repo":"andvg3/LSDM","repo_kind":"official","path":"diffusion/losses.py","file_url":"https://github.com/andvg3/LSDM/blob/HEAD/diffusion/losses.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cfd76fd0d89574a4"}},{"code_sha256_prefix":"f6b944f50d3f15ae","entry":"count_parameters","repo":"andvg3/LSDM","repo_kind":"official","path":"contact_former/posa_models.py","file_url":"https://github.com/andvg3/LSDM/blob/HEAD/contact_former/posa_models.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6b944f50d3f15ae"}},{"code_sha256_prefix":"cd33283d615fb3d7","entry":"discretized_gaussian_log_likelihood","repo":"andvg3/LSDM","repo_kind":"official","path":"diffusion/losses.py","file_url":"https://github.com/andvg3/LSDM/blob/HEAD/diffusion/losses.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cd33283d615fb3d7"}},{"code_sha256_prefix":"227e57257afaf7dd","entry":"get_norm_layer","repo":"andvg3/LSDM","repo_kind":"official","path":"contact_former/models_common.py","file_url":"https://github.com/andvg3/LSDM/blob/HEAD/contact_former/models_common.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"227e57257afaf7dd"}},{"code_sha256_prefix":"cf2798b666b231ca","entry":"normal_kl","repo":"andvg3/LSDM","repo_kind":"official","path":"diffusion/losses.py","file_url":"https://github.com/andvg3/LSDM/blob/HEAD/diffusion/losses.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cf2798b666b231ca"}},{"code_sha256_prefix":"d95508ee7d7034df","entry":"sample_in_bbox","repo":"andvg3/LSDM","repo_kind":"official","path":"get_next_obj_class.py","file_url":"https://github.com/andvg3/LSDM/blob/HEAD/get_next_obj_class.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d95508ee7d7034df"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}