{"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/3dmit-3d-multi-modal-instruction-tuning-for","title":"3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding","arxiv_id":"2401.03201","date":"2024-01-06","proceeding":null,"authors":["Zeju Li","Chao Zhang","Xiaoyan Wang","Ruilong Ren","Yifan Xu","Ruifei Ma","Xiangde Liu"],"abstract":"The remarkable potential of multi-modal large language models (MLLMs) in comprehending both vision and language information has been widely acknowledged. However, the scarcity of 3D scenes-language pairs in comparison to their 2D counterparts, coupled with the inadequacy of existing approaches in understanding of 3D scenes by LLMs, poses a significant challenge. In response, we collect and construct an extensive dataset comprising 75K instruction-response pairs tailored for 3D scenes. This dataset addresses tasks related to 3D VQA, 3D grounding, and 3D conversation. To further enhance the integration of 3D spatial information into LLMs, we introduce a novel and efficient prompt tuning paradigm, 3DMIT. This paradigm eliminates the alignment stage between 3D scenes and language and extends the instruction prompt with the 3D modality information including the entire scene and segmented objects. We evaluate the effectiveness of our method across diverse tasks in the 3D scene domain and find that our approach serves as a strategic means to enrich LLMs' comprehension of the 3D world. Our code is available at https://github.com/staymylove/3DMIT.","url_abs":"https://arxiv.org/abs/2401.03201v2","url_pdf":"https://arxiv.org/pdf/2401.03201v2.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":"3dmit-3d-multi-modal-instruction-tuning-for","repo_url":"https://github.com/staymylove/3DMIT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.03201","atlas_url":"https://app.syntology.ai/?focus=2401.03201","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03201"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/staymylove/3DMIT","reach":{"status":"ok"}}],"summary":{"ran":5,"unverified":5},"by_repo_kind":{"official":{"samples":10,"ran":5,"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":10,"samples":[{"code_sha256_prefix":"78e54f470017d052","entry":"is_number","repo":"staymylove/3DMIT","repo_kind":"official","path":"src/vg_eval_script.py","file_url":"https://github.com/staymylove/3DMIT/blob/HEAD/src/vg_eval_script.py","link_basis":"harvester_set","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":"78e54f470017d052"}},{"code_sha256_prefix":"c08da74e57caf534","entry":"parse_num","repo":"staymylove/3DMIT","repo_kind":"official","path":"src/vg_eval_script.py","file_url":"https://github.com/staymylove/3DMIT/blob/HEAD/src/vg_eval_script.py","link_basis":"harvester_set","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":"c08da74e57caf534"}},{"code_sha256_prefix":"4e436e13094b20cb","entry":"processDigitArticle","repo":"staymylove/3DMIT","repo_kind":"official","path":"src/cal_scanqa_score.py","file_url":"https://github.com/staymylove/3DMIT/blob/HEAD/src/cal_scanqa_score.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4e436e13094b20cb"}},{"code_sha256_prefix":"35e84a8da1d4f427","entry":"processPunctuation","repo":"staymylove/3DMIT","repo_kind":"official","path":"src/cal_scanqa_score.py","file_url":"https://github.com/staymylove/3DMIT/blob/HEAD/src/cal_scanqa_score.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"35e84a8da1d4f427"}},{"code_sha256_prefix":"95c185ff93ba4784","entry":"simple_ratio","repo":"staymylove/3DMIT","repo_kind":"official","path":"src/cal_scanqa_score.py","file_url":"https://github.com/staymylove/3DMIT/blob/HEAD/src/cal_scanqa_score.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":"95c185ff93ba4784"}},{"code_sha256_prefix":"d120d55fa22e5d4b","entry":"VQAvisionacc","repo":"staymylove/3DMIT","repo_kind":"official","path":"src/common_eval_3d.py","file_url":"https://github.com/staymylove/3DMIT/blob/HEAD/src/common_eval_3d.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":"d120d55fa22e5d4b"}},{"code_sha256_prefix":"b413b1b38ae500e9","entry":"inside_bbox_eval","repo":"staymylove/3DMIT","repo_kind":"official","path":"src/locating_eval.py","file_url":"https://github.com/staymylove/3DMIT/blob/HEAD/src/locating_eval.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":"b413b1b38ae500e9"}},{"code_sha256_prefix":"2061604e04a010b7","entry":"inside_human_bbox_eval","repo":"staymylove/3DMIT","repo_kind":"official","path":"src/locating_eval.py","file_url":"https://github.com/staymylove/3DMIT/blob/HEAD/src/locating_eval.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":"2061604e04a010b7"}},{"code_sha256_prefix":"4672066a5bb3bdad","entry":"parse_entity","repo":"staymylove/3DMIT","repo_kind":"official","path":"src/vg_eval_script.py","file_url":"https://github.com/staymylove/3DMIT/blob/HEAD/src/vg_eval_script.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":"4672066a5bb3bdad"}},{"code_sha256_prefix":"a3a876da2e698f5c","entry":"point_distance_eval","repo":"staymylove/3DMIT","repo_kind":"official","path":"src/locating_eval.py","file_url":"https://github.com/staymylove/3DMIT/blob/HEAD/src/locating_eval.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":"a3a876da2e698f5c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}