{"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/spatialbot-precise-spatial-understanding-with","title":"SpatialBot: Precise Spatial Understanding with Vision Language Models","arxiv_id":"2406.13642","date":"2024-06-19","proceeding":null,"authors":["Wenxiao Cai","Iaroslav Ponomarenko","Jianhao Yuan","Xiaoqi Li","Wankou Yang","Hao Dong","Bo Zhao"],"abstract":"Vision Language Models (VLMs) have achieved impressive performance in 2D image understanding, however they are still struggling with spatial understanding which is the foundation of Embodied AI. In this paper, we propose SpatialBot for better spatial understanding by feeding both RGB and depth images. Additionally, we have constructed the SpatialQA dataset, which involves multi-level depth-related questions to train VLMs for depth understanding. Finally, we present SpatialBench to comprehensively evaluate VLMs' capabilities in spatial understanding at different levels. Extensive experiments on our spatial-understanding benchmark, general VLM benchmarks and Embodied AI tasks, demonstrate the remarkable improvements of SpatialBot trained on SpatialQA. The model, code and data are available at https://github.com/BAAI-DCAI/SpatialBot.","url_abs":"https://arxiv.org/abs/2406.13642v6","url_pdf":"https://arxiv.org/pdf/2406.13642v6.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":"spatialbot-precise-spatial-understanding-with","repo_url":"https://github.com/baai-dcai/spatialbot","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"spatial-reasoning","task_name":"Spatial Reasoning"}],"methods":[],"datasets_introduced":[{"slug":"spatialqa","name":"SpatialQA","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/spatial-reasoning-on-6-dof-spatialbench","task":"Spatial Reasoning","dataset":"6-DoF SpatialBench","model":"SpatialBot","rank_in_archive_order":4,"of":7,"metrics":{"Orientation-abs":"22.9","Orientation-rel":"39.6","Position-abs":"21.6","Position-rel":"50.9","Total":"32.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.13642","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13642"}},"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/baai-dcai/spatialbot","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran_violates":1,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"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":"42a46570620cd9fa","entry":"get_chunk","repo":"baai-dcai/spatialbot","repo_kind":"official","path":"bunny/eval/model_vqa.py","file_url":"https://github.com/baai-dcai/spatialbot/blob/HEAD/bunny/eval/model_vqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"code_sha256_prefix":"bae18947b56f2be1","entry":"is_none","repo":"baai-dcai/spatialbot","repo_kind":"official","path":"bunny/eval/model_vqa_mmbench.py","file_url":"https://github.com/baai-dcai/spatialbot/blob/HEAD/bunny/eval/model_vqa_mmbench.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bae18947b56f2be1"}},{"code_sha256_prefix":"076c252c52cbb161","entry":"split_list","repo":"baai-dcai/spatialbot","repo_kind":"official","path":"bunny/eval/model_vqa.py","file_url":"https://github.com/baai-dcai/spatialbot/blob/HEAD/bunny/eval/model_vqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"076c252c52cbb161"}},{"code_sha256_prefix":"e9b7271007c206d0","entry":"load_pretrained_model","repo":"baai-dcai/spatialbot","repo_kind":"official","path":"bunny/model/builder.py","file_url":"https://github.com/baai-dcai/spatialbot/blob/HEAD/bunny/model/builder.py","link_basis":"first_harvest_node","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":"e9b7271007c206d0"}},{"code_sha256_prefix":"ce93b7e192e1a8b7","entry":"load_yaml","repo":"baai-dcai/spatialbot","repo_kind":"official","path":"bunny/eval/eval_rtx.py","file_url":"https://github.com/baai-dcai/spatialbot/blob/HEAD/bunny/eval/eval_rtx.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":"ce93b7e192e1a8b7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}