{"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/muvo-a-multimodal-generative-world-model-for","title":"MUVO: A Multimodal World Model with Spatial Representations for Autonomous Driving","arxiv_id":"2311.11762","date":"2023-11-20","proceeding":null,"authors":["Daniel Bogdoll","Yitian Yang","Tim Joseph","J. Marius Zöllner"],"abstract":"Learning unsupervised world models for autonomous driving has the potential to improve the reasoning capabilities of today's systems dramatically. However, most work neglects the physical attributes of the world and focuses on sensor data alone. We propose MUVO, a MUltimodal World Model with spatial VOxel representations, to address this challenge. We utilize raw camera and lidar data to learn a sensor-agnostic geometric representation of the world. We demonstrate multimodal future predictions and show that our spatial representation improves the prediction quality of both camera images and lidar point clouds.","url_abs":"https://arxiv.org/abs/2311.11762v3","url_pdf":"https://arxiv.org/pdf/2311.11762v3.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":"muvo-a-multimodal-generative-world-model-for","repo_url":"https://github.com/fzi-forschungszentrum-informatik/muvo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.11762","atlas_url":"https://app.syntology.ai/?focus=2311.11762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.11762"}},"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/fzi-forschungszentrum-informatik/muvo","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":4,"ran":5,"unverified":2},"by_repo_kind":{"official":{"samples":11,"ran":9,"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":11,"samples":[{"code_sha256_prefix":"8945de8524a23486","entry":"cumsum_trick","repo":"fzi-forschungszentrum-informatik/muvo","repo_kind":"official","path":"muvo/models/frustum_pooling.py","file_url":"https://github.com/fzi-forschungszentrum-informatik/muvo/blob/HEAD/muvo/models/frustum_pooling.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8945de8524a23486"}},{"code_sha256_prefix":"a352d14edc8a0764","entry":"functional_crop","repo":"fzi-forschungszentrum-informatik/muvo","repo_kind":"official","path":"muvo/models/preprocess.py","file_url":"https://github.com/fzi-forschungszentrum-informatik/muvo/blob/HEAD/muvo/models/preprocess.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":"a352d14edc8a0764"}},{"code_sha256_prefix":"2db9b3af8fbc9ab1","entry":"functional_resize","repo":"fzi-forschungszentrum-informatik/muvo","repo_kind":"official","path":"muvo/models/preprocess.py","file_url":"https://github.com/fzi-forschungszentrum-informatik/muvo/blob/HEAD/muvo/models/preprocess.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":"2db9b3af8fbc9ab1"}},{"code_sha256_prefix":"f15eb537a2a1deb9","entry":"gen_dx_bx","repo":"fzi-forschungszentrum-informatik/muvo","repo_kind":"official","path":"muvo/models/frustum_pooling.py","file_url":"https://github.com/fzi-forschungszentrum-informatik/muvo/blob/HEAD/muvo/models/frustum_pooling.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":"f15eb537a2a1deb9"}},{"code_sha256_prefix":"ea594d78df24aacd","entry":"get_iou","repo":"fzi-forschungszentrum-informatik/muvo","repo_kind":"official","path":"muvo/metrics.py","file_url":"https://github.com/fzi-forschungszentrum-informatik/muvo/blob/HEAD/muvo/metrics.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":"ea594d78df24aacd"}},{"code_sha256_prefix":"45e55a1e5f285f6f","entry":"pack_sequence_dim","repo":"fzi-forschungszentrum-informatik/muvo","repo_kind":"official","path":"muvo/utils/network_utils.py","file_url":"https://github.com/fzi-forschungszentrum-informatik/muvo/blob/HEAD/muvo/utils/network_utils.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"45e55a1e5f285f6f"}},{"code_sha256_prefix":"fbe923f7c196da7e","entry":"quick_cumsum","repo":"fzi-forschungszentrum-informatik/muvo","repo_kind":"official","path":"muvo/models/frustum_pooling.py","file_url":"https://github.com/fzi-forschungszentrum-informatik/muvo/blob/HEAD/muvo/models/frustum_pooling.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fbe923f7c196da7e"}},{"code_sha256_prefix":"a9bb7e423749f858","entry":"remove_last","repo":"fzi-forschungszentrum-informatik/muvo","repo_kind":"official","path":"muvo/utils/network_utils.py","file_url":"https://github.com/fzi-forschungszentrum-informatik/muvo/blob/HEAD/muvo/utils/network_utils.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":"a9bb7e423749f858"}},{"code_sha256_prefix":"c6d11c36bcc8cd1c","entry":"remove_past","repo":"fzi-forschungszentrum-informatik/muvo","repo_kind":"official","path":"muvo/utils/network_utils.py","file_url":"https://github.com/fzi-forschungszentrum-informatik/muvo/blob/HEAD/muvo/utils/network_utils.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c6d11c36bcc8cd1c"}},{"code_sha256_prefix":"1158a775edf4a8b4","entry":"functional_resize_batch","repo":"fzi-forschungszentrum-informatik/muvo","repo_kind":"official","path":"muvo/models/preprocess.py","file_url":"https://github.com/fzi-forschungszentrum-informatik/muvo/blob/HEAD/muvo/models/preprocess.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":"1158a775edf4a8b4"}},{"code_sha256_prefix":"019b2c84dd83f0bd","entry":"get_accuracy","repo":"fzi-forschungszentrum-informatik/muvo","repo_kind":"official","path":"muvo/metrics.py","file_url":"https://github.com/fzi-forschungszentrum-informatik/muvo/blob/HEAD/muvo/metrics.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":"019b2c84dd83f0bd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}