{"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/ovo-open-vocabulary-occupancy","title":"OVO: Open-Vocabulary Occupancy","arxiv_id":"2305.16133","date":"2023-05-25","proceeding":null,"authors":["Zhiyu Tan","ZiChao Dong","Cheng Zhang","Weikun Zhang","Hang Ji","Hao Li"],"abstract":"Semantic occupancy prediction aims to infer dense geometry and semantics of surroundings for an autonomous agent to operate safely in the 3D environment. Existing occupancy prediction methods are almost entirely trained on human-annotated volumetric data. Although of high quality, the generation of such 3D annotations is laborious and costly, restricting them to a few specific object categories in the training dataset. To address this limitation, this paper proposes Open Vocabulary Occupancy (OVO), a novel approach that allows semantic occupancy prediction of arbitrary classes but without the need for 3D annotations during training. Keys to our approach are (1) knowledge distillation from a pre-trained 2D open-vocabulary segmentation model to the 3D occupancy network, and (2) pixel-voxel filtering for high-quality training data generation. The resulting framework is simple, compact, and compatible with most state-of-the-art semantic occupancy prediction models. On NYUv2 and SemanticKITTI datasets, OVO achieves competitive performance compared to supervised semantic occupancy prediction approaches. Furthermore, we conduct extensive analyses and ablation studies to offer insights into the design of the proposed framework. Our code is publicly available at https://github.com/dzcgaara/OVO.","url_abs":"https://arxiv.org/abs/2305.16133v2","url_pdf":"https://arxiv.org/pdf/2305.16133v2.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":"ovo-open-vocabulary-occupancy","repo_url":"https://github.com/dzcgaara/OVO","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.16133","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16133"}},"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/dzcgaara/OVO","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":8},"by_repo_kind":{"official":{"samples":11,"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":"5530781a69d17464","entry":"compute_super_CP_multilabel_loss","repo":"dzcgaara/OVO","repo_kind":"official","path":"ovo/loss/CRP_loss.py","file_url":"https://github.com/dzcgaara/OVO/blob/HEAD/ovo/loss/CRP_loss.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5530781a69d17464"}},{"code_sha256_prefix":"251f4945130ffbc3","entry":"get_iou","repo":"dzcgaara/OVO","repo_kind":"official","path":"ovo/loss/sscMetrics.py","file_url":"https://github.com/dzcgaara/OVO/blob/HEAD/ovo/loss/sscMetrics.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"251f4945130ffbc3"}},{"code_sha256_prefix":"d062b8e225df0d31","entry":"sem_scal_loss","repo":"dzcgaara/OVO","repo_kind":"official","path":"ovo/loss/ssc_loss.py","file_url":"https://github.com/dzcgaara/OVO/blob/HEAD/ovo/loss/ssc_loss.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d062b8e225df0d31"}},{"code_sha256_prefix":"033da7a511cc1166","entry":"KL_sep","repo":"dzcgaara/OVO","repo_kind":"official","path":"ovo/loss/ssc_loss.py","file_url":"https://github.com/dzcgaara/OVO/blob/HEAD/ovo/loss/ssc_loss.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"033da7a511cc1166"}},{"code_sha256_prefix":"690e5487ce07509a","entry":"batch_dice_loss","repo":"dzcgaara/OVO","repo_kind":"official","path":"ovo/loss/matcher.py","file_url":"https://github.com/dzcgaara/OVO/blob/HEAD/ovo/loss/matcher.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"690e5487ce07509a"}},{"code_sha256_prefix":"3dabeacae742104a","entry":"batch_sigmoid_focal_loss","repo":"dzcgaara/OVO","repo_kind":"official","path":"ovo/loss/matcher.py","file_url":"https://github.com/dzcgaara/OVO/blob/HEAD/ovo/loss/matcher.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3dabeacae742104a"}},{"code_sha256_prefix":"3219ddcaadf018ca","entry":"compute_mask_matching_loss","repo":"dzcgaara/OVO","repo_kind":"official","path":"ovo/loss/mask_matching_loss.py","file_url":"https://github.com/dzcgaara/OVO/blob/HEAD/ovo/loss/mask_matching_loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3219ddcaadf018ca"}},{"code_sha256_prefix":"3a8c2b6651437097","entry":"focal_loss","repo":"dzcgaara/OVO","repo_kind":"official","path":"ovo/loss/mask_matching_loss.py","file_url":"https://github.com/dzcgaara/OVO/blob/HEAD/ovo/loss/mask_matching_loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3a8c2b6651437097"}},{"code_sha256_prefix":"1cf8e8cd991e96bb","entry":"geo_scal_loss","repo":"dzcgaara/OVO","repo_kind":"official","path":"ovo/loss/ssc_loss.py","file_url":"https://github.com/dzcgaara/OVO/blob/HEAD/ovo/loss/ssc_loss.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1cf8e8cd991e96bb"}},{"code_sha256_prefix":"40d8d0dfd5686afe","entry":"get_accuracy","repo":"dzcgaara/OVO","repo_kind":"official","path":"ovo/loss/sscMetrics.py","file_url":"https://github.com/dzcgaara/OVO/blob/HEAD/ovo/loss/sscMetrics.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"40d8d0dfd5686afe"}},{"code_sha256_prefix":"9b0cb366167a3ed4","entry":"get_dice_loss","repo":"dzcgaara/OVO","repo_kind":"official","path":"ovo/loss/mask_matching_loss.py","file_url":"https://github.com/dzcgaara/OVO/blob/HEAD/ovo/loss/mask_matching_loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9b0cb366167a3ed4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}