{"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/monocular-occupancy-prediction-for-scalable","title":"Monocular Occupancy Prediction for Scalable Indoor Scenes","arxiv_id":"2407.11730","date":"2024-07-16","proceeding":null,"authors":["Hongxiao Yu","Yuqi Wang","Yuntao Chen","Zhaoxiang Zhang"],"abstract":"Camera-based 3D occupancy prediction has recently garnered increasing attention in outdoor driving scenes. However, research in indoor scenes remains relatively unexplored. The core differences in indoor scenes lie in the complexity of scene scale and the variance in object size. In this paper, we propose a novel method, named ISO, for predicting indoor scene occupancy using monocular images. ISO harnesses the advantages of a pretrained depth model to achieve accurate depth predictions. Furthermore, we introduce the Dual Feature Line of Sight Projection (D-FLoSP) module within ISO, which enhances the learning of 3D voxel features. To foster further research in this domain, we introduce Occ-ScanNet, a large-scale occupancy benchmark for indoor scenes. With a dataset size 40 times larger than the NYUv2 dataset, it facilitates future scalable research in indoor scene analysis. Experimental results on both NYUv2 and Occ-ScanNet demonstrate that our method achieves state-of-the-art performance. The dataset and code are made publicly at https://github.com/hongxiaoy/ISO.git.","url_abs":"https://arxiv.org/abs/2407.11730v2","url_pdf":"https://arxiv.org/pdf/2407.11730v2.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":"monocular-occupancy-prediction-for-scalable","repo_url":"https://github.com/hongxiaoy/ISO","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-semantic-scene-completion-from-a-single","task_name":"3D Semantic Scene Completion from a single RGB image"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[{"slug":"occscannet","name":"OccScanNet","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-scene-completion-from-a-single","task":"3D Semantic Scene Completion from a single RGB image","dataset":"NYUv2","model":"ISO","rank_in_archive_order":1,"of":6,"metrics":{"mIoU":"31.25"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.11730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11730"}},"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":"deterministic:regex_extraction","url":"https://github.com/hongxiaoy/ISO","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"unverified":5},"by_repo_kind":{"official":{"samples":9,"ran":4,"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":"488de7dc43489343","entry":"compute_super_CP_multilabel_loss","repo":"hongxiaoy/ISO","repo_kind":"official","path":"iso/loss/CRP_loss.py","file_url":"https://github.com/hongxiaoy/ISO/blob/HEAD/iso/loss/CRP_loss.py","link_basis":"first_harvest_node","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":"488de7dc43489343"}},{"code_sha256_prefix":"a99e276e1b9e7530","entry":"get_depth_index","repo":"hongxiaoy/ISO","repo_kind":"official","path":"iso/models/modules.py","file_url":"https://github.com/hongxiaoy/ISO/blob/HEAD/iso/models/modules.py","link_basis":"first_harvest_node","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":"a99e276e1b9e7530"}},{"code_sha256_prefix":"251f4945130ffbc3","entry":"get_iou","repo":"hongxiaoy/ISO","repo_kind":"official","path":"iso/loss/sscMetrics.py","file_url":"https://github.com/hongxiaoy/ISO/blob/HEAD/iso/loss/sscMetrics.py","link_basis":"first_harvest_node","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":"hongxiaoy/ISO","repo_kind":"official","path":"iso/loss/ssc_loss.py","file_url":"https://github.com/hongxiaoy/ISO/blob/HEAD/iso/loss/ssc_loss.py","link_basis":"first_harvest_node","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":"hongxiaoy/ISO","repo_kind":"official","path":"iso/loss/ssc_loss.py","file_url":"https://github.com/hongxiaoy/ISO/blob/HEAD/iso/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":"cee458c6cb15d593","entry":"bin_depths","repo":"hongxiaoy/ISO","repo_kind":"official","path":"iso/models/modules.py","file_url":"https://github.com/hongxiaoy/ISO/blob/HEAD/iso/models/modules.py","link_basis":"harvester_set","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":"cee458c6cb15d593"}},{"code_sha256_prefix":"1cf8e8cd991e96bb","entry":"geo_scal_loss","repo":"hongxiaoy/ISO","repo_kind":"official","path":"iso/loss/ssc_loss.py","file_url":"https://github.com/hongxiaoy/ISO/blob/HEAD/iso/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":"hongxiaoy/ISO","repo_kind":"official","path":"iso/loss/sscMetrics.py","file_url":"https://github.com/hongxiaoy/ISO/blob/HEAD/iso/loss/sscMetrics.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":"40d8d0dfd5686afe"}},{"code_sha256_prefix":"e3e9b85784ce26ed","entry":"sample_grid_feature","repo":"hongxiaoy/ISO","repo_kind":"official","path":"iso/models/modules.py","file_url":"https://github.com/hongxiaoy/ISO/blob/HEAD/iso/models/modules.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":"e3e9b85784ce26ed"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}