{"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/density-guided-translator-boosts-synthetic-to","title":"Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Clouds","arxiv_id":"2403.18469","date":"2024-03-27","proceeding":"CVPR 2024 1","authors":["Zhimin Yuan","Wankang Zeng","Yanfei Su","Weiquan Liu","Ming Cheng","Yulan Guo","Cheng Wang"],"abstract":"3D synthetic-to-real unsupervised domain adaptive segmentation is crucial to annotating new domains. Self-training is a competitive approach for this task, but its performance is limited by different sensor sampling patterns (i.e., variations in point density) and incomplete training strategies. In this work, we propose a density-guided translator (DGT), which translates point density between domains, and integrates it into a two-stage self-training pipeline named DGT-ST. First, in contrast to existing works that simultaneously conduct data generation and feature/output alignment within unstable adversarial training, we employ the non-learnable DGT to bridge the domain gap at the input level. Second, to provide a well-initialized model for self-training, we propose a category-level adversarial network in stage one that utilizes the prototype to prevent negative transfer. Finally, by leveraging the designs above, a domain-mixed self-training method with source-aware consistency loss is proposed in stage two to narrow the domain gap further. Experiments on two synthetic-to-real segmentation tasks (SynLiDAR $\\rightarrow$ semanticKITTI and SynLiDAR $\\rightarrow$ semanticPOSS) demonstrate that DGT-ST outperforms state-of-the-art methods, achieving 9.4$\\%$ and 4.3$\\%$ mIoU improvements, respectively. Code is available at \\url{https://github.com/yuan-zm/DGT-ST}.","url_abs":"https://arxiv.org/abs/2403.18469v1","url_pdf":"https://arxiv.org/pdf/2403.18469v1.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":"density-guided-translator-boosts-synthetic-to","repo_url":"https://github.com/yuan-zm/dgt-st","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2403.18469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18469"}},"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/yuan-zm/DGT-ST","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"ran_fixture":2,"ran_violates":1,"ran_honours":1},"by_repo_kind":{"official":{"samples":9,"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":0,"samples":[{"code_sha256_prefix":"558d7686e41507e4","entry":"adjust_learning_rate","repo":"yuan-zm/DGT-ST","repo_kind":"official","path":"network/lr_adjust.py","file_url":"https://github.com/yuan-zm/DGT-ST/blob/HEAD/network/lr_adjust.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":"558d7686e41507e4"}},{"code_sha256_prefix":"6fb3d0b7c21a351d","entry":"change_Config_DEBUG","repo":"yuan-zm/DGT-ST","repo_kind":"official","path":"train_DGT_ST.py","file_url":"https://github.com/yuan-zm/DGT-ST/blob/HEAD/train_DGT_ST.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":"6fb3d0b7c21a351d"}},{"code_sha256_prefix":"dc27030cd2b7e51e","entry":"get_specific_beam_mask","repo":"yuan-zm/DGT-ST","repo_kind":"official","path":"dgt_utils/check_Chosed_beam_label_sp.py","file_url":"https://github.com/yuan-zm/DGT-ST/blob/HEAD/dgt_utils/check_Chosed_beam_label_sp.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":"dc27030cd2b7e51e"}},{"code_sha256_prefix":"d94639b28b2134ff","entry":"iou","repo":"yuan-zm/DGT-ST","repo_kind":"official","path":"network/lov_loss.py","file_url":"https://github.com/yuan-zm/DGT-ST/blob/HEAD/network/lov_loss.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d94639b28b2134ff"}},{"code_sha256_prefix":"1211530cd527bd0b","entry":"iou_binary","repo":"yuan-zm/DGT-ST","repo_kind":"official","path":"network/lov_loss.py","file_url":"https://github.com/yuan-zm/DGT-ST/blob/HEAD/network/lov_loss.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1211530cd527bd0b"}},{"code_sha256_prefix":"89cdbfea9999106d","entry":"load_label","repo":"yuan-zm/DGT-ST","repo_kind":"official","path":"eval_performance.py","file_url":"https://github.com/yuan-zm/DGT-ST/blob/HEAD/eval_performance.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":"89cdbfea9999106d"}},{"code_sha256_prefix":"e85b5d21dc5b8382","entry":"lovasz_grad","repo":"yuan-zm/DGT-ST","repo_kind":"official","path":"network/lov_loss.py","file_url":"https://github.com/yuan-zm/DGT-ST/blob/HEAD/network/lov_loss.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e85b5d21dc5b8382"}},{"code_sha256_prefix":"b3b7c1c716f4ca66","entry":"lr_poly","repo":"yuan-zm/DGT-ST","repo_kind":"official","path":"network/lr_adjust.py","file_url":"https://github.com/yuan-zm/DGT-ST/blob/HEAD/network/lr_adjust.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b3b7c1c716f4ca66"}},{"code_sha256_prefix":"aeba475616903383","entry":"lr_warmup","repo":"yuan-zm/DGT-ST","repo_kind":"official","path":"network/lr_adjust.py","file_url":"https://github.com/yuan-zm/DGT-ST/blob/HEAD/network/lr_adjust.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":"aeba475616903383"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}