{"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/arbitrary-scale-point-cloud-upsampling-by","title":"Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning","arxiv_id":"2403.05117","date":"2024-03-08","proceeding":null,"authors":["Hang Du","Xuejun Yan","Jingjing Wang","Di Xie","ShiLiang Pu"],"abstract":"Recently, arbitrary-scale point cloud upsampling mechanism became increasingly popular due to its efficiency and convenience for practical applications. To achieve this, most previous approaches formulate it as a problem of surface approximation and employ point-based networks to learn surface representations. However, learning surfaces from sparse point clouds is more challenging, and thus they often suffer from the low-fidelity geometry approximation. To address it, we propose an arbitrary-scale Point cloud Upsampling framework using Voxel-based Network (\\textbf{PU-VoxelNet}). Thanks to the completeness and regularity inherited from the voxel representation, voxel-based networks are capable of providing predefined grid space to approximate 3D surface, and an arbitrary number of points can be reconstructed according to the predicted density distribution within each grid cell. However, we investigate the inaccurate grid sampling caused by imprecise density predictions. To address this issue, a density-guided grid resampling method is developed to generate high-fidelity points while effectively avoiding sampling outliers. Further, to improve the fine-grained details, we present an auxiliary training supervision to enforce the latent geometric consistency among local surface patches. Extensive experiments indicate the proposed approach outperforms the state-of-the-art approaches not only in terms of fixed upsampling rates but also for arbitrary-scale upsampling.","url_abs":"https://arxiv.org/abs/2403.05117v1","url_pdf":"https://arxiv.org/pdf/2403.05117v1.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":"arbitrary-scale-point-cloud-upsampling-by","repo_url":"https://github.com/hikvision-research/3dvision","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"point-cloud-upsampling","task_name":"point cloud upsampling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.05117","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05117"}},"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/hikvision-research/3DVision","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":4,"ran":8,"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":14,"ran":14,"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":"67196e77547ae476","entry":"fit_Wjet","repo":"hikvision-research/3DVision","repo_kind":"official","path":"Normal-Estimation/ZTEE/models/AdaFit_ms_HG.py","file_url":"https://github.com/hikvision-research/3DVision/blob/HEAD/Normal-Estimation/ZTEE/models/AdaFit_ms_HG.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"67196e77547ae476"}},{"code_sha256_prefix":"889d52e22e118dee","entry":"get_pts","repo":"hikvision-research/3DVision","repo_kind":"official","path":"PointCompletion/FBNet/vis_utils.py","file_url":"https://github.com/hikvision-research/3DVision/blob/HEAD/PointCompletion/FBNet/vis_utils.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":"889d52e22e118dee"}},{"code_sha256_prefix":"c779aa8bd2f53710","entry":"knn","repo":"hikvision-research/3DVision","repo_kind":"official","path":"Normal-Estimation/ZTEE/models/AdaFit_ms_HG.py","file_url":"https://github.com/hikvision-research/3DVision/blob/HEAD/Normal-Estimation/ZTEE/models/AdaFit_ms_HG.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c779aa8bd2f53710"}},{"code_sha256_prefix":"7f8230b3084eaaab","entry":"l2_norm","repo":"hikvision-research/3DVision","repo_kind":"official","path":"Normal-Estimation/ZTEE/evaluate.py","file_url":"https://github.com/hikvision-research/3DVision/blob/HEAD/Normal-Estimation/ZTEE/evaluate.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7f8230b3084eaaab"}},{"code_sha256_prefix":"49e600ee63c3fa98","entry":"load_shape","repo":"hikvision-research/3DVision","repo_kind":"official","path":"Normal-Estimation/ZTEE/dataset.py","file_url":"https://github.com/hikvision-research/3DVision/blob/HEAD/Normal-Estimation/ZTEE/dataset.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":"49e600ee63c3fa98"}},{"code_sha256_prefix":"1a8e2c70d1e5c35a","entry":"load_shape","repo":"hikvision-research/3DVision","repo_kind":"official","path":"Normal-Estimation/ZTEE/utils/pcpnet_dataset.py","file_url":"https://github.com/hikvision-research/3DVision/blob/HEAD/Normal-Estimation/ZTEE/utils/pcpnet_dataset.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":"1a8e2c70d1e5c35a"}},{"code_sha256_prefix":"1825be6622bab350","entry":"query_knn","repo":"hikvision-research/3DVision","repo_kind":"official","path":"PointUpsampling/PUCRN/network/PUCRN.py","file_url":"https://github.com/hikvision-research/3DVision/blob/HEAD/PointUpsampling/PUCRN/network/PUCRN.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1825be6622bab350"}},{"code_sha256_prefix":"cf0046cf40271347","entry":"query_knn","repo":"hikvision-research/3DVision","repo_kind":"official","path":"PointCompletion/FBNet/FBNet.py","file_url":"https://github.com/hikvision-research/3DVision/blob/HEAD/PointCompletion/FBNet/FBNet.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":"cf0046cf40271347"}},{"code_sha256_prefix":"d20869ed02f749dc","entry":"query_knn","repo":"hikvision-research/3DVision","repo_kind":"official","path":"Normal-Estimation/ZTEE/models/utils.py","file_url":"https://github.com/hikvision-research/3DVision/blob/HEAD/Normal-Estimation/ZTEE/models/utils.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":"d20869ed02f749dc"}},{"code_sha256_prefix":"5524dd810616aa27","entry":"query_knn_point","repo":"hikvision-research/3DVision","repo_kind":"official","path":"Normal-Estimation/ZTEE/models/utils.py","file_url":"https://github.com/hikvision-research/3DVision/blob/HEAD/Normal-Estimation/ZTEE/models/utils.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":"5524dd810616aa27"}},{"code_sha256_prefix":"bba815f3d353d9b4","entry":"query_knn_point","repo":"hikvision-research/3DVision","repo_kind":"official","path":"PointUpsampling/PUCRN/network/PUCRN.py","file_url":"https://github.com/hikvision-research/3DVision/blob/HEAD/PointUpsampling/PUCRN/network/PUCRN.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":"bba815f3d353d9b4"}},{"code_sha256_prefix":"bc24576fff5169fd","entry":"solve_linear_system","repo":"hikvision-research/3DVision","repo_kind":"official","path":"Normal-Estimation/ZTEE/models/AdaFit_ms_HG.py","file_url":"https://github.com/hikvision-research/3DVision/blob/HEAD/Normal-Estimation/ZTEE/models/AdaFit_ms_HG.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bc24576fff5169fd"}},{"code_sha256_prefix":"580dee6761649b29","entry":"square_distance","repo":"hikvision-research/3DVision","repo_kind":"official","path":"Normal-Estimation/ZTEE/models/utils.py","file_url":"https://github.com/hikvision-research/3DVision/blob/HEAD/Normal-Estimation/ZTEE/models/utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"580dee6761649b29"}},{"code_sha256_prefix":"5dca87aba0a5901c","entry":"square_distance","repo":"hikvision-research/3DVision","repo_kind":"official","path":"PointCompletion/FBNet/FBNet.py","file_url":"https://github.com/hikvision-research/3DVision/blob/HEAD/PointCompletion/FBNet/FBNet.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":"5dca87aba0a5901c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}