{"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/diffusionpcr-diffusion-models-for-robust","title":"Adaptive Multi-step Refinement Network for Robust Point Cloud Registration","arxiv_id":"2312.03053","date":"2023-12-05","proceeding":null,"authors":["Zhi Chen","Yufan Ren","Tong Zhang","Zheng Dang","Wenbing Tao","Sabine Süsstrunk","Mathieu Salzmann"],"abstract":"Point Cloud Registration (PCR) estimates the relative rigid transformation between two point clouds of the same scene. Despite significant progress with learning-based approaches, existing methods still face challenges when the overlapping region between the two point clouds is small. In this paper, we propose an adaptive multi-step refinement network that refines the registration quality at each step by leveraging the information from the preceding step. To achieve this, we introduce a training procedure and a refinement network. Firstly, to adapt the network to the current step, we utilize a generalized one-way attention mechanism, which prioritizes the last step's estimated overlapping region, and we condition the network on step indices. Secondly, instead of training the network to map either random transformations or a fixed pre-trained model's estimations to the ground truth, we train it on transformations with varying registration qualities, ranging from accurate to inaccurate, thereby enhancing the network's adaptiveness and robustness. Despite its conceptual simplicity, our method achieves state-of-the-art performance on both the 3DMatch/3DLoMatch and KITTI benchmarks. Notably, on 3DLoMatch, our method reaches 80.4% recall rate, with an absolute improvement of 1.2%.","url_abs":"https://arxiv.org/abs/2312.03053v2","url_pdf":"https://arxiv.org/pdf/2312.03053v2.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":"diffusionpcr-diffusion-models-for-robust","repo_url":"https://github.com/zhichen902/amr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"point-cloud-registration","task_name":"Point Cloud Registration"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.03053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03053"}},"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/zhichen902/amr","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"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":"17d584be4ed0edfd","entry":"get_soft_mask","repo":"zhichen902/amr","repo_kind":"official","path":"experiments/geotransformer.3dmatch.stage4.gse.k3.max.oacl.stage2.sinkhorn/model.py","file_url":"https://github.com/zhichen902/amr/blob/HEAD/experiments/geotransformer.3dmatch.stage4.gse.k3.max.oacl.stage2.sinkhorn/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"17d584be4ed0edfd"}},{"code_sha256_prefix":"7e4df6976748d024","entry":"inject_default_parser","repo":"zhichen902/amr","repo_kind":"official","path":"geotransformer/engine/base_tester.py","file_url":"https://github.com/zhichen902/amr/blob/HEAD/geotransformer/engine/base_tester.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7e4df6976748d024"}},{"code_sha256_prefix":"e59b3354578c7f3c","entry":"inject_default_parser","repo":"zhichen902/amr","repo_kind":"official","path":"geotransformer/engine/base_trainer.py","file_url":"https://github.com/zhichen902/amr/blob/HEAD/geotransformer/engine/base_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e59b3354578c7f3c"}},{"code_sha256_prefix":"a05a14e6dbbb0375","entry":"prepare_one_data","repo":"zhichen902/amr","repo_kind":"official","path":"geotransformer/engine/epoch_based_trainer.py","file_url":"https://github.com/zhichen902/amr/blob/HEAD/geotransformer/engine/epoch_based_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a05a14e6dbbb0375"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}