{"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/cg-slam-efficient-dense-rgb-d-slam-in-a","title":"CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Field","arxiv_id":"2403.16095","date":"2024-03-24","proceeding":null,"authors":["Jiarui Hu","Xianhao Chen","Boyin Feng","Guanglin Li","Liangjing Yang","Hujun Bao","Guofeng Zhang","Zhaopeng Cui"],"abstract":"Recently neural radiance fields (NeRF) have been widely exploited as 3D representations for dense simultaneous localization and mapping (SLAM). Despite their notable successes in surface modeling and novel view synthesis, existing NeRF-based methods are hindered by their computationally intensive and time-consuming volume rendering pipeline. This paper presents an efficient dense RGB-D SLAM system, i.e., CG-SLAM, based on a novel uncertainty-aware 3D Gaussian field with high consistency and geometric stability. Through an in-depth analysis of Gaussian Splatting, we propose several techniques to construct a consistent and stable 3D Gaussian field suitable for tracking and mapping. Additionally, a novel depth uncertainty model is proposed to ensure the selection of valuable Gaussian primitives during optimization, thereby improving tracking efficiency and accuracy. Experiments on various datasets demonstrate that CG-SLAM achieves superior tracking and mapping performance with a notable tracking speed of up to 15 Hz. We will make our source code publicly available. Project page: https://zju3dv.github.io/cg-slam.","url_abs":"https://arxiv.org/abs/2403.16095v1","url_pdf":"https://arxiv.org/pdf/2403.16095v1.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":"cg-slam-efficient-dense-rgb-d-slam-in-a","repo_url":"https://github.com/hjr37/CG-SLAM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"nerf","task_name":"NeRF"},{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"},{"task_slug":"simultaneous-localization-and-mapping","task_name":"Simultaneous Localization and Mapping"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.16095","atlas_url":"https://app.syntology.ai/?focus=2403.16095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16095"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/hjr37/CG-SLAM","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran_honours":4,"ran":3,"unverified":6},"by_repo_kind":{"listed":{"samples":15,"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":"95abae1a2b93399d","entry":"PILtoTorch","repo":"hjr37/CG-SLAM","repo_kind":"listed","path":"gaussian_utils/general_utils.py","file_url":"https://github.com/hjr37/CG-SLAM/blob/HEAD/gaussian_utils/general_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"95abae1a2b93399d"}},{"code_sha256_prefix":"5a8b1e0eb5ec2789","entry":"RGB2SH","repo":"hjr37/CG-SLAM","repo_kind":"listed","path":"gaussian_utils/sh_utils.py","file_url":"https://github.com/hjr37/CG-SLAM/blob/HEAD/gaussian_utils/sh_utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5a8b1e0eb5ec2789"}},{"code_sha256_prefix":"d3d0dc69477aa06b","entry":"eval_sh","repo":"hjr37/CG-SLAM","repo_kind":"listed","path":"gaussian_utils/sh_utils.py","file_url":"https://github.com/hjr37/CG-SLAM/blob/HEAD/gaussian_utils/sh_utils.py","link_basis":"harvester_set","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":"d3d0dc69477aa06b"}},{"code_sha256_prefix":"c56b7ef16f309a45","entry":"gaussian","repo":"hjr37/CG-SLAM","repo_kind":"listed","path":"gaussian_utils/loss_utils.py","file_url":"https://github.com/hjr37/CG-SLAM/blob/HEAD/gaussian_utils/loss_utils.py","link_basis":"harvester_set","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":"c56b7ef16f309a45"}},{"code_sha256_prefix":"7325f65ee1e29543","entry":"get_expon_lr_func","repo":"hjr37/CG-SLAM","repo_kind":"listed","path":"gaussian_utils/general_utils.py","file_url":"https://github.com/hjr37/CG-SLAM/blob/HEAD/gaussian_utils/general_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7325f65ee1e29543"}},{"code_sha256_prefix":"b488da571728b636","entry":"inverse_sigmoid","repo":"hjr37/CG-SLAM","repo_kind":"listed","path":"gaussian_utils/general_utils.py","file_url":"https://github.com/hjr37/CG-SLAM/blob/HEAD/gaussian_utils/general_utils.py","link_basis":"harvester_set","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":"b488da571728b636"}},{"code_sha256_prefix":"ac0e42d6fbcfbbe6","entry":"l1_loss","repo":"hjr37/CG-SLAM","repo_kind":"listed","path":"gaussian_utils/loss_utils.py","file_url":"https://github.com/hjr37/CG-SLAM/blob/HEAD/gaussian_utils/loss_utils.py","link_basis":"harvester_set","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":"ac0e42d6fbcfbbe6"}},{"code_sha256_prefix":"8c3b0f873ba11813","entry":"l2_loss","repo":"hjr37/CG-SLAM","repo_kind":"listed","path":"gaussian_utils/loss_utils.py","file_url":"https://github.com/hjr37/CG-SLAM/blob/HEAD/gaussian_utils/loss_utils.py","link_basis":"harvester_set","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":"8c3b0f873ba11813"}},{"code_sha256_prefix":"c1e505eec9aae423","entry":"searchForMaxIteration","repo":"hjr37/CG-SLAM","repo_kind":"listed","path":"gaussian_utils/system_utils.py","file_url":"https://github.com/hjr37/CG-SLAM/blob/HEAD/gaussian_utils/system_utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c1e505eec9aae423"}},{"code_sha256_prefix":"55e5c8b4a3e6a864","entry":"SH2RGB","repo":"hjr37/CG-SLAM","repo_kind":"listed","path":"gaussian_utils/sh_utils.py","file_url":"https://github.com/hjr37/CG-SLAM/blob/HEAD/gaussian_utils/sh_utils.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":"55e5c8b4a3e6a864"}},{"code_sha256_prefix":"5b23bdfce9048dec","entry":"geom_transform_points","repo":"hjr37/CG-SLAM","repo_kind":"listed","path":"gaussian_utils/graphics_utils.py","file_url":"https://github.com/hjr37/CG-SLAM/blob/HEAD/gaussian_utils/graphics_utils.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":"5b23bdfce9048dec"}},{"code_sha256_prefix":"f304da20700d51cd","entry":"getWorld2View","repo":"hjr37/CG-SLAM","repo_kind":"listed","path":"gaussian_utils/graphics_utils.py","file_url":"https://github.com/hjr37/CG-SLAM/blob/HEAD/gaussian_utils/graphics_utils.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":"f304da20700d51cd"}},{"code_sha256_prefix":"6c394c1d0cb69da4","entry":"getWorld2View2","repo":"hjr37/CG-SLAM","repo_kind":"listed","path":"gaussian_utils/graphics_utils.py","file_url":"https://github.com/hjr37/CG-SLAM/blob/HEAD/gaussian_utils/graphics_utils.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":"6c394c1d0cb69da4"}},{"code_sha256_prefix":"6e14e874e7f40344","entry":"mse","repo":"hjr37/CG-SLAM","repo_kind":"listed","path":"gaussian_utils/image_utils.py","file_url":"https://github.com/hjr37/CG-SLAM/blob/HEAD/gaussian_utils/image_utils.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":"6e14e874e7f40344"}},{"code_sha256_prefix":"c10ce69ac48a8f3b","entry":"psnr","repo":"hjr37/CG-SLAM","repo_kind":"listed","path":"gaussian_utils/image_utils.py","file_url":"https://github.com/hjr37/CG-SLAM/blob/HEAD/gaussian_utils/image_utils.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":"c10ce69ac48a8f3b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}