{"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/contextgs-compact-3d-gaussian-splatting-with","title":"ContextGS: Compact 3D Gaussian Splatting with Anchor Level Context Model","arxiv_id":"2405.20721","date":"2024-05-31","proceeding":null,"authors":["YuFei Wang","Zhihao LI","Lanqing Guo","Wenhan Yang","Alex C. Kot","Bihan Wen"],"abstract":"Recently, 3D Gaussian Splatting (3DGS) has become a promising framework for novel view synthesis, offering fast rendering speeds and high fidelity. However, the large number of Gaussians and their associated attributes require effective compression techniques. Existing methods primarily compress neural Gaussians individually and independently, i.e., coding all the neural Gaussians at the same time, with little design for their interactions and spatial dependence. Inspired by the effectiveness of the context model in image compression, we propose the first autoregressive model at the anchor level for 3DGS compression in this work. We divide anchors into different levels and the anchors that are not coded yet can be predicted based on the already coded ones in all the coarser levels, leading to more accurate modeling and higher coding efficiency. To further improve the efficiency of entropy coding, e.g., to code the coarsest level with no already coded anchors, we propose to introduce a low-dimensional quantized feature as the hyperprior for each anchor, which can be effectively compressed. Our work pioneers the context model in the anchor level for 3DGS representation, yielding an impressive size reduction of over 100 times compared to vanilla 3DGS and 15 times compared to the most recent state-of-the-art work Scaffold-GS, while achieving comparable or even higher rendering quality.","url_abs":"https://arxiv.org/abs/2405.20721v1","url_pdf":"https://arxiv.org/pdf/2405.20721v1.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":"contextgs-compact-3d-gaussian-splatting-with","repo_url":"https://github.com/wyf0912/contextgs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"3dgs","task_name":"3DGS"},{"task_slug":"image-compression","task_name":"Image Compression"},{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2405.20721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20721"}},"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/wyf0912/contextgs","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":4,"ran_honours":2,"unverified":5},"by_repo_kind":{"official":{"samples":11,"ran":6,"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":11,"samples":[{"code_sha256_prefix":"7d4abf0a105f3eb4","entry":"find_divide_scale","repo":"wyf0912/contextgs","repo_kind":"official","path":"scene/gaussian_model.py","file_url":"https://github.com/wyf0912/contextgs/blob/HEAD/scene/gaussian_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7d4abf0a105f3eb4"}},{"code_sha256_prefix":"c56b7ef16f309a45","entry":"gaussian","repo":"wyf0912/contextgs","repo_kind":"official","path":"utils/loss_utils.py","file_url":"https://github.com/wyf0912/contextgs/blob/HEAD/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c56b7ef16f309a45"}},{"code_sha256_prefix":"ac0e42d6fbcfbbe6","entry":"l1_loss","repo":"wyf0912/contextgs","repo_kind":"official","path":"utils/loss_utils.py","file_url":"https://github.com/wyf0912/contextgs/blob/HEAD/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ac0e42d6fbcfbbe6"}},{"code_sha256_prefix":"8c3b0f873ba11813","entry":"l2_loss","repo":"wyf0912/contextgs","repo_kind":"official","path":"utils/loss_utils.py","file_url":"https://github.com/wyf0912/contextgs/blob/HEAD/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8c3b0f873ba11813"}},{"code_sha256_prefix":"1dab900b2adbe38e","entry":"normalize_activation","repo":"wyf0912/contextgs","repo_kind":"official","path":"lpipsPyTorch/modules/utils.py","file_url":"https://github.com/wyf0912/contextgs/blob/HEAD/lpipsPyTorch/modules/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1dab900b2adbe38e"}},{"code_sha256_prefix":"56858e04e6fdb2ff","entry":"read_next_bytes","repo":"wyf0912/contextgs","repo_kind":"official","path":"scene/colmap_loader.py","file_url":"https://github.com/wyf0912/contextgs/blob/HEAD/scene/colmap_loader.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"56858e04e6fdb2ff"}},{"code_sha256_prefix":"6378dadd2a7c1373","entry":"extract_context_feat","repo":"wyf0912/contextgs","repo_kind":"official","path":"scene/gaussian_model.py","file_url":"https://github.com/wyf0912/contextgs/blob/HEAD/scene/gaussian_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"6378dadd2a7c1373"}},{"code_sha256_prefix":"d7fc3fbb3e339c7a","entry":"get_network","repo":"wyf0912/contextgs","repo_kind":"official","path":"lpipsPyTorch/modules/networks.py","file_url":"https://github.com/wyf0912/contextgs/blob/HEAD/lpipsPyTorch/modules/networks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d7fc3fbb3e339c7a"}},{"code_sha256_prefix":"b06f27c08cf5d0ca","entry":"get_state_dict","repo":"wyf0912/contextgs","repo_kind":"official","path":"lpipsPyTorch/modules/utils.py","file_url":"https://github.com/wyf0912/contextgs/blob/HEAD/lpipsPyTorch/modules/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b06f27c08cf5d0ca"}},{"code_sha256_prefix":"6ce64cf0fbcd6bb1","entry":"qvec2rotmat","repo":"wyf0912/contextgs","repo_kind":"official","path":"scene/colmap_loader.py","file_url":"https://github.com/wyf0912/contextgs/blob/HEAD/scene/colmap_loader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6ce64cf0fbcd6bb1"}},{"code_sha256_prefix":"659bc4e7e63ed8f9","entry":"rotmat2qvec","repo":"wyf0912/contextgs","repo_kind":"official","path":"scene/colmap_loader.py","file_url":"https://github.com/wyf0912/contextgs/blob/HEAD/scene/colmap_loader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"659bc4e7e63ed8f9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}