{"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/compact3d-compressing-gaussian-splat-radiance","title":"CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization","arxiv_id":"2311.18159","date":"2023-11-30","proceeding":null,"authors":["KL Navaneet","Kossar Pourahmadi Meibodi","Soroush Abbasi Koohpayegani","Hamed Pirsiavash"],"abstract":"3D Gaussian Splatting (3DGS) is a new method for modeling and rendering 3D radiance fields that achieves much faster learning and rendering time compared to SOTA NeRF methods. However, it comes with a drawback in the much larger storage demand compared to NeRF methods since it needs to store the parameters for several 3D Gaussians. We notice that many Gaussians may share similar parameters, so we introduce a simple vector quantization method based on K-means to quantize the Gaussian parameters while optimizing them. Then, we store the small codebook along with the index of the code for each Gaussian. We compress the indices further by sorting them and using a method similar to run-length encoding. Moreover, we use a simple regularizer to encourage zero opacity (invisible Gaussians) to reduce the storage and rendering time by a large factor through reducing the number of Gaussians. We do extensive experiments on standard benchmarks as well as an existing 3D dataset that is an order of magnitude larger than the standard benchmarks used in this field. We show that our simple yet effective method can reduce the storage cost for 3DGS by 40 to 50x and rendering time by 2 to 3x with a very small drop in the quality of rendered images.","url_abs":"https://arxiv.org/abs/2311.18159v3","url_pdf":"https://arxiv.org/pdf/2311.18159v3.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":"compact3d-compressing-gaussian-splat-radiance","repo_url":"https://github.com/ucdvision/compact3d","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3dgs","task_name":"3DGS"},{"task_slug":"nerf","task_name":"NeRF"},{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/novel-view-synthesis-on-mip-nerf-360","task":"Novel View Synthesis","dataset":"Mip-NeRF 360","model":"Compact3D","rank_in_archive_order":7,"of":14,"metrics":{"LPIPS":"0.228","PSNR":"27.16","SSIM":"0.808"},"uses_additional_data":false},{"leaderboard":"/sota/novel-view-synthesis-on-tanks-and-temples","task":"Novel View Synthesis","dataset":"Tanks and Temples","model":"Compact3D","rank_in_archive_order":6,"of":10,"metrics":{"LPIPS":"0.188","PSNR":"23.47","SSIM":"0.840"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.18159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18159"}},"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/ucdvision/compact3d","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"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":"869a1fa6e88ff1fa","entry":"dec2binary","repo":"ucdvision/compact3d","repo_kind":"official","path":"train_kmeans.py","file_url":"https://github.com/ucdvision/compact3d/blob/HEAD/train_kmeans.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":"869a1fa6e88ff1fa"}},{"code_sha256_prefix":"74c6a993a0948239","entry":"prepare_output_and_logger","repo":"ucdvision/compact3d","repo_kind":"official","path":"train_kmeans.py","file_url":"https://github.com/ucdvision/compact3d/blob/HEAD/train_kmeans.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"74c6a993a0948239"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}