{"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/compact-3d-scene-representation-via-self","title":"Compact 3D Scene Representation via Self-Organizing Gaussian Grids","arxiv_id":"2312.13299","date":"2023-12-19","proceeding":null,"authors":["Wieland Morgenstern","Florian Barthel","Anna Hilsmann","Peter Eisert"],"abstract":"3D Gaussian Splatting has recently emerged as a highly promising technique for modeling of static 3D scenes. In contrast to Neural Radiance Fields, it utilizes efficient rasterization allowing for very fast rendering at high-quality. However, the storage size is significantly higher, which hinders practical deployment, e.g. on resource constrained devices. In this paper, we introduce a compact scene representation organizing the parameters of 3D Gaussian Splatting (3DGS) into a 2D grid with local homogeneity, ensuring a drastic reduction in storage requirements without compromising visual quality during rendering. Central to our idea is the explicit exploitation of perceptual redundancies present in natural scenes. In essence, the inherent nature of a scene allows for numerous permutations of Gaussian parameters to equivalently represent it. To this end, we propose a novel highly parallel algorithm that regularly arranges the high-dimensional Gaussian parameters into a 2D grid while preserving their neighborhood structure. During training, we further enforce local smoothness between the sorted parameters in the grid. The uncompressed Gaussians use the same structure as 3DGS, ensuring a seamless integration with established renderers. Our method achieves a reduction factor of 17x to 42x in size for complex scenes with no increase in training time, marking a substantial leap forward in the domain of 3D scene distribution and consumption. Additional information can be found on our project page: https://fraunhoferhhi.github.io/Self-Organizing-Gaussians/","url_abs":"https://arxiv.org/abs/2312.13299v2","url_pdf":"https://arxiv.org/pdf/2312.13299v2.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":"compact-3d-scene-representation-via-self","repo_url":"https://github.com/fraunhoferhhi/Self-Organizing-Gaussians","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"compact-3d-scene-representation-via-self","repo_url":"https://github.com/facebookresearch/uco3d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"CC-BY-4.0"}}],"tasks":[{"task_slug":"3d-scene-reconstruction","task_name":"3D Scene Reconstruction"},{"task_slug":"3dgs","task_name":"3DGS"},{"task_slug":"data-compression","task_name":"Data Compression"},{"task_slug":"image-compression","task_name":"Image Compression"},{"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-deep-blending","task":"Novel View Synthesis","dataset":"Deep Blending","model":"Self-Organizing Gaussians","rank_in_archive_order":1,"of":1,"metrics":{"LPIPS":"0.258","PSNR":"30.35","SSIM":"0.909","Size (MB)":"16.8"},"uses_additional_data":false},{"leaderboard":"/sota/novel-view-synthesis-on-mip-nerf-360","task":"Novel View Synthesis","dataset":"Mip-NeRF 360","model":"Self-Organizing Gaussians","rank_in_archive_order":6,"of":14,"metrics":{"LPIPS":"0.22","PSNR":"27.64","SSIM":"0.864","Size (MB)":"40.3"},"uses_additional_data":false},{"leaderboard":"/sota/novel-view-synthesis-on-nerf","task":"Novel View Synthesis","dataset":"NeRF","model":"Self-Organizing Gaussians","rank_in_archive_order":2,"of":12,"metrics":{"LPIPS":"0.031","PSNR":"33.7","SSIM":"0.969","Size (MB)":"4.1"},"uses_additional_data":false},{"leaderboard":"/sota/novel-view-synthesis-on-tanks-and-temples","task":"Novel View Synthesis","dataset":"Tanks and Temples","model":"Self-Organizing Gaussians","rank_in_archive_order":4,"of":10,"metrics":{"LPIPS":"0.208","PSNR":"25.63","Size (MB)":"21.4"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2312.13299","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.13299"}},"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/fraunhoferhhi/Self-Organizing-Gaussians","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/uco3d","reach":{"status":"ok","spdx":"CC-BY-4.0"}}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"bb1a101c33c97d1e","entry":"normalize_img","repo":"fraunhoferhhi/Self-Organizing-Gaussians","repo_kind":"official","path":"compression/codec.py","file_url":"https://github.com/fraunhoferhhi/Self-Organizing-Gaussians/blob/HEAD/compression/codec.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"bb1a101c33c97d1e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}