{"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/eagles-efficient-accelerated-3d-gaussians","title":"EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS","arxiv_id":"2312.04564","date":"2023-12-07","proceeding":null,"authors":["Sharath Girish","Kamal Gupta","Abhinav Shrivastava"],"abstract":"Recently, 3D Gaussian splatting (3D-GS) has gained popularity in novel-view scene synthesis. It addresses the challenges of lengthy training times and slow rendering speeds associated with Neural Radiance Fields (NeRFs). Through rapid, differentiable rasterization of 3D Gaussians, 3D-GS achieves real-time rendering and accelerated training. They, however, demand substantial memory resources for both training and storage, as they require millions of Gaussians in their point cloud representation for each scene. We present a technique utilizing quantized embeddings to significantly reduce per-point memory storage requirements and a coarse-to-fine training strategy for a faster and more stable optimization of the Gaussian point clouds. Our approach develops a pruning stage which results in scene representations with fewer Gaussians, leading to faster training times and rendering speeds for real-time rendering of high resolution scenes. We reduce storage memory by more than an order of magnitude all while preserving the reconstruction quality. We validate the effectiveness of our approach on a variety of datasets and scenes preserving the visual quality while consuming 10-20x lesser memory and faster training/inference speed. Project page and code is available https://efficientgaussian.github.io","url_abs":"https://arxiv.org/abs/2312.04564v3","url_pdf":"https://arxiv.org/pdf/2312.04564v3.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":"eagles-efficient-accelerated-3d-gaussians","repo_url":"https://github.com/sharath-girish/efficientgaussian","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.04564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04564"}},"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/sharath-girish/efficientgaussian","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":6,"unverified":1},"by_repo_kind":{"official":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"862dad92da0b96a3","entry":"get_dft_matrix","repo":"sharath-girish/efficientgaussian","repo_kind":"official","path":"compress/decoders.py","file_url":"https://github.com/sharath-girish/efficientgaussian/blob/HEAD/compress/decoders.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"862dad92da0b96a3"}},{"code_sha256_prefix":"ac0e42d6fbcfbbe6","entry":"l1_loss","repo":"sharath-girish/efficientgaussian","repo_kind":"official","path":"utils/loss_utils.py","file_url":"https://github.com/sharath-girish/efficientgaussian/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":"sharath-girish/efficientgaussian","repo_kind":"official","path":"utils/loss_utils.py","file_url":"https://github.com/sharath-girish/efficientgaussian/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":"cdd00787894554b5","entry":"readImages","repo":"sharath-girish/efficientgaussian","repo_kind":"official","path":"metrics.py","file_url":"https://github.com/sharath-girish/efficientgaussian/blob/HEAD/metrics.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cdd00787894554b5"}},{"code_sha256_prefix":"fad41d008b6ba603","entry":"run","repo":"sharath-girish/efficientgaussian","repo_kind":"official","path":"render_360.py","file_url":"https://github.com/sharath-girish/efficientgaussian/blob/HEAD/render_360.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"fad41d008b6ba603"}},{"code_sha256_prefix":"f172024837446815","entry":"scaled_l1_loss","repo":"sharath-girish/efficientgaussian","repo_kind":"official","path":"utils/loss_utils.py","file_url":"https://github.com/sharath-girish/efficientgaussian/blob/HEAD/utils/loss_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f172024837446815"}},{"code_sha256_prefix":"0d6397b844204510","entry":"prepare_output_and_logger","repo":"sharath-girish/efficientgaussian","repo_kind":"official","path":"render_360.py","file_url":"https://github.com/sharath-girish/efficientgaussian/blob/HEAD/render_360.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":"0d6397b844204510"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}