{"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/gaussianimage-1000-fps-image-representation","title":"GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting","arxiv_id":"2403.08551","date":"2024-03-13","proceeding":null,"authors":["Xinjie Zhang","Xingtong Ge","Tongda Xu","Dailan He","Yan Wang","Hongwei Qin","Guo Lu","Jing Geng","Jun Zhang"],"abstract":"Implicit neural representations (INRs) recently achieved great success in image representation and compression, offering high visual quality and fast rendering speeds with 10-1000 FPS, assuming sufficient GPU resources are available. However, this requirement often hinders their use on low-end devices with limited memory. In response, we propose a groundbreaking paradigm of image representation and compression by 2D Gaussian Splatting, named GaussianImage. We first introduce 2D Gaussian to represent the image, where each Gaussian has 8 parameters including position, covariance and color. Subsequently, we unveil a novel rendering algorithm based on accumulated summation. Remarkably, our method with a minimum of 3$\\times$ lower GPU memory usage and 5$\\times$ faster fitting time not only rivals INRs (e.g., WIRE, I-NGP) in representation performance, but also delivers a faster rendering speed of 1500-2000 FPS regardless of parameter size. Furthermore, we integrate existing vector quantization technique to build an image codec. Experimental results demonstrate that our codec attains rate-distortion performance comparable to compression-based INRs such as COIN and COIN++, while facilitating decoding speeds of approximately 2000 FPS. Additionally, preliminary proof of concept shows that our codec surpasses COIN and COIN++ in performance when using partial bits-back coding. Code is available at https://github.com/Xinjie-Q/GaussianImage.","url_abs":"https://arxiv.org/abs/2403.08551v5","url_pdf":"https://arxiv.org/pdf/2403.08551v5.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":"gaussianimage-1000-fps-image-representation","repo_url":"https://github.com/xinjie-q/gaussianimage","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.08551","atlas_url":"https://app.syntology.ai/?focus=2403.08551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08551"}},"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/xinjie-q/gaussianimage","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Xinjie-Q/GaussianImage","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7},"by_repo_kind":{"official":{"samples":7,"ran":7,"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":"a291c2776caf3a35","entry":"grad_scale","repo":"Xinjie-Q/GaussianImage","repo_kind":"official","path":"quantize.py","file_url":"https://github.com/Xinjie-Q/GaussianImage/blob/HEAD/quantize.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a291c2776caf3a35"}},{"code_sha256_prefix":"f5b2d15797cbfb2c","entry":"image_path_to_tensor","repo":"Xinjie-Q/GaussianImage","repo_kind":"official","path":"train_quantize.py","file_url":"https://github.com/Xinjie-Q/GaussianImage/blob/HEAD/train_quantize.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":"f5b2d15797cbfb2c"}},{"code_sha256_prefix":"98c39765afc54fc8","entry":"parse_args","repo":"Xinjie-Q/GaussianImage","repo_kind":"official","path":"train_quantize.py","file_url":"https://github.com/Xinjie-Q/GaussianImage/blob/HEAD/train_quantize.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":"98c39765afc54fc8"}},{"code_sha256_prefix":"63025c93e75efbe9","entry":"random_quat_tensor","repo":"Xinjie-Q/GaussianImage","repo_kind":"official","path":"gaussiansplatting_3d.py","file_url":"https://github.com/Xinjie-Q/GaussianImage/blob/HEAD/gaussiansplatting_3d.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"63025c93e75efbe9"}},{"code_sha256_prefix":"13a834379c89aaae","entry":"ste","repo":"Xinjie-Q/GaussianImage","repo_kind":"official","path":"quantize.py","file_url":"https://github.com/Xinjie-Q/GaussianImage/blob/HEAD/quantize.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"13a834379c89aaae"}},{"code_sha256_prefix":"e3cb74fbb6292ab5","entry":"strip_lowerdiag","repo":"Xinjie-Q/GaussianImage","repo_kind":"official","path":"utils.py","file_url":"https://github.com/Xinjie-Q/GaussianImage/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e3cb74fbb6292ab5"}},{"code_sha256_prefix":"11f871291d5ed58c","entry":"strip_symmetric","repo":"Xinjie-Q/GaussianImage","repo_kind":"official","path":"utils.py","file_url":"https://github.com/Xinjie-Q/GaussianImage/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"11f871291d5ed58c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}