{"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/fast-generalizable-gaussian-splatting","title":"MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo","arxiv_id":"2405.12218","date":"2024-05-20","proceeding":null,"authors":["Tianqi Liu","Guangcong Wang","Shoukang Hu","Liao Shen","Xinyi Ye","Yuhang Zang","Zhiguo Cao","Wei Li","Ziwei Liu"],"abstract":"We present MVSGaussian, a new generalizable 3D Gaussian representation approach derived from Multi-View Stereo (MVS) that can efficiently reconstruct unseen scenes. Specifically, 1) we leverage MVS to encode geometry-aware Gaussian representations and decode them into Gaussian parameters. 2) To further enhance performance, we propose a hybrid Gaussian rendering that integrates an efficient volume rendering design for novel view synthesis. 3) To support fast fine-tuning for specific scenes, we introduce a multi-view geometric consistent aggregation strategy to effectively aggregate the point clouds generated by the generalizable model, serving as the initialization for per-scene optimization. Compared with previous generalizable NeRF-based methods, which typically require minutes of fine-tuning and seconds of rendering per image, MVSGaussian achieves real-time rendering with better synthesis quality for each scene. Compared with the vanilla 3D-GS, MVSGaussian achieves better view synthesis with less training computational cost. Extensive experiments on DTU, Real Forward-facing, NeRF Synthetic, and Tanks and Temples datasets validate that MVSGaussian attains state-of-the-art performance with convincing generalizability, real-time rendering speed, and fast per-scene optimization.","url_abs":"https://arxiv.org/abs/2405.12218v3","url_pdf":"https://arxiv.org/pdf/2405.12218v3.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":"fast-generalizable-gaussian-splatting","repo_url":"https://github.com/TQTQliu/MVSGaussian","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"nerf","task_name":"NeRF"},{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.12218","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.12218"}},"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/TQTQliu/MVSGaussian","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran":6,"unverified":1},"by_repo_kind":{"official":{"samples":8,"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":"5a8b1e0eb5ec2789","entry":"RGB2SH","repo":"TQTQliu/MVSGaussian","repo_kind":"official","path":"fusion.py","file_url":"https://github.com/TQTQliu/MVSGaussian/blob/HEAD/fusion.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a8b1e0eb5ec2789"}},{"code_sha256_prefix":"87df4437d34bb35f","entry":"make_data_sampler","repo":"TQTQliu/MVSGaussian","repo_kind":"official","path":"lib/datasets/make_dataset.py","file_url":"https://github.com/TQTQliu/MVSGaussian/blob/HEAD/lib/datasets/make_dataset.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":"87df4437d34bb35f"}},{"code_sha256_prefix":"b0c00209a1cb4ff9","entry":"make_evaluator","repo":"TQTQliu/MVSGaussian","repo_kind":"official","path":"lib/evaluators/make_evaluator.py","file_url":"https://github.com/TQTQliu/MVSGaussian/blob/HEAD/lib/evaluators/make_evaluator.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":"b0c00209a1cb4ff9"}},{"code_sha256_prefix":"cdd00787894554b5","entry":"readImages","repo":"TQTQliu/MVSGaussian","repo_kind":"official","path":"lib/metrics.py","file_url":"https://github.com/TQTQliu/MVSGaussian/blob/HEAD/lib/metrics.py","link_basis":"harvester_set","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":"cdd00787894554b5"}},{"code_sha256_prefix":"a1db096963f65ed2","entry":"read_img","repo":"TQTQliu/MVSGaussian","repo_kind":"official","path":"fusion.py","file_url":"https://github.com/TQTQliu/MVSGaussian/blob/HEAD/fusion.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":"a1db096963f65ed2"}},{"code_sha256_prefix":"18ed79bdb5f6cf13","entry":"read_pfm","repo":"TQTQliu/MVSGaussian","repo_kind":"official","path":"fusion.py","file_url":"https://github.com/TQTQliu/MVSGaussian/blob/HEAD/fusion.py","link_basis":"harvester_set","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":"18ed79bdb5f6cf13"}},{"code_sha256_prefix":"e94ed7d31400e408","entry":"sample_patch","repo":"TQTQliu/MVSGaussian","repo_kind":"official","path":"lib/datasets/mvsgs_utils.py","file_url":"https://github.com/TQTQliu/MVSGaussian/blob/HEAD/lib/datasets/mvsgs_utils.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":"e94ed7d31400e408"}},{"code_sha256_prefix":"65d6513bc44b700c","entry":"load_cfg","repo":"TQTQliu/MVSGaussian","repo_kind":"official","path":"lib/config/yacs.py","file_url":"https://github.com/TQTQliu/MVSGaussian/blob/HEAD/lib/config/yacs.py","link_basis":"first_harvest_node","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":"65d6513bc44b700c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}