{"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/hicom-hierarchical-coherent-motion-for","title":"HiCoM: Hierarchical Coherent Motion for Streamable Dynamic Scene with 3D Gaussian Splatting","arxiv_id":"2411.07541","date":"2024-11-12","proceeding":null,"authors":["Qiankun Gao","Jiarui Meng","Chengxiang Wen","Jie Chen","Jian Zhang"],"abstract":"The online reconstruction of dynamic scenes from multi-view streaming videos faces significant challenges in training, rendering and storage efficiency. Harnessing superior learning speed and real-time rendering capabilities, 3D Gaussian Splatting (3DGS) has recently demonstrated considerable potential in this field. However, 3DGS can be inefficient in terms of storage and prone to overfitting by excessively growing Gaussians, particularly with limited views. This paper proposes an efficient framework, dubbed HiCoM, with three key components. First, we construct a compact and robust initial 3DGS representation using a perturbation smoothing strategy. Next, we introduce a Hierarchical Coherent Motion mechanism that leverages the inherent non-uniform distribution and local consistency of 3D Gaussians to swiftly and accurately learn motions across frames. Finally, we continually refine the 3DGS with additional Gaussians, which are later merged into the initial 3DGS to maintain consistency with the evolving scene. To preserve a compact representation, an equivalent number of low-opacity Gaussians that minimally impact the representation are removed before processing subsequent frames. Extensive experiments conducted on two widely used datasets show that our framework improves learning efficiency of the state-of-the-art methods by about $20\\%$ and reduces the data storage by $85\\%$, achieving competitive free-viewpoint video synthesis quality but with higher robustness and stability. Moreover, by parallel learning multiple frames simultaneously, our HiCoM decreases the average training wall time to $<2$ seconds per frame with negligible performance degradation, substantially boosting real-world applicability and responsiveness.","url_abs":"https://arxiv.org/abs/2411.07541v2","url_pdf":"https://arxiv.org/pdf/2411.07541v2.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":"hicom-hierarchical-coherent-motion-for","repo_url":"https://github.com/gqk/hicom","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"3dgs","task_name":"3DGS"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.07541","atlas_url":"https://app.syntology.ai/?focus=2411.07541","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07541"}},"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/gqk/hicom","reach":null}],"summary":{"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"ca66ee414c168052","entry":"Grid","repo":"gqk/hicom","repo_kind":"official","path":"pipeline/hicom/model/deformation.py","file_url":"https://github.com/gqk/hicom/blob/HEAD/pipeline/hicom/model/deformation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ca66ee414c168052"}},{"code_sha256_prefix":"c5e56f86ed839f09","entry":"DeformConfig","repo":"gqk/hicom","repo_kind":"official","path":"pipeline/hicom/model/deformation.py","file_url":"https://github.com/gqk/hicom/blob/HEAD/pipeline/hicom/model/deformation.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":"c5e56f86ed839f09"}},{"code_sha256_prefix":"f8abe2b60b7ece72","entry":"Deformation","repo":"gqk/hicom","repo_kind":"official","path":"pipeline/hicom/model/deformation.py","file_url":"https://github.com/gqk/hicom/blob/HEAD/pipeline/hicom/model/deformation.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":"f8abe2b60b7ece72"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}