SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2411.07541 · NeurIPS · 2024

HiCoM: Hierarchical Coherent Motion for Streamable Dynamic Scene with 3D Gaussian Splatting

Jian Zhang, Jie Chen, Jiarui Meng, Qiankun Gao, Chengxiang Wen

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
gqk/hicom — 1 of 3
FunctionStatusWhere it lives
Grid Ran gqk/hicom/pipeline/hicom/model/deformation.py
pointer only (licence: NOASSERTION) · get_code("ca66ee414c168052")
DeformConfig Not yet run gqk/hicom/pipeline/hicom/model/deformation.py
pointer only (licence: NOASSERTION) · get_code("c5e56f86ed839f09")
Deformation Not yet run gqk/hicom/pipeline/hicom/model/deformation.py
pointer only (licence: NOASSERTION) · get_code("f8abe2b60b7ece72")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Training Time (seconds) 100 200 300 Rendering Speed (fps) StreamRF 3DGStream HiCoM (ours) HiCoM-P4 (ours) Figure 1: The proposed HiCoM framework for streamable dynamic scene reconstruction achieves competitive rendering quality with significantly shorter training time, faster rendering speed, and substantially reduced storage and transmission requirements. The left figures show results of our HiCoM on N3DV [1] and Meet Room [2] datasets, where "Res" indicates video resolution. The right figure is tested on the N3DV [1] dataset, where the radius of the circle corresponds to the average storage per frame and the method in the top left corner demonstrates the best performance.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2411.07541")
get_code_for_paper("2411.07541")
have("2411.07541")

Connect an agent — have() is free.