SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.01339 · 2024

Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 6 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
zju3dv/street_gaussians canonical 2 of 2
lightwheelai/street-gaussians-ns pwc_unofficial 4 of 4
FunctionStatusWhere it lives
IDFT Ran lightwheelai/street-gaussians-ns/street_gaussians_ns/sgn_splatfacto_scene_graph.py
code served (permissive licence) · get_code("1a536a8480df2817")
RGB2SH Ran lightwheelai/street-gaussians-ns/street_gaussians_ns/sgn_splatfacto.py
code served (permissive licence) · get_code("3d2c1a432b1a3561")
SH2RGB Ran lightwheelai/street-gaussians-ns/street_gaussians_ns/sgn_splatfacto.py
code served (permissive licence) · get_code("508a98451f5b78fe")
get_PCA_Norm Ran zju3dv/street_gaussians/lib/datasets/base_readers.py
pointer only (licence: NOASSERTION) · get_code("f9a78cc774a03dfe")
get_Sphere_Norm Ran zju3dv/street_gaussians/lib/datasets/base_readers.py
pointer only (licence: NOASSERTION) · get_code("a4a058e513f53050")
random_quat_tensor Ran lightwheelai/street-gaussians-ns/street_gaussians_ns/sgn_splatfacto.py
code served (permissive licence) · get_code("57acaa6d628ba9f8")

Repositories linked to this paper

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

Abstract

This paper aims to tackle the problem of modeling dynamic urban streets for autonomous driving scenes. Recent methods extend NeRF by incorporating tracked vehicle poses to animate vehicles, enabling photo-realistic view synthesis of dynamic urban street scenes. However, significant limitations are their slow training and rendering speed. We introduce Street Gaussians, a new explicit scene representation that tackles these limitations. Specifically, the dynamic urban scene is represented as a set of point clouds equipped with semantic logits and 3D Gaussians, each associated with either a foreground vehicle or the background. To model the dynamics of foreground object vehicles, each object point cloud is optimized with optimizable tracked poses, along with a 4D spherical harmonics model for the dynamic appearance. The explicit representation allows easy composition of object vehicles and background, which in turn allows for scene editing operations and rendering at 135 FPS (1066 $\times$ 1600 resolution) within half an hour of training. The proposed method is evaluated on multiple challenging benchmarks, including KITTI and Waymo Open datasets. Experiments show that the proposed method consistently outperforms state-of-the-art methods across all datasets. The code will be released to ensure reproducibility.

For agents

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

get_harvested_code_for_paper("2401.01339")
get_code_for_paper("2401.01339")
have("2401.01339")

Connect an agent — have() is free.