SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.17427 · CVPR · 2024

VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction

Jianzhuang Liu, Youliang Yan, Jiaqi Lin, Wenming Yang, Songcen Xu, Zhihao Li, Yangdi Lu, Xiao Tang, Shiyong Liu, Xiaofei Wu, Jiayue Liu

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 7 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
kangpeilun/VastGaussian pwc_unofficial 7 of 10
FunctionStatusWhere it lives
decouple_appearance Ran kangpeilun/VastGaussian/train_vast.py
code served (permissive licence) · get_code("ecdc8508503ed67c")
gaussian Ran kangpeilun/VastGaussian/utils/loss_utils.py
code served (permissive licence) · get_code("c56b7ef16f309a45")
l1_loss Ran kangpeilun/VastGaussian/utils/loss_utils.py
code served (permissive licence) · get_code("ac0e42d6fbcfbbe6")
l2_loss Ran kangpeilun/VastGaussian/utils/loss_utils.py
code served (permissive licence) · get_code("8c3b0f873ba11813")
normalize_activation Ran kangpeilun/VastGaussian/lpipsPyTorch/modules/utils.py
code served (permissive licence) · get_code("1dab900b2adbe38e")
readImages Ran kangpeilun/VastGaussian/metrics.py
code served (permissive licence) · get_code("cdd00787894554b5")
setup_logging Ran kangpeilun/VastGaussian/train_vast.py
code served (permissive licence) · get_code("ab6a64fe2fcad5f5")
get_network Not yet run kangpeilun/VastGaussian/lpipsPyTorch/modules/networks.py
code served (permissive licence) · get_code("07bd0da29c4dc7bb")
get_state_dict Not yet run kangpeilun/VastGaussian/lpipsPyTorch/modules/utils.py
code served (permissive licence) · get_code("b06f27c08cf5d0ca")
prepare_output_and_logger Not yet run kangpeilun/VastGaussian/train_vast.py
code served (permissive licence) · get_code("72d69d6c61ff0b97")

Repositories linked to this paper

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

Abstract

Equal contribution † Corresponding author (a) Mega-NeRF (b) Switch-NeRF (c) Modified 3DGS (d) VastGaussian (ours) (e) Ground Truth

For agents

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

get_harvested_code_for_paper("2402.17427")
get_code_for_paper("2402.17427")
have("2402.17427")

Connect an agent — have() is free.