SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.20791 · NeurIPS · 2025

MetaGS: A Meta-Learned Gaussian-Phong Model for Out-of-Distribution 3D Scene Relighting

Yunbo Wang, Xiaokang Yang, Yumeng He

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 13 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
ymhe12/GS-Phong canonical 6 of 13
FunctionStatusWhere it lives
gaussian Ran ymhe12/GS-Phong/utils/loss_utils.py
pointer only (licence: NONE) · get_code("c56b7ef16f309a45")
l1_loss Ran ymhe12/GS-Phong/utils/loss_utils.py
pointer only (licence: NONE) · get_code("ac0e42d6fbcfbbe6")
l2_loss Ran ymhe12/GS-Phong/utils/loss_utils.py
pointer only (licence: NONE) · get_code("8c3b0f873ba11813")
normalize_activation Ran ymhe12/GS-Phong/lpipsPyTorch/modules/utils.py
pointer only (licence: NONE) · get_code("1dab900b2adbe38e")
readImages Ran ymhe12/GS-Phong/metrics.py
pointer only (licence: NONE) · get_code("cdd00787894554b5")
read_next_bytes Ran ymhe12/GS-Phong/utils/read_write_model.py
pointer only (licence: NONE) · get_code("56858e04e6fdb2ff")
get_network Not yet run ymhe12/GS-Phong/lpipsPyTorch/modules/networks.py
pointer only (licence: NONE) · get_code("07bd0da29c4dc7bb")
get_state_dict Not yet run ymhe12/GS-Phong/lpipsPyTorch/modules/utils.py
pointer only (licence: NONE) · get_code("b06f27c08cf5d0ca")
prepare_output_and_logger Not yet run ymhe12/GS-Phong/train_meta.py
pointer only (licence: NONE) · get_code("43887f53e9b99271")
qvec2rotmat Not yet run ymhe12/GS-Phong/scene/colmap_loader.py
pointer only (licence: NONE) · get_code("6ce64cf0fbcd6bb1")
read_cameras_binary Not yet run ymhe12/GS-Phong/utils/read_write_model.py
pointer only (licence: NONE) · get_code("a10bf79d34938dbd")
read_cameras_text Not yet run ymhe12/GS-Phong/utils/read_write_model.py
pointer only (licence: NONE) · get_code("c424ebf4a6c32cbd")
rotmat2qvec Not yet run ymhe12/GS-Phong/scene/colmap_loader.py
pointer only (licence: NONE) · get_code("659bc4e7e63ed8f9")

Repositories linked to this paper

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

Abstract

Out-of-distribution (OOD) 3D relighting requires novel view synthesis under unseen lighting conditions that differ significantly from the observed images. Existing relighting methods, which assume consistent light source distributions between training and testing, often degrade in OOD scenarios. We introduce MetaGS to tackle this challenge from two perspectives. First, we propose a meta-learning approach to train 3D Gaussian splatting, which explicitly promotes learning generalizable Gaussian geometries and appearance attributes across diverse lighting conditions, even with biased training data. Second, we embed fundamental physical priors from the Blinn-Phong reflection model into Gaussian splatting, which enhances the decoupling of shading components and leads to more accurate 3D scene reconstruction. Results on both synthetic and real-world datasets demonstrate the effectiveness of MetaGS in challenging OOD relighting tasks, supporting efficient point-light relighting and generalizing well to unseen environment lighting maps.

For agents

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

get_harvested_code_for_paper("2405.20791")
get_code_for_paper("2405.20791")
have("2405.20791")

Connect an agent — have() is free.