SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.05133 · 2023

GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 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
guduxiaolang/gir canonical 6 of 10
FunctionStatusWhere it lives
gaussian Ran guduxiaolang/gir/utils/loss_utils.py
pointer only (licence: NONE) · get_code("c56b7ef16f309a45")
l1_loss Ran guduxiaolang/gir/utils/loss_utils.py
pointer only (licence: NONE) · get_code("ac0e42d6fbcfbbe6")
l2_loss Ran guduxiaolang/gir/utils/loss_utils.py
pointer only (licence: NONE) · get_code("8c3b0f873ba11813")
normalize_activation Ran guduxiaolang/gir/lpipsPyTorch/modules/utils.py
pointer only (licence: NONE) · get_code("1dab900b2adbe38e")
read_next_bytes Ran guduxiaolang/gir/scene/colmap_loader.py
pointer only (licence: NONE) · get_code("56858e04e6fdb2ff")
safe_normalize Ran guduxiaolang/gir/submodules/envlight/renderer.py
pointer only (licence: NONE) · get_code("1c9cf033d080b2e0")
get_network Not yet run guduxiaolang/gir/lpipsPyTorch/modules/networks.py
pointer only (licence: NONE) · get_code("07bd0da29c4dc7bb")
get_state_dict Not yet run guduxiaolang/gir/lpipsPyTorch/modules/utils.py
pointer only (licence: NONE) · get_code("b06f27c08cf5d0ca")
qvec2rotmat Not yet run guduxiaolang/gir/scene/colmap_loader.py
pointer only (licence: NONE) · get_code("6ce64cf0fbcd6bb1")
rotmat2qvec Not yet run guduxiaolang/gir/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

This paper presents a 3D Gaussian Inverse Rendering (GIR) method, employing 3D Gaussian representations to effectively factorize the scene into material properties, light, and geometry. The key contributions lie in three-fold. We compute the normal of each 3D Gaussian using the shortest eigenvector, with a directional masking scheme forcing accurate normal estimation without external supervision. We adopt an efficient voxel-based indirect illumination tracing scheme that stores direction-aware outgoing radiance in each 3D Gaussian to disentangle secondary illumination for approximating multi-bounce light transport. To further enhance the illumination disentanglement, we represent a high-resolution environmental map with a learnable low-resolution map and a lightweight, fully convolutional network. Our method achieves state-of-the-art performance in both relighting and novel view synthesis tasks among the recently proposed inverse rendering methods while achieving real-time rendering. This substantiates our proposed method's efficacy and broad applicability, highlighting its potential as an influential tool in various real-time interactive graphics applications such as material editing and relighting. The code will be released at https://github.com/guduxiaolang/GIR.

For agents

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

get_harvested_code_for_paper("2312.05133")
get_code_for_paper("2312.05133")
have("2312.05133")

Connect an agent — have() is free.