SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2412.00905 · 2024

Ref-GS: Directional Factorization for 2D Gaussian Splatting

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 12 functions out of this paper's own repositories and ran 5 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
YoujiaZhang/Ref-GS canonical 5 of 12
FunctionStatusWhere it lives
gaussian Ran YoujiaZhang/Ref-GS/utils/loss_utils.py
code served (permissive licence) · get_code("c56b7ef16f309a45")
l1_loss Ran YoujiaZhang/Ref-GS/utils/loss_utils.py
code served (permissive licence) · get_code("ac0e42d6fbcfbbe6")
l2_loss Ran YoujiaZhang/Ref-GS/utils/loss_utils.py
code served (permissive licence) · get_code("8c3b0f873ba11813")
normalize_activation Ran YoujiaZhang/Ref-GS/lpipsPyTorch/modules/utils.py
code served (permissive licence) · get_code("1dab900b2adbe38e")
read_next_bytes Ran YoujiaZhang/Ref-GS/scene/colmap_loader.py
code served (permissive licence) · get_code("56858e04e6fdb2ff")
get_network Not yet run YoujiaZhang/Ref-GS/lpipsPyTorch/modules/networks.py
code served (permissive licence) · get_code("07bd0da29c4dc7bb")
get_state_dict Not yet run YoujiaZhang/Ref-GS/lpipsPyTorch/modules/utils.py
code served (permissive licence) · get_code("b06f27c08cf5d0ca")
prepare_output_and_logger Not yet run YoujiaZhang/Ref-GS/train-NeRF.py
code served (permissive licence) · get_code("14c1f8cb24f602cf")
prepare_output_and_logger Not yet run YoujiaZhang/Ref-GS/train-NeRO.py
code served (permissive licence) · get_code("c80af193336d9809")
prepare_output_and_logger Not yet run YoujiaZhang/Ref-GS/train-real.py
code served (permissive licence) · get_code("495defa964436eba")
qvec2rotmat Not yet run YoujiaZhang/Ref-GS/scene/colmap_loader.py
code served (permissive licence) · get_code("6ce64cf0fbcd6bb1")
rotmat2qvec Not yet run YoujiaZhang/Ref-GS/scene/colmap_loader.py
code served (permissive licence) · 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

In this paper, we introduce Ref-GS, a novel approach for directional light factorization in 2D Gaussian splatting, which enables photorealistic view-dependent appearance rendering and precise geometry recovery. Ref-GS builds upon the deferred rendering of Gaussian splatting and applies directional encoding to the deferred-rendered surface, effectively reducing the ambiguity between orientation and viewing angle. Next, we introduce a spherical Mip-grid to capture varying levels of surface roughness, enabling roughness-aware Gaussian shading. Additionally, we propose a simple yet efficient geometry-lighting factorization that connects geometry and lighting via the vector outer product, significantly reducing renderer overhead when integrating volumetric attributes. Our method achieves superior photorealistic rendering for a range of open-world scenes while also accurately recovering geometry.

For agents

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

get_harvested_code_for_paper("2412.00905")
get_code_for_paper("2412.00905")
have("2412.00905")

Connect an agent — have() is free.