SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.09987 · ICCV · 2023

Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedra

Jonas Kulhanek, Torsten Sattler

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 2 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
jkulhanek/tetra-nerf canonical 2 of 5
FunctionStatusWhere it lives
read_cameras_text Ran jkulhanek/tetra-nerf/tetranerf/utils/colmap_utils.py
code served (permissive licence) · get_code("8a38e306ff4c5b42")
read_next_bytes Ran jkulhanek/tetra-nerf/tetranerf/utils/colmap_utils.py
code served (permissive licence) · get_code("56858e04e6fdb2ff")
map_from_real_distances_to_biased_with_bounds Not yet run jkulhanek/tetra-nerf/tetranerf/nerfstudio/model.py
code served (permissive licence) · get_code("3de3b5ee11b904ac")
read_cameras_binary Not yet run jkulhanek/tetra-nerf/tetranerf/utils/colmap_utils.py
code served (permissive licence) · get_code("4a20cdd355703af3")
skimage_ssim Not yet run jkulhanek/tetra-nerf/tetranerf/nerfstudio/model.py
code served (permissive licence) · get_code("d5408c73d7a6a219")

Repositories linked to this paper

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

Abstract

Figure 1. The input to Tetra-NeRF is a point cloud which is triangulated to get a set of tetrahedra used to represent the radiance field. Rays are sampled, and the field is queried. Barycentric interpolation is used to interpolate tetrahedra vertices, and the resulting features are passed through a shallow MLP to get the density and colours for volumetric rendering.

For agents

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

get_harvested_code_for_paper("2304.09987")
get_code_for_paper("2304.09987")
have("2304.09987")

Connect an agent — have() is free.