Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedra

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F23%3A00369657" target="_blank" >RIV/68407700:21230/23:00369657 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21730/23:00369657

Výsledek na webu

<a href="https://doi.org/10.1109/ICCV51070.2023.01692" target="_blank" >https://doi.org/10.1109/ICCV51070.2023.01692</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICCV51070.2023.01692" target="_blank" >10.1109/ICCV51070.2023.01692</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedra

Popis výsledku v původním jazyce

Neural Radiance Fields (NeRFs) are a very recent and very popular approach for the problems of novel view syn thesis and 3D reconstruction. A popular scene representa tion used by NeRFs is to combine a uniform, voxel-based subdivision of the scene with an MLP. Based on the ob servation that a (sparse) point cloud of the scene is often available, this paper proposes to use an adaptive represen tation based on tetrahedra obtained by Delaunay triangula tion instead of uniform subdivision or point-based represen tations. We show that such a representation enables efficient training and leads to state-of-the-art results. Our approach elegantly combines concepts from 3D geometry process ing, triangle-based rendering, and modern neural radiance fields. Compared to voxel-based representations, ours pro vides more detail around parts of the scene likely to be close to the surface. Compared to point-based representations, our approach achieves better performance. The source code is publicly available at: https://jkulhanek.com/tetra-nerf.

Název v anglickém jazyce

Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedra

Popis výsledku anglicky

Neural Radiance Fields (NeRFs) are a very recent and very popular approach for the problems of novel view syn thesis and 3D reconstruction. A popular scene representa tion used by NeRFs is to combine a uniform, voxel-based subdivision of the scene with an MLP. Based on the ob servation that a (sparse) point cloud of the scene is often available, this paper proposes to use an adaptive represen tation based on tetrahedra obtained by Delaunay triangula tion instead of uniform subdivision or point-based represen tations. We show that such a representation enables efficient training and leads to state-of-the-art results. Our approach elegantly combines concepts from 3D geometry process ing, triangle-based rendering, and modern neural radiance fields. Compared to voxel-based representations, ours pro vides more detail around parts of the scene likely to be close to the surface. Compared to point-based representations, our approach achieves better performance. The source code is publicly available at: https://jkulhanek.com/tetra-nerf.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GX23-07973X" target="_blank" >GX23-07973X: Sjednocená Reprezentace 3D Map</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

ICCV2023: Proceedings of the International Conference on Computer Vision

ISBN

979-8-3503-0719-1

ISSN

1550-5499

e-ISSN

2380-7504

Počet stran výsledku

12

Strana od-do

18412-18423

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Paris

Datum konání akce

2. 10. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001169500503004