Nilut: Conditional neural implicit 3d lookup tables for image enhancement

Marcos V Conde, Javier Vazquez-Corral, Michael S Brown, Radu Timofte

Producció científica: Capítol de llibreCapítolRecercaAvaluat per experts

14 Descàrregues (Pure)

Resum

3D lookup tables (3D LUTs) are a key component for image enhancement. Modern image signal processors (ISPs) have dedicated support for these as part of the camera rendering pipeline. Cameras typically provide multiple options for picture styles, where each style is usually obtained by applying a
unique handcrafted 3D LUT. Current approaches for learning and applying 3D LUTs are notably fast, yet not so memoryeffcient, as storing multiple 3D LUTs is required. For this reason and other implementation limitations, their use on mobile devices is less popular. In this work, we propose a Neural Implicit LUT (NILUT), an implicitly defned continuous 3D color transformation
parameterized by a neural network. We show that NILUTs are capable of accurately emulating real 3D LUTs. Moreover, a NILUT can be extended to incorporate multiple styles into a single network with the ability to blend
styles implicitly. Our novel approach is memory-effcient, controllable and can complement previous methods, including learned ISPs. Code at
https://github.com/mv-lab/nilut
Idioma originalAnglès
Títol de la publicacióProceedings of the AAAI Conference on Artificial Intelligence
Pàgines1371-1379
Nombre de pàgines9
Volum38
Estat de la publicacióPublicada - 2024

Fingerprint

Navegar pels temes de recerca de 'Nilut: Conditional neural implicit 3d lookup tables for image enhancement'. Junts formen un fingerprint únic.

Com citar-ho