Real-Time Neural Materials using Block-Compressed Features - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Real-Time Neural Materials using Block-Compressed Features

Clément Weinreich
  • Fonction : Auteur
  • PersonId : 1298681
Louis de Oliveira
  • Fonction : Auteur
  • PersonId : 1298682
Antoine Houdard
Georges Nader

Résumé

Neural materials typically consist of a collection of neural features along with a decoder network. The main challenge in integrating such models in real-time rendering pipelines lies in the large size required to store their features in GPU memory and the complexity of evaluating the network efficiently. We present a neural material model whose features and decoder are specifically designed to be used in real-time rendering pipelines. Our framework leverages hardware-based block compression (BC) texture formats to store the learned features and trains the model to output the material information continuously in space and scale. To achieve this, we organize the features in a block-based manner and emulate BC6 decompression during training, making it possible to export them as regular BC6 textures. This structure allows us to use high resolution features while maintaining a low memory footprint. Consequently, this enhances our model's overall capability, enabling the use of a lightweight and simple decoder architecture that can be evaluated directly in a shader. Furthermore, since the learned features can be decoded continuously, it allows for random uv sampling and smooth transition between scales without needing any subsequent filtering. As a result, our neural material has a small memory footprint, can be decoded extremely fast adding a minimal computational overhead to the rendering pipeline.
Fichier principal
Vignette du fichier
neural-textures.pdf (47.95 Mo) Télécharger le fichier
supplementary_material.pdf (7.04 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04255874 , version 1 (24-10-2023)
hal-04255874 , version 2 (18-02-2024)

Licence

Paternité

Identifiants

Citer

Clément Weinreich, Louis de Oliveira, Antoine Houdard, Georges Nader. Real-Time Neural Materials using Block-Compressed Features. Eurographics 2024, Apr 2024, Limassol (Chypre), Cyprus. ⟨hal-04255874v2⟩
224 Consultations
120 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More