Quantisierungsbewusstes Training für Wörterbuchgesteuerte Implizite Neuronale Darstellung zur Bild- und Videokompression

Details

Veröffentlichungs-Nr.

EP4765808

Anmeldetag

18. Dezember 2024

Veröffentlichung

24. Juni 2026

Rechtsraum

EP

Abstract

In various implementations, methods and devices are disclosed that involves quantization aware training for dictionary-driven INR (Implicit Neural Representation). For instance, one or more quantization parameters for an INR network corresponding to an image region are obtained, wherein the INR network is reconstructed at both encoding and decoding by combining tail layers to head layers, the tail layers being defined by the one or more inverse quantized network parameters and the head layers being a weighted combination of one or more INR basis functions by the one or more inverse quantized coefficients, respectively. Then, the image region is reconstructed based on the reconstructed INR network. The one or more quantization parameters for the INR network, the one or more quantized coefficients of the head layers and the one or more quantized network parameters of the tail layers are encoded into or decoded from the bitstream.

Anmelder

Firma

InterDigital CE Patent Holdings, SAS

Land

🇫🇷 Frankreich