Logo do repositório

Percorrer por autor "Ghafari, Mohammadreza"

A mostrar 1 - 2 de 2
  • IT/IST/IPLeiria Report on JPEG PCC Core Experiment 4.1: Attention Models
    Publication . Ghafari, Mohammadreza; Guarda, André; Rodrigues, Nuno; Pereira, Fernando
    Context and Objective: In the JPEG Pleno PC dataset, there are some PCs (e.g., sparse PCs) which are more ‘difficult’ to code and may benefit from improvements in the JPEG PCC VM DL coding model.
    2023-07Outro Acesso restrito Ver mais
  • Scalable Graph-Guided Transformer for Point Cloud Geometry Coding
    Publication . Ghafari, Mohammadreza; Guarda, André F. R.; Rodrigues, Nuno M. M.; Pereira, Fernando
    Attention models, particularly Transformers, have significantly advanced deep learning in fields like natural language processing and computer vision by capturing contextual relationships in both sequential and spatial data. This ability is valuable for Point Clouds (PC), which are unstructured sets of points in 3D space. Transformers can effectively identify correlations between distant points, allowing them to focus on the most critical regions of the data. To demonstrate this capability, this paper proposes a novel, scalable Graph-Guided Transformer model, labeled 2GFormer, for static PC geometry. This model is built using a scalable architecture that leverages Graph Convolutions to enhance a Relational Neighborhood SelfAttention (RNSA) base layer model. Both models are integrated into the JPEG Pleno Learning-based Point Cloud Coding (JPEG PCC) standard, resulting in the creation of two attention-enabled codecs for static PC coding: JPEG RNSA and JPEG 2GFormer. While JPEG RNSA codec delivers significant compression improvements for solid and dense PCs compared to the baseline JPEG PCC standard, JPEG 2GFormer extends these gains to solid, dense, and sparse PCs with only a marginal increase in model parameters. Additionally, JPEG 2GFormer outperforms both conventional and learning-based state-of-the-art PC codecs. These results position JPEG 2GFormer as a highly efficient solution for versatile PC coding.
    2025Artigo de investigação Acesso restrito Ver mais