Výsledky vyhledávání

Report

Gaussian Deja-vu: Creating Controllable 3D Gaussian Head-Avatars with Enhanced Generalization and Personalization Abilities

Autor: Yan, Peizhi, Ward, Rabab, Tang, Qiang, Du, Shan

Recent advancements in 3D Gaussian Splatting (3DGS) have unlocked significant potential for modeling 3D head avatars, providing greater flexibility than mesh-based methods and more efficient rendering compared to NeRF-based approaches. Despite these

Externí odkaz: http://arxiv.org/abs/2409.16147

Zobrazit plný text záznamu

Akademický článek

An evolutionary game-theoretic analysis of cooperation strategy between SMEs and cross-border e-commerce platforms considering the cross-network effect

Autor: Du, Shan

Publikováno v: Kybernetes, 2023, Vol. 53, Issue 5, pp. 1857-1887.

Externí odkaz: http://www.emeraldinsight.com/doi/10.1108/K-09-2022-1316

Zobrazit plný text záznamu

Report

Real-World Image Super Resolution via Unsupervised Bi-directional Cycle Domain Transfer Learning based Generative Adversarial Network

Autor: Wang, Xiang, Yang, Yimin, Guo, Zhichang, Zhou, Zhili, Liu, Yu, Pang, Qixiang, Du, Shan

Deep Convolutional Neural Networks (DCNNs) have exhibited impressive performance on image super-resolution tasks. However, these deep learning-based super-resolution methods perform poorly in real-world super-resolution tasks, where the paired high-r

Externí odkaz: http://arxiv.org/abs/2211.10563

Zobrazit plný text záznamu

Report

Semantic Encoder Guided Generative Adversarial Face Ultra-Resolution Network

Autor: Wang, Xiang, Yang, Yimin, Pang, Qixiang, Lu, Xiao, Liu, Yu, Du, Shan

Face super-resolution is a domain-specific image super-resolution, which aims to generate High-Resolution (HR) face images from their Low-Resolution (LR) counterparts. In this paper, we propose a novel face super-resolution method, namely Semantic En

Externí odkaz: http://arxiv.org/abs/2211.10532

Zobrazit plný text záznamu

Report

Spatiotemporal Multi-scale Bilateral Motion Network for Gait Recognition

Autor: Ding, Xinnan, Du, Shan, Zhang, Yu, Wang, Kejun

The critical goal of gait recognition is to acquire the inter-frame walking habit representation from the gait sequences. The relations between frames, however, have not received adequate attention in comparison to the intra-frame features. In this p

Externí odkaz: http://arxiv.org/abs/2209.12364

Zobrazit plný text záznamu