Výsledky vyhledávání - "Sial, Hassan"

Report

Relighting from a Single Image: Datasets and Deep Intrinsic-based Architecture

Autor: Yang, Yixiong, Sial, Hassan Ahmed, Baldrich, Ramon, Vanrell, Maria

Single image scene relighting aims to generate a realistic new version of an input image so that it appears to be illuminated by a new target light condition. Although existing works have explored this problem from various perspectives, generating re

Externí odkaz: http://arxiv.org/abs/2409.18770

Zobrazit plný text záznamu

Report

Intrinsic Decomposition of Document Images In-the-Wild

Autor: Das, Sagnik, Sial, Hassan Ahmed, Ma, Ke, Baldrich, Ramon, Vanrell, Maria, Samaras, Dimitris

Automatic document content processing is affected by artifacts caused by the shape of the paper, non-uniform and diverse color of lighting conditions. Fully-supervised methods on real data are impossible due to the large amount of data needed. Hence,

Externí odkaz: http://arxiv.org/abs/2011.14447

Zobrazit plný text záznamu

Report

Light Direction and Color Estimation from Single Image with Deep Regression

Autor: Sial, Hassan A., Baldrich, Ramon, Vanrell, Maria, Samaras, Dimitris

We present a method to estimate the direction and color of the scene light source from a single image. Our method is based on two main ideas: (a) we use a new synthetic dataset with strong shadow effects with similar constraints to the SID dataset; (

Externí odkaz: http://arxiv.org/abs/2009.08941

Zobrazit plný text záznamu

Report

Deep intrinsic decomposition trained on surreal scenes yet with realistic light effects

Autor: Sial, Hassan, Baldrich, Ramon, Vanrell, Maria

Publikováno v: JOSA A 2020

Estimation of intrinsic images still remains a challenging task due to weaknesses of ground-truth datasets, which either are too small or present non-realistic issues. On the other hand, end-to-end deep learning architectures start to achieve interes

Externí odkaz: http://arxiv.org/abs/2009.06295

Zobrazit plný text záznamu

Akademický článek

Exploring dermoscopic structures for melanoma lesions’ classification.

Autor: Malik, Fiza Saeed, Yousaf, Muhammad Haroon, Sial, Hassan Ahmed, Viriri, Serestina

Publikováno v: Frontiers in Big Data; 2024, p1-19, 19p

Zobrazit plný text záznamu

Estimating Light Effects from a Single Image : Deep Architectures and Ground-Truth Generation

Autor: Sial, Hassan Ahmed

Publikováno v: TDX (Tesis Doctorals en Xarxa)
TDR. Tesis Doctorales en Red
instname
Dipòsit Digital de Documents de la UAB
Universitat Autònoma de Barcelona

En aquesta tesi explorem com estimar els efectes de la llum que interactua amb els objectes d’una escena a partir d’una sola imatge. Per assolir aquest objectiu, ens centrem en la recuperació de components intrínseques com ara la reflectància,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::d56b385355ba6dfab0154b14dd4f6124
https://ddd.uab.cat/record/257616

Zobrazit plný text záznamu