Publications de Radu Timofte | EPFL Graph Search

NTIRE 2021 Depth Guided Image Relighting Challenge

Sabine Süsstrunk, Majed El Helou, Ruofan Zhou, Radu Timofte

Image relighting is attracting increasing interest due to its various applications. From a research perspective, image relighting can be exploited to conduct both image normalization for domain adaptation, and also for data augmentation. It also has multip ...

IEEE COMPUTER SOC2021

DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation

Alexandre Massoud Alahi, Radu Timofte

Scalable Vector Graphics (SVG) are ubiquitous in modern 2D interfaces due to their ability to scale to different resolutions. However, despite the success of deep learning-based models applied to rasterized images, the problem of vector graphics representa ...

2020

AIM 2020: Scene Relighting and Illumination Estimation Challenge

Sabine Süsstrunk, Majed El Helou, Ruofan Zhou, Matthew Brown, Xin Huang, Radu Timofte, Tongtong Zhao, Shanshan Zhao, Yu Zhu, Yuzhong Liu

We review the AIM 2020 challenge on virtual image relighting and illumination estimation. This paper presents the novel VIDIT dataset used in the challenge and the different proposed solutions and final evaluation results over the 3 challenge tracks. The f ...

2020

AIM 2019 Challenge on Image Extreme Super-Resolution: Methods and Results

Majed El Helou, Liying Lu, Ruofan Zhou, Xin Yang, Wei Li, Radu Timofte, Jia Yu, Muhammad Haris, Peng Yi, Jiayi Ma

This paper reviews the AIM 2019 challenge on extreme image super-resolution, the problem of restoring of rich details in a low resolution image. Compared to previous, this challenge focuses on an extreme upscaling factor, x16, and employs the novel DIVerse ...

IEEE COMPUTER SOC2019

NTIRE 2018 Challenge on Spectral Reconstruction from RGB Images

Lei Zhang, Bing Zhang, Majed El Helou, Ruofan Zhou, Fayez Lahoud, Dong Liu, Marjan Shahpaski, Radu Timofte, Chang Chen, Soumik Sarkar

This paper reviews the first challenge on spectral image reconstruction from RGB images, i.e., the recovery of whole-scene hyperspectral (HS) information from a 3- channel RGB image. The challenge was divided into 2 tracks: the “Clean” track sought HS reco ...

2018