computer-vision-1

Image Relighting

3260 papers • 126 benchmarks • 313 datasets

Image relighting involves changing the illumination settings of an image.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in image-relighting-1

Trend

Dataset

Best Model

Actions

Stanford-ORB

VIDIT’20 validation set

Libraries

i

Use these libraries to find image-relighting-1 models and implementations

majedelhelou/VIDIT

3 papers 164

Datasets

Subtasks

No subtasks available.

Most implemented papers

Scale-Recurrent Network for Deep Image Deblurring

Xiaoyong Shen, Jiaya Jia, Jue Wang, Xin Tao, Hongyun Gao, Yi Wang•Mon Feb 05 2018

A Scale-recurrent Network (SRN-DeblurNet) is proposed and shown to produce better quality results than state-of-the-arts, both quantitatively and qualitatively in single image deblurring.

1224

Content

0

Paper Graph

NTIRE 2021 Depth Guided Image Relighting Challenge

S. Süsstrunk, Radu Timofte, Majed El Helou, Ruofan Zhou•Mon Apr 26 2021

This paper reviews the NTIRE 2021 depth guided image relighting challenge and relies on the VIDIT dataset for each of the two challenge tracks, including depth information, to transform the illumination settings of an input image to match those of another guide image, similar to style transfer.

33 0

Paper Graph

VIDIT: Virtual Image Dataset for Illumination Transfer

S. Süsstrunk, Majed El Helou, Ruofan Zhou, Johan Barthas•Sun May 10 2020

This work presents a novel dataset, the Virtual Image Dataset for Illumination Transfer (VIDIT), in an effort to create a reference evaluation benchmark and to push forward the development of illumination manipulation methods.

41 0

Paper Graph

AIM 2020: Scene Relighting and Illumination Estimation Challenge

Jian Cheng, Radu Timofte, Cong Leng, M. Afifi, Majed El Helou, Ruofan Zhou, Nisarg A. Shah, Shanshan Zhao, Michael S. Brown, Kuldeep Purohit, A. Rajagopalan, Sourya Dipta Das, Yu Zhu, Sabine E. Susstrunk, Hengxing Cai, Yuzhong Liu, Li-Wen Wang, Zhi-Song Liu, Chu-Tak Li, Akashdeep Jassal, Tongtong Zhao, S. Nathan, M. Beham, R. Suganya, Qing Wang, Zhongyun Hu, Xin Huang, Yaning Li, Maitreya Suin, Densen Puthussery, S. HrishikeshP., M. Kuriakose, V. JijiC., Liping Dong, Zhuolong Jiang, Chenghua Li•Sat Sep 26 2020

The novel VIDIT dataset used in the AIM 2020 challenge and the different proposed solutions and final evaluation results over the 3 challenge tracks are presented.

44 0

Paper Graph

Multi-modal Bifurcated Network for Depth Guided Image Relighting

Haowen Luo, Wei-Ting Chen, Sy-Yen Kuo, Hao-Hsiang Yang•Sun May 02 2021

A deep learningbased method called multi-modal bifurcated network (MBNet) for depth guided image relighting, where given an image and the corresponding depth maps, a new image with the given illuminant angle and color temperature is generated by this model.

13 0

Paper Graph

Extracting Triangular 3D Models, Materials, and Lighting From Images

S. Fidler, Alex Evans, T. Müller, Wenzheng Chen, Jun Gao, Jacob Munkberg, J. Hasselgren, Tianchang Shen•Tue Nov 23 2021

This work outputs triangle meshes with spatially-varying materials and environment lighting that can be deployed in any traditional graphics engine unmodified, and introduces a differentiable formulation of the split sum approximation of environment lighting to efficiently recover all-frequency lighting.

460 0

Paper Graph

0.5 Petabyte Simulation of a 45-Qubit Quantum Circuit

Thomas Häner, Damian S. Steiger•Mon Apr 03 2017

This work applies a scheduling algorithm to quantum supremacy circuits in order to reduce the required communication and simulate a 45-qubit circuit on the Cori II supercomputer using 8, 192 nodes and 0.5 petabytes of memory, which constitutes the largest quantum circuit simulation to this date.

200 0

Paper Graph

Local Relighting of Real Scenes

Àgata Lapedriza, A. Torralba, Ali Jahanian, Audrey Cui, Shahin Mahdizadehaghdam, Rohit Kumar, David Bau•Tue Jul 05 2022

This work proposes an approach for local relighting that trains a model without supervision of any novel image dataset by using synthetically generated image pairs from another model, including a stylespace-manipulated GAN.

3 0

Paper Graph

GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing

Xiaohong Liu, Yongrui Ma, Zhihao Shi•Wed Aug 07 2019

An end-to-end trainable Convolutional Neural Network for single image dehazing, named GridDehazeNet, which implements a novel attention-based multi-scale estimation on a grid network, and an explanation as to why it is not necessarily beneficial to take advantage of the dimension reduction offered by the atmosphere scattering model.

959 0

Paper Graph

Scene relighting with illumination estimation in the latent space on an encoder-decoder scheme

Alexandre Pierre Dherse, Martin Nicolas Everaert, J. Gwizdala•Tue Jun 02 2020

The image relighting task of transferring illumination conditions between two images offers an interesting and difficult challenge with potential applications in photography, cinematography and computer graphics and methods are presented to achieve that goal.

5 0

Paper Graph

Adding a benchmark result helps the community track progress.