mlsanityData to 14 Oct 2026

NTIRE 2021 Depth Guided Image Relighting Challenge

arXiv 2104.13365 ↗First posted 27 Apr 2021cs.CV eess.IVcited by 23

Not on the map. Why?

Abstract (arXiv)

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 multiple direct uses for photo montage and aesthetic enhancement. In this paper, we review the NTIRE 2021 depth guided image relighting challenge. We rely on the VIDIT dataset for each of our two challenge tracks, including depth information. The first track is on one-to-one relighting where the goal is to transform the illumination setup of an input image (color temperature and light source position) to the target illumination setup. In the second track, the any-to-any relighting challenge, the objective is to transform the illumination settings of the input image to match those of another guide image, similar to style transfer. In both tracks, participants were given depth information about the captured scenes. We had nearly 250 registered participants, leading to 18 confirmed team submissions in the final competition stage. The competitions, methods, and final results are presented in this paper.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 24 of its 59 references that are in the map. First posted on arXiv 27 Apr 2021.

Builds on

24 of 59 references.

References · 24

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2016Densely Connected Convolutional Networkscited by 6,720
  4. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  5. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
  6. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 470
  7. 2017A General and Adaptive Robust Loss Functioncited by 236
  8. 2020Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurringcited by 119
  9. 2020Replacing Mobile Camera ISP with a Single Deep Learning Modelcited by 108
  10. 2020Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detectioncited by 72
  11. 2020Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detectioncited by 40
  12. 2019Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learningcited by 31
12 more
  1. 2020Hierarchical Regression Network for Spectral Reconstruction from RGB Imagescited by 29
  2. 2020VIDIT: Virtual Image Dataset for Illumination Transfercited by 26
  3. 2021NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Resultscited by 26
  4. 2020Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networkscited by 21
  5. 2020AIM 2020: Scene Relighting and Illumination Estimation Challengecited by 18
  6. 2020Y-net: Multi-scale feature aggregation network with wavelet structure similarity loss function for single image dehazingcited by 14
  7. 2020WDRN : A Wavelet Decomposed RelightNet for Image Relightingcited by 14
  8. 2020Deep Relighting Networks for Image Light Source Manipulationcited by 12
  9. 20202D Image Relighting with Image-to-Image Translationcited by 10
  10. 2021DSRN: an Efficient Deep Network for Image Relightingcited by 5
  11. 2021Multi-scale Self-calibrated Network for Image Light Source Transfercited by 4
  12. 2020Scene relighting with illumination estimation in the latent space on an encoder-decoder schemecited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 3; 2023: 3; 2024: 3; 2025: 0; 2026: 3.

23 papers.

Sort:

  1. 2021NTIRE 2021 Challenge on Image Deblurringcited by 50
  2. 2021NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Resultscited by 36
  3. 2021NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Resultscited by 22
  4. 2021NTIRE 2021 Challenge on Perceptual Image Quality Assessmentcited by 18
  5. 2021NTIRE 2021 Challenge on Video Super-Resolutioncited by 15
  6. 2021S3Net: A Single Stream Structure for Depth Guided Image Relightingcited by 9
  7. 2021NTIRE 2021 Multi-modal Aerial View Object Classification Challengecited by 7
  8. 2021Multi-modal Bifurcated Network for Depth Guided Image Relightingcited by 6
  9. 2022Exposure Correction Model to Enhance Image Qualitycited by 6
  10. 2024Relighting from a Single Image: Datasets and Deep Intrinsic-based Architecturecited by 6
  11. 2021SILT: Self-supervised Lighting Transfer Using Implicit Image Decompositioncited by 4
  12. 2023Computational Flash Photography through Intrinsicscited by 4
11 more
  1. 2021Physically Inspired Dense Fusion Networks for Relightingcited by 3
  2. 2022Designing An Illumination-Aware Network for Deep Image Relightingcited by 3
  3. 2023Spectral Sensitivity Estimation Without a Cameracited by 3
  4. 2022Local Relighting of Real Scenescited by 2
  5. 2021SIRfyN: Single Image Relighting from your Neighborscited by 1
  6. 2024MLI-NeRF: Multi-Light Intrinsic-Aware Neural Radiance Fieldscited by 1
  7. 2023Maturity-Aware Active Learning for Semantic Segmentation with Hierarchically-Adaptive Sample Assessmentcited by 0
  8. 2024Learning Relighting and Intrinsic Decomposition in Neural Radiance Fieldscited by 0
  9. 2026RehearsalNeRF: Decoupling Intrinsic Neural Fields of Dynamic Illuminations for Scene Editingcited by 0
  10. 2026Hidden-Shot: Towards One-Shot Task Generalization for Low-Level Vision Generalist Modelscited by 0
  11. 2026Monocular Depth Estimation from a Single Image: Progress and Opportunitiescited by 0