mlsanityData to 14 Oct 2026

S3Net: A Single Stream Structure for Depth Guided Image Relighting

arXiv 2105.00681 ↗First posted 3 May 2021cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Depth guided any-to-any image relighting aims to generate a relit image from the original image and corresponding depth maps to match the illumination setting of the given guided image and its depth map. To the best of our knowledge, this task is a new challenge that has not been addressed in the previous literature. To address this issue, we propose a deep learning-based neural Single Stream Structure network called S3Net for depth guided image relighting. This network is an encoder-decoder model. We concatenate all images and corresponding depth maps as the input and feed them into the model. The decoder part contains the attention module and the enhanced module to focus on the relighting-related regions in the guided images. Experiments performed on challenging benchmark show that the proposed model achieves the 3 rd highest SSIM in the NTIRE 2021 Depth Guided Any-to-any Relighting Challenge.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 20 of its 39 references that are in the map. First posted on arXiv 3 May 2021.

Builds on

20 of 39 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  6. 2017Squeeze-and-Excitation Networkscited by 4,789
  7. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  8. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 470
  9. 2014Recurrent Models of Visual Attentioncited by 349
  10. 2017A General and Adaptive Robust Loss Functioncited by 236
  11. 2020Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentationcited by 122
  12. 2020Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detectioncited by 72
8 more
  1. 2020Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detectioncited by 40
  2. 2020VIDIT: Virtual Image Dataset for Illumination Transfercited by 26
  3. 2021NTIRE 2021 Depth Guided Image Relighting Challengecited by 23
  4. 2020AIM 2020: Scene Relighting and Illumination Estimation Challengecited by 18
  5. 2020Y-net: Multi-scale feature aggregation network with wavelet structure similarity loss function for single image dehazingcited by 14
  6. 2020WDRN : A Wavelet Decomposed RelightNet for Image Relightingcited by 14
  7. 2018Neural Stereoscopic Image Style Transfercited by 10
  8. 2020Wavelet Channel Attention Module with a Fusion Network for Single Image Derainingcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 1; 2023: 0; 2024: 3; 2025: 1; 2026: 2.

9 papers.

  1. 2024LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relightingcited by 38
  2. 2024GenLit: Reformulating Single-Image Relighting as Video Generationcited by 20
  3. 2024Latent Intrinsics Emerge from Training to Relightcited by 17
  4. 2021LAFFNet: A Lightweight Adaptive Feature Fusion Network for Underwater Image Enhancementcited by 8
  5. 2022Shakes on a Plane: Unsupervised Depth Estimation from Unstabilized Photographycited by 8
  6. 2021Robust Unsupervised Multi-Object Tracking in Noisy Environmentscited by 1
  7. 2026Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimationcited by 1
  8. 2025CLIP-RL: Surgical Scene Segmentation Using Contrastive Language-Vision Pretraining & Reinforcement Learningcited by 0
  9. 2026Relighting as a Probe of Visual Priors via Augmented Latent Intrinsicscited by 0