mlsanityData to 14 Oct 2026

RenDetNet: Weakly-supervised Shadow Detection with Shadow Caster Verification

arXiv 2408.17143 ↗First posted 30 Aug 2024cs.CV cs.GRcited by 0

Not on the map. Why?

Abstract (arXiv)

Existing shadow detection models struggle to differentiate dark image areas from shadows. In this paper, we tackle this issue by verifying that all detected shadows are real, i.e. they have paired shadow casters. We perform this step in a physically-accurate manner by differentiably re-rendering the scene and observing the changes stemming from carving out estimated shadow casters. Thanks to this approach, the RenDetNet proposed in this paper is the first learning-based shadow detection model whose supervisory signals can be computed in a self-supervised manner. The developed system compares favourably against recent models trained on our data. As part of this publication, we release our code on github.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 49 references that are in the map. First posted on arXiv 30 Aug 2024.

Builds on

27 of 49 references.

References · 27

  1. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,179
  2. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 236
  3. 2021AGORA: Avatars in Geography Optimized for Regression Analysiscited by 205
  4. 2017Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removalcited by 161
  5. 2019HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objectscited by 110
  6. 2019Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Datacited by 92
  7. 2020Bridging Composite and Real: Towards End-to-end Deep Image Mattingcited by 89
  8. 2022DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Networkcited by 69
  9. 2017Direction-aware Spatial Context Features for Shadow Detectioncited by 56
  10. 2020Portrait Shadow Manipulationcited by 42
  11. 2017A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuationcited by 39
  12. 2020Shadow Removal by a Lightness-Guided Network with Training on Unpaired Datacited by 38
15 more
  1. 2019Instance Shadow Detectioncited by 37
  2. 2021Learning from Synthetic Shadows for Shadow Detection and Removalcited by 27
  3. 2022Instance Shadow Detection with A Single-Stage Detectorcited by 22
  4. 2023SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labelscited by 19
  5. 2019Water-Filling: An Efficient Algorithm for Digitized Document Shadow Removalcited by 17
  6. 2021Multi-View Fusion for Multi-Level Robotic Scene Understandingcited by 17
  7. 2022Video Shadow Detection via Spatio-Temporal Interpolation Consistency Trainingcited by 12
  8. 2023SDDNet: Style-guided Dual-layer Disentanglement Network for Shadow Detectioncited by 11
  9. 2020Multi-View Consistency Loss for Improved Single-Image 3D Reconstruction of Clothed Peoplecited by 9
  10. 2021Fine-Context Shadow Detection using Shadow Removalcited by 9
  11. 2024S3R-Net: A Single-Stage Approach to Self-Supervised Shadow Removalcited by 6
  12. 2022Video Instance Shadow Detection Under the Sun and Skycited by 3
  13. 2019Shadow Detection for Ultrasound Images Using Unlabeled Data and Synthetic Shadowscited by 2
  14. 2022Shadow-Oriented Tracking Method for Multi-Target Tracking in Video-SARcited by 1
  15. 2023AI driven shadow model detection in agropv farmscited by 1

Built on by

Not cited yet.