mlsanityData to 14 Oct 2026

VibrantLeaves: A principled parametric image generator for training deep restoration models

arXiv 2504.10201 ↗First posted 14 Apr 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce a synthetic image generator relying on a few simple principles, specifically focusing on geometric modeling, textures, and a simple modeling of image acquisition. These principles, integrated into the classical Dead Leaves model, allow for the creation of high-quality training sets for image restoration tasks. Standard image denoising and super-resolution networks trained on these datasets achieve performance comparable to those trained on natural image datasets. The motivation behind this approach stems from the limitations of Deep Neural Networks in image restoration tasks. Despite their impressive performance, these networks are often poorly understood and prone to biases inherited from standard natural image training sets. To mitigate these issues, we emphasize the need for a better control over training sets, particularly through the use of synthetic and abstract datasets. Furthermore, our work includes a detailed analysis of the principles considered, identifying which image properties are necessary for maintaining high performance, thus taking a first step towards explainability. Besides, we show that neural networks trained with our synthetic sets naturally inherit robustness to the invariance properties of these sets, namely rotation and scale.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 42 of its 103 references that are in the map. First posted on arXiv 14 Apr 2025.

Builds on

42 of 103 references.

References · 42

  1. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  2. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  3. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  4. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  5. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  6. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,457
  7. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  8. 2016Group Equivariant Convolutional Networkscited by 1,165
  9. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,059
  10. 2016Playing for Data: Ground Truth from Computer Gamescited by 818
  11. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 510
  12. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 470
30 more
  1. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 470
  2. 2022Kubric: A scalable dataset generatorcited by 381
  3. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  4. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  5. 2023PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Trackingcited by 276
  6. 2021DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effortcited by 264
  7. 2020ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulationcited by 250
  8. 2017Benchmarking Denoising Algorithms with Real Photographscited by 209
  9. 2018Multi-level Wavelet-CNN for Image Restorationcited by 184
  10. 2016EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesiscited by 178
  11. 2022Fake it till you make it: Learning transferable representations from synthetic ImageNet clonescited by 172
  12. 2018Synthetic Data Augmentation using GAN for Improved Liver Lesion Classificationcited by 136
  13. 2018Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approachcited by 119
  14. 2021AutoFlow: Learning a Better Training Set for Optical Flowcited by 102
  15. 2021Pre-training without Natural Imagescited by 100
  16. 2018Neural Nearest Neighbors Networkscited by 98
  17. 2021Learning to See by Looking at Noisecited by 92
  18. 2018How good is my GAN?cited by 74
  19. 2023Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --cited by 71
  20. 2020Rendering Natural Camera Bokeh Effect with Deep Learningcited by 57
  21. 2019Generative adversarial networks (GAN) based efficient sampling of chemical space for inverse design of inorganic materialscited by 46
  22. 2019Deep Graph-Convolutional Image Denoisingcited by 32
  23. 2021Can Vision Transformers Learn without Natural Images?cited by 32
  24. 2023Learning Weakly Convex Regularizers for Convergent Image-Reconstruction Algorithmscited by 31
  25. 2021Improving Fractal Pre-trainingcited by 26
  26. 2023Visual Atoms: Pre-training Vision Transformers with Sinusoidal Wavescited by 20
  27. 2018Deep Leaf Segmentation Using Synthetic Datacited by 19
  28. 2020BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restorationcited by 15
  29. 2023SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learningcited by 8
  30. 2018Nonlocality-Reinforced Convolutional Neural Networks for Image Denoisingcited by 6

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Ideal Observer for Segmentation of Dead Leaves Imagescited by 0