mlsanityData to 7 Oct 2026

Single Image Depth Prediction with Wavelet Decomposition

arXiv 2106.02022 ↗First posted 3 Jun 2021cs.CVcited by 34

Not on the map. Why?

Abstract (arXiv)

We present a novel method for predicting accurate depths from monocular images with high efficiency. This optimal efficiency is achieved by exploiting wavelet decomposition, which is integrated in a fully differentiable encoder-decoder architecture. We demonstrate that we can reconstruct high-fidelity depth maps by predicting sparse wavelet coefficients. In contrast with previous works, we show that wavelet coefficients can be learned without direct supervision on coefficients. Instead we supervise only the final depth image that is reconstructed through the inverse wavelet transform. We additionally show that wavelet coefficients can be learned in fully self-supervised scenarios, without access to ground-truth depth. Finally, we apply our method to different state-of-the-art monocular depth estimation models, in each case giving similar or better results compared to the original model, while requiring less than half the multiply-adds in the decoder network. Code at https://github.com/nianticlabs/wavelet-monodepth

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 46 of its 70 references that are in the map. First posted on arXiv 3 Jun 2021.

Builds on

46 of 70 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  7. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  8. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  9. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  10. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  11. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  12. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
34 more
  1. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  2. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 697
  3. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  4. 2016Learning Structured Sparsity in Deep Neural Networkscited by 538
  5. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 515
  6. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  7. 2019PointRend: Image Segmentation as Renderingcited by 439
  8. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  9. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  10. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  11. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  12. 2017Sparsity Invariant CNNscited by 325
  13. 2018Slimmable Neural Networkscited by 301
  14. 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
  15. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  16. 2019Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Camerascited by 170
  17. 2018NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applicationscited by 146
  18. 2018Evaluation of CNN-based Single-Image Depth Estimation Methodscited by 137
  19. 2018High Quality Monocular Depth Estimation via Transfer Learningcited by 133
  20. 2019Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Cameracited by 130
  21. 2019Self-Supervised Monocular Depth Hintscited by 127
  22. 2018Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layerscited by 112
  23. 2018Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understandingcited by 101
  24. 2020Convolutional Networks with Dense Connectivitycited by 98
  25. 2019FastDepth: Fast Monocular Depth Estimation on Embedded Systemscited by 93
  26. 2020Wavelet Integrated CNNs for Noise-Robust Image Classificationcited by 60
  27. 2019SharpNet: Fast and Accurate Recovery of Occluding Contours in Monocular Depth Estimationcited by 59
  28. 2020Wavelet-Based Dual-Branch Network for Image Demoireingcited by 55
  29. 2019Structure-Aware Residual Pyramid Network for Monocular Depth Estimationcited by 49
  30. 2020Predicting Sharp and Accurate Occlusion Boundaries in Monocular Depth Estimation Using Displacement Fieldscited by 40
  31. 2019Wavelet Domain Style Transfer for an Effective Perception-distortion Tradeoff in Single Image Super-Resolutioncited by 30
  32. 2018Towards real-time unsupervised monocular depth estimation on CPUcited by 26
  33. 2020Real-time single image depth perception in the wild with handheld devicescited by 18
  34. 2018CReaM: Condensed Real-time Models for Depth Prediction using Convolutional Neural Networkscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 12; 2023: 10; 2024: 4; 2025: 3; 2026: 2.

34 papers.

Sort:

By area:

  1. 2022Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patchescited by 57
  2. 2022Glass Segmentation with RGB-Thermal Image Pairscited by 26
  3. 2021Deep Depth from Focus with Differential Focus Volumecited by 20
  4. 2022Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problemcited by 20
  5. 2022Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolutioncited by 19
  6. 2022Self-distilled Feature Aggregation for Self-supervised Monocular Depth Estimationcited by 17
  7. 2023Elevation Estimation-Driven Building 3D Reconstruction from Single-View Remote Sensing Imagerycited by 17
  8. 2023Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attackscited by 17
  9. 2025RingMoE: Mixture-of-Modality-Experts Multi-Modal Foundation Models for Universal Remote Sensing Image Interpretationcited by 16
  10. 2023VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalizationcited by 15
  11. 2023WeatherDepth: Curriculum Contrastive Learning for Self-Supervised Depth Estimation under Adverse Weather Conditionscited by 15
  12. 2022DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimationcited by 12
22 more
  1. 2023MonoDiffusion: Self-Supervised Monocular Depth Estimation Using Diffusion Modelcited by 12
  2. 2023Self-Supervised Monocular Depth Estimation with Self-Reference Distillation and Disparity Offset Refinementcited by 10
  3. 2025SNeRV: Spectra-preserving Neural Representation for Videocited by 9
  4. 2022RAFT-MSF: Self-Supervised Monocular Scene Flow using Recurrent Optimizercited by 7
  5. 2022Multi-Scale Wavelet Transformer for Face Forgery Detectioncited by 6
  6. 2024Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attackscited by 5
  7. 2022Hybrid Skip: A Biologically Inspired Skip Connection for the UNet Architecturecited by 3
  8. 2022Neural Contourlet Network for Monocular 360 Depth Estimationcited by 3
  9. 2022Frequency-Aware Self-Supervised Monocular Depth Estimationcited by 3
  10. 2023Dynamic Frame Interpolation in Wavelet Domaincited by 3
  11. 2024XctDiff: Reconstruction of CT Images with Consistent Anatomical Structures from a Single Radiographic Projection Imagecited by 3
  12. 2025SAMwave: Wavelet-Driven Feature Enrichment for Effective Adaptation of Segment Anything Modelcited by 3
  13. 2021Object-aware Monocular Depth Prediction with Instance Convolutionscited by 2
  14. 2023FSNet: Redesign Self-Supervised MonoDepth for Full-Scale Depth Prediction for Autonomous Drivingcited by 2
  15. 2024PASTA: Towards Flexible and Efficient HDR Imaging Via Progressively Aggregated Spatio-Temporal Alignmentcited by 2
  16. 2022Rethinking Skip Connections in Encoder-decoder Networks for Monocular Depth Estimationcited by 1
  17. 2023InSpaceType: Reconsider Space Type in Indoor Monocular Depth Estimationcited by 1
  18. 2023FocDepthFormer: Transformer with latent LSTM for Depth Estimation from Focal Stackcited by 1
  19. 2021Style Transfer with Target Feature Palette and Attention Coloringcited by 0
  20. 2024InSpaceType: Dataset and Benchmark for Reconsidering Cross-Space Type Performance in Indoor Monocular Depthcited by 0
  21. 2026Spectral Rectification for Parameter-Efficient Adaptation of Foundation Models in Colonoscopy Depth Estimationcited by 0
  22. 2026FAAR: Efficient Frequency-Aware Multi-Task Fine-Tuning via Automatic Rank Selectioncited by 0