mlsanityData to 7 Oct 2026

Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Report

arXiv 2211.04470 ↗First posted 7 Nov 2022cs.CV eess.IVcited by 4

Not on the map. Why?

Abstract (arXiv)

Various depth estimation models are now widely used on many mobile and IoT devices for image segmentation, bokeh effect rendering, object tracking and many other mobile tasks. Thus, it is very crucial to have efficient and accurate depth estimation models that can run fast on low-power mobile chipsets. In this Mobile AI challenge, the target was to develop deep learning-based single image depth estimation solutions that can show a real-time performance on IoT platforms and smartphones. For this, the participants used a large-scale RGB-to-depth dataset that was collected with the ZED stereo camera capable to generated depth maps for objects located at up to 50 meters. The runtime of all models was evaluated on the Raspberry Pi 4 platform, where the developed solutions were able to generate VGA resolution depth maps at up to 27 FPS while achieving high fidelity results. All models developed in the challenge are also compatible with any Android or Linux-based mobile devices, their detailed description is provided in this paper.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 56 of its 81 references that are in the map. First posted on arXiv 7 Nov 2022.

Builds on

56 of 81 references.

References · 56

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  5. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  6. 2019Searching for MobileNetV3cited by 1,984
  7. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  8. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  9. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  10. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  11. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  12. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 480
38 more
  1. 2019GhostNet: More Features from Cheap Operationscited by 410
  2. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  3. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 379
  4. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  5. 2017Sparsity Invariant CNNscited by 325
  6. 2019Structured Knowledge Distillation for Dense Predictioncited by 277
  7. 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 265
  8. 2017A General and Adaptive Robust Loss Functioncited by 236
  9. 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 233
  10. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 233
  11. 2019MetaPruning: Meta Learning for Automatic Neural Network Channel Pruningcited by 226
  12. 2016Single-Image Depth Perception in the Wildcited by 179
  13. 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
  14. 2017DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networkscited by 156
  15. 2020FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensionscited by 152
  16. 2019Quantization Networkscited by 151
  17. 2020Replacing Mobile Camera ISP with a Single Deep Learning Modelcited by 108
  18. 2014Deep Convolutional Neural Fields for Depth Estimation from a Single Imagecited by 106
  19. 2019FastDepth: Fast Monocular Depth Estimation on Embedded Systemscited by 93
  20. 2019Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networkscited by 87
  21. 2020NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Resultscited by 83
  22. 2019AI Benchmark: All About Deep Learning on Smartphones in 2019cited by 76
  23. 2018AI Benchmark: Running Deep Neural Networks on Android Smartphonescited by 75
  24. 2019Learning Filter Basis for Convolutional Neural Network Compressioncited by 57
  25. 2020Rendering Natural Camera Bokeh Effect with Deep Learningcited by 57
  26. 2020NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Resultscited by 51
  27. 2020AIM 2020 Challenge on Learned Image Signal Processing Pipelinecited by 44
  28. 2018PIRM Challenge on Perceptual Image Enhancement on Smartphones: Reportcited by 38
  29. 2021Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Reportcited by 34
  30. 2021Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Reportcited by 34
  31. 2017WESPE: Weakly Supervised Photo Enhancer for Digital Camerascited by 32
  32. 2020AIM 2020 Challenge on Rendering Realistic Bokehcited by 26
  33. 2020T-Basis: a Compact Representation for Neural Networkscited by 21
  34. 2022AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Resultscited by 20
  35. 2021Collapsible Linear Blocks for Super-Efficient Super Resolutioncited by 19
  36. 2021Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Reportcited by 19
  37. 2021Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Reportcited by 19
  38. 2020Deploying Image Deblurring across Mobile Devices: A Perspective of Quality and Latencycited by 16

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3.

4 papers.

  1. 2024Towards Robust Monocular Depth Estimation in Non-Lambertian Surfacescited by 9
  2. 2023Diffusion-Augmented Depth Prediction with Sparse Annotationscited by 8
  3. 2024Virtually Enriched NYU Depth V2 Dataset for Monocular Depth Estimation: Do We Need Artificial Augmentation?cited by 1
  4. 2024Variable Aperture Bokeh Rendering via Customized Focal Plane Guidancecited by 1