mlsanityData to 14 Oct 2026

Lightweight Monocular Depth Estimation through Guided Decoding

arXiv 2203.04206 ↗First posted 8 Mar 2022cs.CV cs.ROcited by 14

Not on the map. Why?

Abstract (arXiv)

We present a lightweight encoder-decoder architecture for monocular depth estimation, specifically designed for embedded platforms. Our main contribution is the Guided Upsampling Block (GUB) for building the decoder of our model. Motivated by the concept of guided image filtering, GUB relies on the image to guide the decoder on upsampling the feature representation and the depth map reconstruction, achieving high resolution results with fine-grained details. Based on multiple GUBs, our model outperforms the related methods on the NYU Depth V2 dataset in terms of accuracy while delivering up to 35.1 fps on the NVIDIA Jetson Nano and up to 144.5 fps on the NVIDIA Xavier NX. Similarly, on the KITTI dataset, inference is possible with up to 23.7 fps on the Jetson Nano and 102.9 fps on the Xavier NX. Our code and models are made publicly available.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 29 of its 45 references that are in the map. First posted on arXiv 8 Mar 2022.

Builds on

29 of 45 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  6. 2017Squeeze-and-Excitation Networkscited by 4,789
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  8. 2021Vision Transformers for Dense Predictioncited by 1,803
  9. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  10. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  11. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 723
  12. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
17 more
  1. 2020AdaBins: Depth Estimation using Adaptive Binscited by 601
  2. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 403
  3. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 382
  4. 2018AMC: AutoML for Model Compression and Acceleration on Mobile Devicescited by 378
  5. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  6. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 234
  7. 2018NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applicationscited by 147
  8. 2018High Quality Monocular Depth Estimation via Transfer Learningcited by 133
  9. 2019FastDepth: Fast Monocular Depth Estimation on Embedded Systemscited by 94
  10. 2021Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenescited by 89
  11. 2019HarDNet: A Low Memory Traffic Networkcited by 76
  12. 2018Towards real-time unsupervised monocular depth estimation on CPUcited by 26
  13. 2020Traffic Control Gesture Recognition for Autonomous Vehiclescited by 24
  14. 2020Real-time single image depth perception in the wild with handheld devicescited by 19
  15. 2018Adversarial Network Compressioncited by 9
  16. 2019DeepLocalization: Landmark-based Self-Localization with Deep Neural Networkscited by 9
  17. 2021Visual Domain Adaptation for Monocular Depth Estimation on Resource-Constrained Hardwarecited by 3

Built on by

Cited by year (2026 to 14 Oct)

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

14 papers.

Sort:

By area:

  1. 2023Real-time Monocular Depth Estimation on Embedded Systemscited by 6
  2. 2022Deep Learning on Home Drone: Searching for the Optimal Architecturecited by 5
  3. 2023PromptMix: Text-to-image diffusion models enhance the performance of lightweight networkscited by 3
  4. 2022LightDepth: A Resource Efficient Depth Estimation Approach for Dealing with Ground Truth Sparsity via Curriculum Learningcited by 2
  5. 2023Lightweight Monocular Depth Estimation via Token-Sharing Transformercited by 2
  6. 2025Visual Autoregressive Modelling for Monocular Depth Estimationcited by 2
  7. 2024Consistency Regularisation for Unsupervised Domain Adaptation in Monocular Depth Estimationcited by 1
  8. 2026ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Devicecited by 1
  9. 2026DepthART: Scaling Foundation Monocular Depth to Tiny Modelscited by 1
  10. 2022Lightweight Monocular Depth Estimation with an Edge Guided Networkcited by 0
  11. 2024Enhanced Encoder-Decoder Architecture for Accurate Monocular Depth Estimationcited by 0
  12. 2025LMDepth: Lightweight Mamba-based Monocular Depth Estimation for Real-World Deploymentcited by 0
2 more
  1. 2025BoRe-Depth: Self-supervised Monocular Depth Estimation with Boundary Refinement for Embedded Systemscited by 0
  2. 2025Real-Time Object Tracking with On-Device Deep Learning for Adaptive Beamforming in Dynamic Acoustic Environmentscited by 0