mlsanityData to 7 Oct 2026

G2-MonoDepth: A General Framework of Generalized Depth Inference from Monocular RGB+X Data

arXiv 2310.15422 ↗First posted 24 Oct 2023cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Monocular depth inference is a fundamental problem for scene perception of robots. Specific robots may be equipped with a camera plus an optional depth sensor of any type and located in various scenes of different scales, whereas recent advances derived multiple individual sub-tasks. It leads to additional burdens to fine-tune models for specific robots and thereby high-cost customization in large-scale industrialization. This paper investigates a unified task of monocular depth inference, which infers high-quality depth maps from all kinds of input raw data from various robots in unseen scenes. A basic benchmark G2-MonoDepth is developed for this task, which comprises four components: (a) a unified data representation RGB+X to accommodate RGB plus raw depth with diverse scene scale/semantics, depth sparsity ([0%, 100%]) and errors (holes/noises/blurs), (b) a novel unified loss to adapt to diverse depth sparsity/errors of input raw data and diverse scales of output scenes, (c) an improved network to well propagate diverse scene scales from input to output, and (d) a data augmentation pipeline to simulate all types of real artifacts in raw depth maps for training. G2-MonoDepth is applied in three sub-tasks including depth estimation, depth completion with different sparsity, and depth enhancement in unseen scenes, and it always outperforms SOTA baselines on both real-world data and synthetic data.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 42 of its 67 references that are in the map. First posted on arXiv 24 Oct 2023.

Builds on

42 of 67 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  6. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  7. 2021Vision Transformers for Dense Predictioncited by 1,789
  8. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  9. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  10. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  11. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  12. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
30 more
  1. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
  2. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  3. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  4. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  5. 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 340
  6. 2020ReZero is All You Need: Fast Convergence at Large Depthcited by 260
  7. 2019DIODE: A Dense Indoor and Outdoor DEpth Datasetcited by 236
  8. 2016DeMoN: Depth and Motion Network for Learning Monocular Stereocited by 200
  9. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 194
  10. 2016Single-Image Depth Perception in the Wildcited by 179
  11. 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
  12. 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 159
  13. 2022NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimationcited by 151
  14. 2018Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Cameracited by 140
  15. 2018Evaluation of CNN-based Single-Image Depth Estimation Methodscited by 137
  16. 2018Learning Depth with Convolutional Spatial Propagation Networkcited by 135
  17. 2018DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Imagecited by 129
  18. 2019Learning Guided Convolutional Network for Depth Completioncited by 111
  19. 2018Deep Depth Completion of a Single RGB-D Imagecited by 110
  20. 2020A Survey on Deep Learning Techniques for Stereo-based Depth Estimationcited by 90
  21. 2019CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depthcited by 75
  22. 2019Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimationcited by 61
  23. 2019Deformable Kernel Networks for Joint Image Filteringcited by 59
  24. 2021Depth Completion with Twin Surface Extrapolation at Occlusion Boundariescited by 41
  25. 2021Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completioncited by 39
  26. 2021Joint Implicit Image Function for Guided Depth Super-Resolutioncited by 31
  27. 2019Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimationcited by 23
  28. 2021S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representationcited by 23
  29. 2019Generating and Exploiting Probabilistic Monocular Depth Estimatescited by 18
  30. 2019Semi-Supervised Adversarial Monocular Depth Estimationcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 5.

12 papers.

  1. 2024OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integrationcited by 28
  2. 2025Distilling Monocular Foundation Model for Fine-grained Depth Completioncited by 14
  3. 2024Scale Propagation Network for Generalizable Depth Completioncited by 5
  4. 2026Any to Full: Prompting Depth Anything for Depth Completion in One Stagecited by 5
  5. 2025PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistencycited by 4
  6. 2026Large Depth Completion Model from Sparse Observationscited by 3
  7. 2025Propagating Sparse Depth via Depth Foundation Model for Out-of-Distribution Depth Completioncited by 2
  8. 2025Multi-Order Matching Network for Alignment-Free Depth Super-Resolutioncited by 1
  9. 2026The Midas Touch for Metric Depthcited by 1
  10. 2025Real-World Depth Recovery via Structure Uncertainty Modeling and Inaccurate GT Depth Fittingcited by 0
  11. 2026DegBins: Degradation-Driven Binning for Depth Super-Resolutioncited by 0
  12. 2026UniT: Unified Geometry Learning with Group Autoregressive Transformercited by 0