mlsanityData to 7 Oct 2026

Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation

arXiv 1704.02157 ↗First posted 7 Apr 2017cs.CVcited by 70

Not on the map. Why?

Abstract (arXiv)

This paper addresses the problem of depth estimation from a single still image. Inspired by recent works on multi- scale convolutional neural networks (CNN), we propose a deep model which fuses complementary information derived from multiple CNN side outputs. Different from previous methods, the integration is obtained by means of continuous Conditional Random Fields (CRFs). In particular, we propose two different variations, one based on a cascade of multiple CRFs, the other on a unified graphical model. By designing a novel CNN implementation of mean-field updates for continuous CRFs, we show that both proposed models can be regarded as sequential deep networks and that training can be performed end-to-end. Through extensive experimental evaluation we demonstrate the effective- ness of the proposed approach and establish new state of the art results on publicly available datasets.

Key facts. Cited by 70 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 26; 2022: 16; 2023: 13; 2024: 11; 2025: 2; 2026: 2.

70 papers.

Sort:

By area:

  1. 2021Transformer-Based Attention Networks for Continuous Pixel-Wise Predictioncited by 125
  2. 2022Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimationcited by 100
  3. 2022LocalBins: Improving Depth Estimation by Learning Local Distributionscited by 92
  4. 2021Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescuecited by 70
  5. 2023LDM3D: Latent Diffusion Model for 3Dcited by 53
  6. 2021Adaptive Surface Normal Constraint for Depth Estimationcited by 43
  7. 2021MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutionscited by 43
  8. 2021Seeing Glass: Joint Point Cloud and Depth Completion for Transparent Objectscited by 39
  9. 2021HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embeddingcited by 36
  10. 2022BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimationcited by 35
  11. 2021SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular imagescited by 33
  12. 2021Learning to Relate Depth and Semantics for Unsupervised Domain Adaptationcited by 32
38 more
  1. 2024Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Drivingcited by 30
  2. 2022DELTAR: Depth Estimation from a Light-weight ToF Sensor and RGB Imagecited by 26
  3. 2021S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representationcited by 23
  4. 2023DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generationcited by 20
  5. 2021Generalizing to the Open World: Deep Visual Odometry with Online Adaptationcited by 19
  6. 2022Depth Map Decomposition for Monocular Depth Estimationcited by 16
  7. 2022Continual Attentive Fusion for Incremental Learning in Semantic Segmentationcited by 15
  8. 2023AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimationcited by 15
  9. 2024Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Surveycited by 15
  10. 2023Single Image Depth Prediction Made Better: A Multivariate Gaussian Takecited by 14
  11. 2024Adaptive Surface Normal Constraint for Geometric Estimation from Monocular Imagescited by 14
  12. 2024Leveraging Near-Field Lighting for Monocular Depth Estimation from Endoscopy Videoscited by 14
  13. 2021PLNet: Plane and Line Priors for Unsupervised Indoor Depth Estimationcited by 12
  14. 2022AR-NeRF: Unsupervised Learning of Depth and Defocus Effects from Natural Images with Aperture Rendering Neural Radiance Fieldscited by 12
  15. 2024Quantifying Task Priority for Multi-Task Optimizationcited by 10
  16. 2021EdgeConv with Attention Module for Monocular Depth Estimationcited by 9
  17. 2022GeoFill: Reference-Based Image Inpainting with Better Geometric Understandingcited by 9
  18. 2023Milestones in Autonomous Driving and Intelligent Vehicles Part II: Perception and Planningcited by 9
  19. 2023WS-SfMLearner: Self-supervised Monocular Depth and Ego-motion Estimation on Surgical Videos with Unknown Camera Parameterscited by 9
  20. 2025Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokenscited by 9
  21. 2021Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Predictioncited by 8
  22. 2021Boundary-induced and scene-aggregated network for monocular depth predictioncited by 8
  23. 2023Contrastive Multi-Task Dense Predictioncited by 8
  24. 2021Self-supervised Depth Estimation Leveraging Global Perception and Geometric Smoothness Using On-board Videoscited by 7
  25. 2022Vision-Based Environmental Perception for Autonomous Drivingcited by 7
  26. 2023Deeper into Self-Supervised Monocular Indoor Depth Estimationcited by 7
  27. 2024Self-supervised Monocular Depth Estimation on Water Scenes via Specular Reflection Priorcited by 7
  28. 2022Pyramid Frequency Network with Spatial Attention Residual Refinement Module for Monocular Depth Estimationcited by 6
  29. 2024Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinementcited by 5
  30. 2021Unsupervised Learning of Depth and Depth-of-Field Effect from Natural Images with Aperture Rendering Generative Adversarial Networkscited by 4
  31. 2021Unsupervised Monocular Depth Perception: Focusing on Moving Objectscited by 4
  32. 2022UAMD-Net: A Unified Adaptive Multimodal Neural Network for Dense Depth Completioncited by 4
  33. 2022Beyond Visual Field of View: Perceiving 3D Environment with Echoes and Visioncited by 4
  34. 2023Depth Estimation from a Single Optical Encoded Image using a Learned Colored-Coded Aperturecited by 3
  35. 2024Large Language Models Can Understanding Depth from Monocular Imagescited by 3
  36. 2021Variational Structured Attention Networks for Deep Visual Representation Learningcited by 2
  37. 2021A Novel 3D-UNet Deep Learning Framework Based on High-Dimensional Bilateral Grid for Edge Consistent Single Image Depth Estimationcited by 2
  38. 2021CI-Net: Contextual Information for Joint Semantic Segmentation and Depth Estimationcited by 2

50 most cited of 70 All 70 (JSON)