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

arXiv: https://arxiv.org/abs/1803.00891 · HTML: https://mlsanity.com/paper/1803.00891/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2018.

## Built on by (most cited first, 19 of 19)

- [NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation](https://mlsanity.com/paper/2203.01502/) (2022)
- [Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Survey](https://mlsanity.com/paper/2406.19675/) (2024)
- [Adaptive Surface Normal Constraint for Geometric Estimation from Monocular Images](https://mlsanity.com/paper/2402.05869/) (2024)
- [Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction](https://mlsanity.com/paper/2101.02843/) (2021)
- [Moving SLAM: Fully Unsupervised Deep Learning in Non-Rigid Scenes](https://mlsanity.com/paper/2105.02195/) (2021)
- [Vision-Based Environmental Perception for Autonomous Driving](https://mlsanity.com/paper/2212.11453/) (2022)
- [Multi-Domain Image-to-Image Translation with Adaptive Inference Graph](https://mlsanity.com/paper/2101.03806/) (2021)
- [Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images](https://mlsanity.com/paper/2109.02288/) (2021)
- [Physics-informed Imitative Reinforcement Learning for Real-world Driving](https://mlsanity.com/paper/2407.02508/) (2024)
- [DynOcc: Learning Single-View Depth from Dynamic Occlusion Cues](https://mlsanity.com/paper/2103.16706/) (2021)
- [Monocular Depth Estimation with Sharp Boundary](https://mlsanity.com/paper/2110.05885/) (2021)
- [InSpaceType: Reconsider Space Type in Indoor Monocular Depth Estimation](https://mlsanity.com/paper/2309.13516/) (2023)
- [MoDiT: Learning Highly Consistent 3D Motion Coefficients with Diffusion Transformer for Talking Head Generation](https://mlsanity.com/paper/2507.05092/) (2025)
- [Extraction of Key-frames of Endoscopic Videos by using Depth Information](https://mlsanity.com/paper/2107.00005/) (2021)
- [Learning Monocular Depth in Dynamic Environment via Context-aware Temporal Attention](https://mlsanity.com/paper/2305.07397/) (2023)
- [InSpaceType: Dataset and Benchmark for Reconsidering Cross-Space Type Performance in Indoor Monocular Depth](https://mlsanity.com/paper/2408.13708/) (2024)
- [Depth as Points: Center Point-based Depth Estimation](https://mlsanity.com/paper/2504.18773/) (2025)
- [Bridging Geometric and Semantic Foundation Models for Generalized Monocular Depth Estimation](https://mlsanity.com/paper/2505.23400/) (2025)
- [GenOpticalFlow: A Generative Approach to Unsupervised Optical Flow Learning](https://mlsanity.com/paper/2603.22270/) (2026)

## Abstract (arXiv)

Depth cues have been proved very useful in various computer vision and robotic tasks. This paper addresses the problem of monocular depth estimation from a single still image. Inspired by the effectiveness of 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 using concatenation or weighted average schemes, 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 an extensive experimental evaluation, we demonstrate the effectiveness of the proposed approach and establish new state of the art results for the monocular depth estimation task on three publicly available datasets, i.e. NYUD-V2, Make3D and KITTI.