# DevNet: Self-supervised Monocular Depth Learning via Density Volume Construction

arXiv: https://arxiv.org/abs/2209.06351 · HTML: https://mlsanity.com/paper/2209.06351/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 53 references that are in the map.
- First posted on arXiv 14 Sep 2022.

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes](https://mlsanity.com/paper/2011.13084/) (2020)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture](https://mlsanity.com/paper/1411.4734/) (2014)
- [3D Packing for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/1905.02693/) (2019)
- [From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation](https://mlsanity.com/paper/1907.10326/) (2019)
- [INeRF: Inverting Neural Radiance Fields for Pose Estimation](https://mlsanity.com/paper/2012.05877/) (2020)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](https://mlsanity.com/paper/1803.02276/) (2018)
- [Categorical Depth Distribution Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.01100/) (2021)
- [Neural Radiance Flow for 4D View Synthesis and Video Processing](https://mlsanity.com/paper/2012.09790/) (2020)
- [Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video](https://mlsanity.com/paper/1908.10553/) (2019)
- [D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry](https://mlsanity.com/paper/2003.01060/) (2020)
- [NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo](https://mlsanity.com/paper/2109.01129/) (2021)
- [Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras](https://mlsanity.com/paper/1904.04998/) (2019)
- [Learning Depth-Guided Convolutions for Monocular 3D Object Detection](https://mlsanity.com/paper/1912.04799/) (2019)
- [Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction](https://mlsanity.com/paper/1803.03893/) (2018)
- [Learning Depth from Monocular Videos using Direct Methods](https://mlsanity.com/paper/1712.00175/) (2017)
- [NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation](https://mlsanity.com/paper/2203.01502/) (2022)
- [Feature-metric Loss for Self-supervised Learning of Depth and Egomotion](https://mlsanity.com/paper/2007.10603/) (2020)
- [Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volume](https://mlsanity.com/paper/2003.13951/) (2020)
- [Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding](https://mlsanity.com/paper/1810.06125/) (2018)
- [Towards Better Generalization: Joint Depth-Pose Learning without PoseNet](https://mlsanity.com/paper/2004.01314/) (2020)
- [The Edge of Depth: Explicit Constraints between Segmentation and Depth](https://mlsanity.com/paper/2004.00171/) (2020)

## Built on by (most cited first, 22 of 22)

- [SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction](https://mlsanity.com/paper/2311.12754/) (2023)
- [Behind the Scenes: Density Fields for Single View Reconstruction](https://mlsanity.com/paper/2301.07668/) (2023)
- [DynPoint: Dynamic Neural Point For View Synthesis](https://mlsanity.com/paper/2310.18999/) (2023)
- [Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation](https://mlsanity.com/paper/2503.15905/) (2025)
- [AIC MLLM: Autonomous Interactive Correction MLLM for Robust Robotic Manipulation](https://mlsanity.com/paper/2406.11548/) (2024)
- [Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks](https://mlsanity.com/paper/2301.13487/) (2023)
- [ConsistentNeRF: Enhancing Neural Radiance Fields with 3D Consistency for Sparse View Synthesis](https://mlsanity.com/paper/2305.11031/) (2023)
- [GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes](https://mlsanity.com/paper/2309.16019/) (2023)
- [Manydepth2: Motion-Aware Self-Supervised Monocular Depth Estimation in Dynamic Scenes](https://mlsanity.com/paper/2312.15268/) (2023)
- [Mono-ViFI: A Unified Learning Framework for Self-supervised Single- and Multi-frame Monocular Depth Estimation](https://mlsanity.com/paper/2407.14126/) (2024)
- [Boosting Self-Supervision for Single-View Scene Completion via Knowledge Distillation](https://mlsanity.com/paper/2404.07933/) (2024)
- [Dusk Till Dawn: Self-supervised Nighttime Stereo Depth Estimation using Visual Foundation Models](https://mlsanity.com/paper/2405.11158/) (2024)
- [Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attacks](https://mlsanity.com/paper/2406.05857/) (2024)
- [AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization](https://mlsanity.com/paper/2308.10001/) (2023)
- [Towards Better Data Exploitation in Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2309.05254/) (2023)
- [Neural Surface Reconstruction from Sparse Views Using Epipolar Geometry](https://mlsanity.com/paper/2406.04301/) (2024)
- [SplatMesh: Interactive 3D Segmentation and Editing Using Mesh-Based Gaussian Splatting](https://mlsanity.com/paper/2312.15856/) (2023)
- [NeuGrasp: Generalizable Neural Surface Reconstruction with Background Priors for Material-Agnostic Object Grasp Detection](https://mlsanity.com/paper/2503.03511/) (2025)
- [Novel View Synthesis with View-Dependent Effects from a Single Image](https://mlsanity.com/paper/2312.08071/) (2023)
- [WSCLoc: Weakly-Supervised Sparse-View Camera Relocalization](https://mlsanity.com/paper/2403.15272/) (2024)
- [Endoscopic Depth Estimation Based on Deep Learning: A Survey](https://mlsanity.com/paper/2507.20881/) (2025)
- [UM-Depth : Uncertainty Masked Self-Supervised Monocular Depth Estimation with Visual Odometry](https://mlsanity.com/paper/2509.13713/) (2025)

## Abstract (arXiv)

Self-supervised depth learning from monocular images normally relies on the 2D pixel-wise photometric relation between temporally adjacent image frames. However, they neither fully exploit the 3D point-wise geometric correspondences, nor effectively tackle the ambiguities in the photometric warping caused by occlusions or illumination inconsistency. To address these problems, this work proposes Density Volume Construction Network (DevNet), a novel self-supervised monocular depth learning framework, that can consider 3D spatial information, and exploit stronger geometric constraints among adjacent camera frustums. Instead of directly regressing the pixel value from a single image, our DevNet divides the camera frustum into multiple parallel planes and predicts the pointwise occlusion probability density on each plane. The final depth map is generated by integrating the density along corresponding rays. During the training process, novel regularization strategies and loss functions are introduced to mitigate photometric ambiguities and overfitting. Without obviously enlarging model parameters size or running time, DevNet outperforms several representative baselines on both the KITTI-2015 outdoor dataset and NYU-V2 indoor dataset. In particular, the root-mean-square-deviation is reduced by around 4% with DevNet on both KITTI-2015 and NYU-V2 in the task of depth estimation. Code is available at https://github.com/gitkaichenzhou/DevNet.