# Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problem

arXiv: https://arxiv.org/abs/2210.00411 · HTML: https://mlsanity.com/paper/2210.00411/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 54 references that are in the map.
- First posted on arXiv 2 Oct 2022.

## Builds on (most cited first, 30 of 42)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1812.07179/) (2018)
- [3D Packing for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/1905.02693/) (2019)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation](https://mlsanity.com/paper/1805.09806/) (2018)
- [Consistent Video Depth Estimation](https://mlsanity.com/paper/2004.15021/) (2020)
- [PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition](https://mlsanity.com/paper/1804.03492/) (2018)
- [Proxy Anchor Loss for Deep Metric Learning](https://mlsanity.com/paper/2003.13911/) (2020)
- [Learning Fine-grained Image Similarity with Deep Ranking](https://mlsanity.com/paper/1404.4661/) (2014)
- [The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth](https://mlsanity.com/paper/2104.14540/) (2021)
- [Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/1906.06310/) (2019)
- [Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras](https://mlsanity.com/paper/1904.04998/) (2019)
- [Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos](https://mlsanity.com/paper/1811.06152/) (2018)
- [Improving Semantic Segmentation via Video Propagation and Label Relaxation](https://mlsanity.com/paper/1812.01593/) (2018)
- [Semantically-Guided Representation Learning for Self-Supervised Monocular Depth](https://mlsanity.com/paper/2002.12319/) (2020)
- [Self-Supervised Monocular Depth Hints](https://mlsanity.com/paper/1909.09051/) (2019)
- [Dataset Augmentation in Feature Space](https://mlsanity.com/paper/1702.05538/) (2017)
- [Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volume](https://mlsanity.com/paper/2003.13951/) (2020)
- [HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2012.07356/) (2020)
- [Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding](https://mlsanity.com/paper/1810.06125/) (2018)
- [Unsupervised Monocular Depth Learning in Dynamic Scenes](https://mlsanity.com/paper/2010.16404/) (2020)
- [The Edge of Depth: Explicit Constraints between Segmentation and Depth](https://mlsanity.com/paper/2004.00171/) (2020)
- [Don't Forget The Past: Recurrent Depth Estimation from Monocular Video](https://mlsanity.com/paper/2001.02613/) (2020)
- [SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimation](https://mlsanity.com/paper/1810.01849/) (2018)

## Built on by (most cited first, 20 of 20)

- [RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions](https://mlsanity.com/paper/2310.15171/) (2023)
- [PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes](https://mlsanity.com/paper/2210.01612/) (2022)
- [Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation](https://mlsanity.com/paper/2503.15905/) (2025)
- [The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation](https://mlsanity.com/paper/2307.15061/) (2023)
- [DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimation](https://mlsanity.com/paper/2405.16960/) (2024)
- [Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2212.05315/) (2022)
- [ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Prediction](https://mlsanity.com/paper/2412.11210/) (2024)
- [SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning](https://mlsanity.com/paper/2407.05283/) (2024)
- [Improving Domain Generalization in Self-supervised Monocular Depth Estimation via Stabilized Adversarial Training](https://mlsanity.com/paper/2411.02149/) (2024)
- [These Maps Are Made by Propagation: Adapting Deep Stereo Networks to Road Scenarios with Decisive Disparity Diffusion](https://mlsanity.com/paper/2411.03717/) (2024)
- [MonoPP: Metric-Scaled Self-Supervised Monocular Depth Estimation by Planar-Parallax Geometry in Automotive Applications](https://mlsanity.com/paper/2411.19717/) (2024)
- [Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2404.14908/) (2024)
- [FlowDepth: Decoupling Optical Flow for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2403.19294/) (2024)
- [MetricDepth: Enhancing Monocular Depth Estimation with Deep Metric Learning](https://mlsanity.com/paper/2412.20390/) (2024)
- [Towards Sharper Object Boundaries in Self-Supervised Depth Estimation](https://mlsanity.com/paper/2509.15987/) (2025)
- [Enhanced Object Tracking by Self-Supervised Auxiliary Depth Estimation Learning](https://mlsanity.com/paper/2405.14195/) (2024)
- [Bridging Geometric and Semantic Foundation Models for Generalized Monocular Depth Estimation](https://mlsanity.com/paper/2505.23400/) (2025)
- [UM-Depth : Uncertainty Masked Self-Supervised Monocular Depth Estimation with Visual Odometry](https://mlsanity.com/paper/2509.13713/) (2025)
- [Self-Supervised Dual-Frequency Phase Decomposition for Single-Shot Composite Fringe Projection Profilometry](https://mlsanity.com/paper/2606.21027/) (2026)
- [RealOOB: A Definition-Consistent Real-World Oriented Occlusion Boundary Benchmark](https://mlsanity.com/paper/2608.30820/) (2026)

## Abstract (arXiv)

Self-supervised monocular depth estimation (MDE) models universally suffer from the notorious edge-fattening issue. Triplet loss, as a widespread metric learning strategy, has largely succeeded in many computer vision applications. In this paper, we redesign the patch-based triplet loss in MDE to alleviate the ubiquitous edge-fattening issue. We show two drawbacks of the raw triplet loss in MDE and demonstrate our problem-driven redesigns. First, we present a min. operator based strategy applied to all negative samples, to prevent well-performing negatives sheltering the error of edge-fattening negatives. Second, we split the anchor-positive distance and anchor-negative distance from within the original triplet, which directly optimizes the positives without any mutual effect with the negatives. Extensive experiments show the combination of these two small redesigns can achieve unprecedented results: Our powerful and versatile triplet loss not only makes our model outperform all previous SoTA by a large margin, but also provides substantial performance boosts to a large number of existing models, while introducing no extra inference computation at all.