# Predicting Sharp and Accurate Occlusion Boundaries in Monocular Depth Estimation Using Displacement Fields

arXiv: https://arxiv.org/abs/2002.12730 · HTML: https://mlsanity.com/paper/2002.12730/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2020.

## Built on by (most cited first, 30 of 40)

- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior](https://mlsanity.com/paper/2204.02091/) (2022)
- [Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging](https://mlsanity.com/paper/2105.14021/) (2021)
- [VA-DepthNet: A Variational Approach to Single Image Depth Prediction](https://mlsanity.com/paper/2302.06556/) (2023)
- [Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail](https://mlsanity.com/paper/2412.04472/) (2024)
- [Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation](https://mlsanity.com/paper/2108.07628/) (2021)
- [Depth Completion with Twin Surface Extrapolation at Occlusion Boundaries](https://mlsanity.com/paper/2104.02253/) (2021)
- [Pano3D: A Holistic Benchmark and a Solid Baseline for 360o Depth Estimation](https://mlsanity.com/paper/2109.02749/) (2021)
- [Single Image Depth Prediction with Wavelet Decomposition](https://mlsanity.com/paper/2106.02022/) (2021)
- [RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth](https://mlsanity.com/paper/2108.00616/) (2021)
- [Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces](https://mlsanity.com/paper/2301.08245/) (2023)
- [Local Similarity Pattern and Cost Self-Reassembling for Deep Stereo Matching Networks](https://mlsanity.com/paper/2112.01011/) (2021)
- [PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes](https://mlsanity.com/paper/2210.01612/) (2022)
- [Exploring Sparse Visual Prompt for Domain Adaptive Dense Prediction](https://mlsanity.com/paper/2303.09792/) (2023)
- [OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations](https://mlsanity.com/paper/2406.11711/) (2024)
- [From 2D to 3D: Re-thinking Benchmarking of Monocular Depth Prediction](https://mlsanity.com/paper/2203.08122/) (2022)
- [MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformer](https://mlsanity.com/paper/2303.13018/) (2023)
- [Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting](https://mlsanity.com/paper/2506.05327/) (2025)
- [A Survey on RGB-D Datasets](https://mlsanity.com/paper/2201.05761/) (2022)
- [CroMo: Cross-Modal Learning for Monocular Depth Estimation](https://mlsanity.com/paper/2203.12485/) (2022)
- [Boundary-induced and scene-aggregated network for monocular depth prediction](https://mlsanity.com/paper/2102.13258/) (2021)
- [Unsupervised Spike Depth Estimation via Cross-modality Cross-domain Knowledge Transfer](https://mlsanity.com/paper/2208.12527/) (2022)
- [Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2212.05315/) (2022)
- [Proximity QA: Unleashing the Power of Multi-Modal Large Language Models for Spatial Proximity Analysis](https://mlsanity.com/paper/2401.17862/) (2024)
- [Virtual Occlusions Through Implicit Depth](https://mlsanity.com/paper/2305.07014/) (2023)
- [Improving Domain Generalization in Self-supervised Monocular Depth Estimation via Stabilized Adversarial Training](https://mlsanity.com/paper/2411.02149/) (2024)
- [MT-ORL: Multi-Task Occlusion Relationship Learning](https://mlsanity.com/paper/2108.05722/) (2021)
- [The Devil is in the Edges: Monocular Depth Estimation with Edge-aware Consistency Fusion](https://mlsanity.com/paper/2404.00373/) (2024)
- [NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfaces](https://mlsanity.com/paper/2506.05815/) (2025)
- [Object-aware Monocular Depth Prediction with Instance Convolutions](https://mlsanity.com/paper/2112.01521/) (2021)

## Abstract (arXiv)

Current methods for depth map prediction from monocular images tend to predict smooth, poorly localized contours for the occlusion boundaries in the input image. This is unfortunate as occlusion boundaries are important cues to recognize objects, and as we show, may lead to a way to discover new objects from scene reconstruction. To improve predicted depth maps, recent methods rely on various forms of filtering or predict an additive residual depth map to refine a first estimate. We instead learn to predict, given a depth map predicted by some reconstruction method, a 2D displacement field able to re-sample pixels around the occlusion boundaries into sharper reconstructions. Our method can be applied to the output of any depth estimation method, in an end-to-end trainable fashion. For evaluation, we manually annotated the occlusion boundaries in all the images in the test split of popular NYUv2-Depth dataset. We show that our approach improves the localization of occlusion boundaries for all state-of-the-art monocular depth estimation methods that we could evaluate, without degrading the depth accuracy for the rest of the images.