# Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumes

arXiv: https://arxiv.org/abs/2008.03633 · HTML: https://mlsanity.com/paper/2008.03633/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Aug 2020.

## Built on by (most cited first, 30 of 50)

- [The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth](https://mlsanity.com/paper/2104.14540/) (2021)
- [Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction](https://mlsanity.com/paper/2103.12091/) (2021)
- [SimpleRecon: 3D Reconstruction Without 3D Convolutions](https://mlsanity.com/paper/2208.14743/) (2022)
- [Self-Supervised Monocular Depth Estimation with Internal Feature Fusion](https://mlsanity.com/paper/2110.09482/) (2021)
- [Behind the Scenes: Density Fields for Single View Reconstruction](https://mlsanity.com/paper/2301.07668/) (2023)
- [Learning Depth Estimation for Transparent and Mirror Surfaces](https://mlsanity.com/paper/2307.15052/) (2023)
- [Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces](https://mlsanity.com/paper/2301.08245/) (2023)
- [PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes](https://mlsanity.com/paper/2210.01612/) (2022)
- [PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Loss](https://mlsanity.com/paper/2103.07362/) (2021)
- [Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2110.08192/) (2021)
- [Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation](https://mlsanity.com/paper/2108.12545/) (2021)
- [DevNet: Self-supervised Monocular Depth Learning via Density Volume Construction](https://mlsanity.com/paper/2209.06351/) (2022)
- [Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTV](https://mlsanity.com/paper/2307.10713/) (2023)
- [SQLdepth: Generalizable Self-Supervised Fine-Structured Monocular Depth Estimation](https://mlsanity.com/paper/2309.00526/) (2023)
- [Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation](https://mlsanity.com/paper/2503.15905/) (2025)
- [Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problem](https://mlsanity.com/paper/2210.00411/) (2022)
- [Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that Matter](https://mlsanity.com/paper/2208.01489/) (2022)
- [Self-distilled Feature Aggregation for Self-supervised Monocular Depth Estimation](https://mlsanity.com/paper/2209.07088/) (2022)
- [DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibrium](https://mlsanity.com/paper/2304.03560/) (2023)
- [The Monocular Depth Estimation Challenge](https://mlsanity.com/paper/2211.12174/) (2022)
- [GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes](https://mlsanity.com/paper/2309.16019/) (2023)
- [From-Ground-To-Objects: Coarse-to-Fine Self-supervised Monocular Depth Estimation of Dynamic Objects with Ground Contact Prior](https://mlsanity.com/paper/2312.10118/) (2023)
- [Self-Supervised Learning of Domain Invariant Features for Depth Estimation](https://mlsanity.com/paper/2106.02594/) (2021)
- [Mono-ViFI: A Unified Learning Framework for Self-supervised Single- and Multi-frame Monocular Depth Estimation](https://mlsanity.com/paper/2407.14126/) (2024)
- [Two-in-One Depth: Bridging the Gap Between Monocular and Binocular Self-supervised Depth Estimation](https://mlsanity.com/paper/2309.00933/) (2023)
- [Lightweight Monocular Depth with a Novel Neural Architecture Search Method](https://mlsanity.com/paper/2108.11105/) (2021)
- [Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTV](https://mlsanity.com/paper/2403.01569/) (2024)
- [Learning Occlusion-Aware Coarse-to-Fine Depth Map for Self-supervised Monocular Depth Estimation](https://mlsanity.com/paper/2203.10925/) (2022)
- [MonoProb: Self-Supervised Monocular Depth Estimation with Interpretable Uncertainty](https://mlsanity.com/paper/2311.06137/) (2023)
- [Boosting Self-Supervision for Single-View Scene Completion via Knowledge Distillation](https://mlsanity.com/paper/2404.07933/) (2024)

## Abstract (arXiv)

Self-supervised depth estimators have recently shown results comparable to the supervised methods on the challenging single image depth estimation (SIDE) task, by exploiting the geometrical relations between target and reference views in the training data. However, previous methods usually learn forward or backward image synthesis, but not depth estimation, as they cannot effectively neglect occlusions between the target and the reference images. Previous works rely on rigid photometric assumptions or the SIDE network to infer depth and occlusions, resulting in limited performance. On the other hand, we propose a method to "Forget About the LiDAR" (FAL), for the training of depth estimators, with Mirrored Exponential Disparity (MED) probability volumes, from which we obtain geometrically inspired occlusion maps with our novel Mirrored Occlusion Module (MOM). Our MOM does not impose a burden on our FAL-net. Contrary to the previous methods that learn SIDE from stereo pairs by regressing disparity in the linear space, our FAL-net regresses disparity by binning it into the exponential space, which allows for better detection of distant and nearby objects. We define a two-step training strategy for our FAL-net: It is first trained for view synthesis and then fine-tuned for depth estimation with our MOM. Our FAL-net is remarkably light-weight and outperforms the previous state-of-the-art methods with 8x fewer parameters and 3x faster inference speeds on the challenging KITTI dataset. We present extensive experimental results on the KITTI, CityScapes, and Make3D datasets to verify our method's effectiveness. To the authors' best knowledge, the presented method performs the best among all the previous self-supervised methods until now.