# Wasserstein Distances for Stereo Disparity Estimation

arXiv: https://arxiv.org/abs/2007.03085 · HTML: https://mlsanity.com/paper/2007.03085/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2020.

## Built on by (most cited first, 30 of 38)

- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [SMD-Nets: Stereo Mixture Density Networks](https://mlsanity.com/paper/2104.03866/) (2021)
- [LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector](https://mlsanity.com/paper/2108.08258/) (2021)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [VPFNet: Improving 3D Object Detection with Virtual Point based LiDAR and Stereo Data Fusion](https://mlsanity.com/paper/2111.14382/) (2021)
- [Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitation](https://mlsanity.com/paper/2108.05773/) (2021)
- [Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective](https://mlsanity.com/paper/2203.10887/) (2022)
- [Local Similarity Pattern and Cost Self-Reassembling for Deep Stereo Matching Networks](https://mlsanity.com/paper/2112.01011/) (2021)
- [A Survey on Deep Stereo Matching in the Twenties](https://mlsanity.com/paper/2407.07816/) (2024)
- [SQLdepth: Generalizable Self-Supervised Fine-Structured Monocular Depth Estimation](https://mlsanity.com/paper/2309.00526/) (2023)
- [PLUMENet: Efficient 3D Object Detection from Stereo Images](https://mlsanity.com/paper/2101.06594/) (2021)
- [Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching](https://mlsanity.com/paper/2306.15612/) (2023)
- [Uncertainty Quantification Metrics for Deep Regression](https://mlsanity.com/paper/2405.04278/) (2024)
- [TemporalStereo: Efficient Spatial-Temporal Stereo Matching Network](https://mlsanity.com/paper/2211.13755/) (2022)
- [DSGN++: Exploiting Visual-Spatial Relation for Stereo-based 3D Detectors](https://mlsanity.com/paper/2204.03039/) (2022)
- [Embodiment: Self-Supervised Depth Estimation Based on Camera Models](https://mlsanity.com/paper/2408.01565/) (2024)
- [DurLAR: A High-fidelity 128-channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-modal Autonomous Driving Applications](https://mlsanity.com/paper/2406.10068/) (2024)
- [Vision-Based Environmental Perception for Autonomous Driving](https://mlsanity.com/paper/2212.11453/) (2022)
- [StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-based 3D Object Detection](https://mlsanity.com/paper/2301.01615/) (2023)
- [Bidirectional Semi-supervised Dual-branch CNN for Robust 3D Reconstruction of Stereo Endoscopic Images via Adaptive Cross and Parallel Supervisions](https://mlsanity.com/paper/2210.08291/) (2022)
- [Stereo Risk: A Continuous Modeling Approach to Stereo Matching](https://mlsanity.com/paper/2407.03152/) (2024)
- [Improving Domain Generalization in Self-supervised Monocular Depth Estimation via Stabilized Adversarial Training](https://mlsanity.com/paper/2411.02149/) (2024)
- [MambaDepth: Enhancing Long-range Dependency for Self-Supervised Fine-Structured Monocular Depth Estimation](https://mlsanity.com/paper/2406.04532/) (2024)
- [Stereo Neural Vernier Caliper](https://mlsanity.com/paper/2203.11018/) (2022)
- [Category-Level Pose Retrieval with Contrastive Features Learnt with Occlusion Augmentation](https://mlsanity.com/paper/2208.06195/) (2022)
- [Transformer-based stereo-aware 3D object detection from binocular images](https://mlsanity.com/paper/2304.11906/) (2023)
- [Towards Continual, Online, Self-Supervised Depth](https://mlsanity.com/paper/2103.00369/) (2021)
- [Joint stereo 3D object detection and implicit surface reconstruction](https://mlsanity.com/paper/2111.12924/) (2021)
- [Hinge-Wasserstein: Estimating Multimodal Aleatoric Uncertainty in Regression Tasks](https://mlsanity.com/paper/2306.00560/) (2023)

## Abstract (arXiv)

Existing approaches to depth or disparity estimation output a distribution over a set of pre-defined discrete values. This leads to inaccurate results when the true depth or disparity does not match any of these values. The fact that this distribution is usually learned indirectly through a regression loss causes further problems in ambiguous regions around object boundaries. We address these issues using a new neural network architecture that is capable of outputting arbitrary depth values, and a new loss function that is derived from the Wasserstein distance between the true and the predicted distributions. We validate our approach on a variety of tasks, including stereo disparity and depth estimation, and the downstream 3D object detection. Our approach drastically reduces the error in ambiguous regions, especially around object boundaries that greatly affect the localization of objects in 3D, achieving the state-of-the-art in 3D object detection for autonomous driving. Our code will be available at https://github.com/Div99/W-Stereo-Disp.