# Stextsuperscript2Mtextsuperscript2: Scalable Stereo Matching Model for Reliable Depth Estimation

arXiv: https://arxiv.org/abs/2507.13229 · HTML: https://mlsanity.com/paper/2507.13229/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 51 references that are in the map.
- First posted on arXiv 17 Jul 2025.

## Builds on (most cited first, 30 of 37)

- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [End-to-End Learning of Geometry and Context for Deep Stereo Regression](https://mlsanity.com/paper/1703.04309/) (2017)
- [RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching](https://mlsanity.com/paper/2109.07547/) (2021)
- [Virtual Worlds as Proxy for Multi-Object Tracking Analysis](https://mlsanity.com/paper/1605.06457/) (2016)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [AANet: Adaptive Aggregation Network for Efficient Stereo Matching](https://mlsanity.com/paper/2004.09548/) (2020)
- [Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation](https://mlsanity.com/paper/2203.11483/) (2022)
- [Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2011.02910/) (2020)
- [Iterative Geometry Encoding Volume for Stereo Matching](https://mlsanity.com/paper/2303.06615/) (2023)
- [FoundationStereo: Zero-Shot Stereo Matching](https://mlsanity.com/paper/2501.09898/) (2025)
- [CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow](https://mlsanity.com/paper/2211.10408/) (2022)
- [CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion](https://mlsanity.com/paper/2210.10716/) (2022)
- [MatchFormer: Interleaving Attention in Transformers for Feature Matching](https://mlsanity.com/paper/2203.09645/) (2022)
- [HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching](https://mlsanity.com/paper/2007.12140/) (2020)
- [SMD-Nets: Stereo Mixture Density Networks](https://mlsanity.com/paper/2104.03866/) (2021)
- [DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch](https://mlsanity.com/paper/1909.05845/) (2019)
- [Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching](https://mlsanity.com/paper/2403.00486/) (2024)
- [REGTR: End-to-end Point Cloud Correspondences with Transformers](https://mlsanity.com/paper/2203.14517/) (2022)
- [Falling Things: A Synthetic Dataset for 3D Object Detection and Pose Estimation](https://mlsanity.com/paper/1804.06534/) (2018)
- [Accurate and Efficient Stereo Matching via Attention Concatenation Volume](https://mlsanity.com/paper/2209.12699/) (2022)
- [Multimodal Deep Learning for Robust RGB-D Object Recognition](https://mlsanity.com/paper/1507.06821/) (2015)
- [DEFOM-Stereo: Depth Foundation Model Based Stereo Matching](https://mlsanity.com/paper/2501.09466/) (2025)
- [MoCha-Stereo: Motif Channel Attention Network for Stereo Matching](https://mlsanity.com/paper/2404.06842/) (2024)
- [Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitation](https://mlsanity.com/paper/2108.05773/) (2021)
- [Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail](https://mlsanity.com/paper/2412.04472/) (2024)

## Abstract (arXiv)

The pursuit of a generalizable stereo matching model, capable of performing well across varying resolutions and disparity ranges without dataset-specific fine-tuning, has revealed a fundamental trade-off. Iterative local search methods achieve high scores on constrained benchmarks, but their core mechanism inherently limits the global consistency required for true generalization. However, global matching architectures, while theoretically more robust, have historically been rendered infeasible by prohibitive computational and memory costs. We resolve this dilemma with Stextsuperscript2Mtextsuperscript2: a global matching architecture that achieves state-of-the-art accuracy and high efficiency without relying on cost volume filtering or deep refinement stacks. Our design integrates a multi-resolution transformer for robust long-range correspondence, trained with a novel loss function that concentrates probability on feasible matches. This approach enables a more robust joint estimation of disparity, occlusion, and confidence. Stextsuperscript2Mtextsuperscript2 establishes a new state of the art on Middlebury v3 and ETH3D benchmarks, significantly outperforming prior methods in most metrics while reconstructing high-quality details with competitive efficiency.