# Temporally Consistent Stereo Matching

arXiv: https://arxiv.org/abs/2407.11950 · HTML: https://mlsanity.com/paper/2407.11950/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 52 references that are in the map.
- First posted on arXiv 16 Jul 2024.

## Builds on (most cited first, 4 of 4)

- [Hierarchical Neural Architecture Search for Deep Stereo Matching](https://mlsanity.com/paper/2010.13501/) (2020)
- [Attention Concatenation Volume for Accurate and Efficient Stereo Matching](https://mlsanity.com/paper/2203.02146/) (2022)
- [Revisiting Depth Completion from a Stereo Matching Perspective for Cross-domain Generalization](https://mlsanity.com/paper/2312.09254/) (2023)
- [Learning for Disparity Estimation through Feature Constancy](https://mlsanity.com/paper/1712.01039/) (2017)

## Built on by (most cited first, 8 of 8)

- [IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching](https://mlsanity.com/paper/2409.00638/) (2024)
- [Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail](https://mlsanity.com/paper/2412.04472/) (2024)
- [Stereo Any Video: Temporally Consistent Stereo Matching](https://mlsanity.com/paper/2503.05549/) (2025)
- [What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?](https://mlsanity.com/paper/2504.16930/) (2025)
- [Helvipad: A Real-World Dataset for Omnidirectional Stereo Depth Estimation](https://mlsanity.com/paper/2411.18335/) (2024)
- [Stereo Anything: Unifying Zero-shot Stereo Matching with Large-Scale Mixed Data](https://mlsanity.com/paper/2411.14053/) (2024)
- [Pseudo-Stereo Inputs: A Solution to the Occlusion Challenge in Self-Supervised Stereo Matching](https://mlsanity.com/paper/2410.02534/) (2024)
- [PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching](https://mlsanity.com/paper/2510.20178/) (2025)

## Abstract (arXiv)

Stereo matching provides depth estimation from binocular images for downstream applications. These applications mostly take video streams as input and require temporally consistent depth maps. However, existing methods mainly focus on the estimation at the single-frame level. This commonly leads to temporally inconsistent results, especially in ill-posed regions. In this paper, we aim to leverage temporal information to improve the temporal consistency, accuracy, and efficiency of stereo matching. To achieve this, we formulate video stereo matching as a process of temporal disparity completion followed by continuous iterative refinements. Specifically, we first project the disparity of the previous timestamp to the current viewpoint, obtaining a semi-dense disparity map. Then, we complete this map through a disparity completion module to obtain a well-initialized disparity map. The state features from the current completion module and from the past refinement are fused together, providing a temporally coherent state for subsequent refinement. Based on this coherent state, we introduce a dual-space refinement module to iteratively refine the initialized result in both disparity and disparity gradient spaces, improving estimations in ill-posed regions. Extensive experiments demonstrate that our method effectively alleviates temporal inconsistency while enhancing both accuracy and efficiency.