# Continuous 3D Label Stereo Matching using Local Expansion Moves

Source: [Continuous 3D Label Stereo Matching using Local Expansion Moves](<https://www.sota2.com/research/paper/68fa64e51e209131cea07386>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:14:52.998Z

Authors: Tatsunori Taniai, Yasuyuki Matsushita, Yoichi Sato, Takeshi Naemura

Published: 2016-03-28T07:27:49.000Z

## Abstract

We present an accurate stereo matching method using local expansion moves based on graph cuts. This new move-making scheme is used to efficiently infer per-pixel 3D plane labels on a pairwise Markov random field (MRF) that effectively combines recently proposed slanted patch matching and curvature regularization terms. The local expansion moves are presented as many alpha-expansions defined for small grid regions. The local expansion moves extend traditional expansion moves by two ways: localization and spatial propagation. By localization, we use different candidate alpha-labels according to the locations of local alpha-expansions. By spatial propagation, we design our local alpha-expansions to propagate currently assigned labels for nearby regions. With this localization and spatial propagation, our method can efficiently infer MRF models with a continuous label space using randomized search. Our method has several advantages over previous approaches that are based on fusion moves or belief propagation; it produces submodular moves deriving a subproblem optimality; it helps find good, smooth, piecewise linear disparity maps; it is suitable for parallelization; it can use cost-volume filtering techniques for accelerating the matching cost computations. Even using a simple pairwise MRF, our method is shown to have best performance in the Middlebury stereo benchmark V2 and V3.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Stereo Matching on Middlebury 2014 (test)](<https://www.sota2.com/research/sota/stereo-matching-on-middlebury-2014-test.md>): Stereo Matching; Middlebury 2014 (test); Bad Pixel Rate (Thresh 2.0): 5.43.

- [Stereo Matching on Middlebury v3](<https://www.sota2.com/research/sota/stereo-matching-on-middlebury-v3.md>): Stereo Matching; Middlebury v3; Bad Pixel Rate (Thresh 2.0): 5.43.

- [Stereo Matching on Middlebury v3 (test)](<https://www.sota2.com/research/sota/stereo-matching-on-middlebury-v3-test.md>): Stereo Matching; Middlebury v3 (test); Avg Error: 2.24.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1603.08328>)

[PDF](<https://arxiv.org/pdf/1603.08328.pdf>)