# Non-Learning Low-Light Stereo Vision

Source: [Non-Learning Low-Light Stereo Vision](<https://www.sota2.com/research/paper/6a1e63b7dbd7150506f852c5>)

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

Data updated: 2026-06-02T05:00:51.557Z

Authors: Jason Wang, Lucas Nguyen, Hyunseung Eom, Wei Xu, Qi Guo

Published: 2026-05-29T21:43:38.000Z

## Abstract

We present a non-learning stereo framework for disparity estimation from severely noisy images. Using the Field of Junctions (FoJ), it retains coarse visual features stable under severe noise for cost volume construction while discarding fine textures inseparable from photon noise. The resulting structural information guides boundary-aware Semi-Global Matching (SGM) that dynamically adapts smoothness penalties to preserve true disparity discontinuities. The output is a sparse disparity map more accurate than those of recent stereo algorithms over unmasked pixels on widely-used benchmark datasets.

## 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 InStereo2K](<https://www.sota2.com/research/sota/stereo-matching-on-instereo2k.md>): Stereo Matching; InStereo2K; EPE (px): 1.5.

- [Stereo Matching on Middlebury 2014](<https://www.sota2.com/research/sota/stereo-matching-on-middlebury-2014.md>): Stereo Matching; Middlebury 2014; Bad Pixel Rate (Thresh 2.0, All): not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.00379>)

[PDF](<https://arxiv.org/pdf/2606.00379.pdf>)
