Papers › MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching

MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching

22 Aug 2021arXiv:2108.09770archive 2025-07-28

Faranak Shamsafar, Samuel Woerz, Rafia Rahim, Andreas Zell

Recent methods in stereo matching have continuously improved the accuracy using deep models. This gain, however, is attained with a high increase in computation cost, such that the network may not fit even on a moderate GPU. This issue raises problems when the model needs to be deployed on resource-limited devices. For this, we propose two light models for stereo vision with reduced complexity and without sacrificing accuracy. Depending on the dimension of cost volume, we design a 2D and a 3D model with encoder-decoders built from 2D and 3D convolutions, respectively. To this end, we leverage 2D MobileNet blocks and extend them to 3D for stereo vision application. Besides, a new cost volume is proposed to boost the accuracy of the 2D model, making it performing close to 3D networks. Experiments show that the proposed 2D/3D networks effectively reduce the computational expense (27%/95% and 72%/38% fewer parameters/operations in 2D and 3D models, respectively) while upholding the accuracy. Our code is available at https://github.com/cogsys-tuebingen/mobilestereonet.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2108.09770")

Code

Syntology Ran 1 of 8 code samples harvested from 3 repositories linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: official repository: 1 sample from 1 repository, 1 ran; community (archive-listed): 7 samples from 2 repositories, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

cogsys-tuebingen/mobilestereonet officialmentioned in papermentioned on GitHubpytorch report
UCI-ISA-Lab/MultiHeadDepth-HomoDepth mentioned on GitHubpytorchMIT report
ibaiGorordo/ONNX-MobileStereoNet mentioned on GitHubpytorchMIT report
ibaiGorordo/TFLite-MobileStereoNet mentioned on GitHubtfMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

8 samples harvested; 1 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
7unverified

Licence: 0 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

input_constructor cogsys-tuebingen/mobilestereonet/cost.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 5e310fcb52fdb183 · report
draw_depth ibaiGorordo/ONNX-MobileStereoNet/mobilestereonet/utils.py community (archive-listed) unverified MIT (permissive) · 9d919b029837f9f6 · report
draw_disparity ibaiGorordo/ONNX-MobileStereoNet/mobilestereonet/utils.py community (archive-listed) unverified MIT (permissive) · f1e3085f00b12eed · report
efficient_blk UCI-ISA-Lab/MultiHeadDepth-HomoDepth/model.py community (archive-listed) unverified MIT (permissive) · e87d661ef8163fd0 · report
feature_fusion UCI-ISA-Lab/MultiHeadDepth-HomoDepth/model.py community (archive-listed) unverified MIT (permissive) · b79a2825facd8942 · report
gard_map UCI-ISA-Lab/MultiHeadDepth-HomoDepth/utils.py community (archive-listed) unverified MIT (permissive) · 78ab4a5f6d826cb2 · report
img2tensor UCI-ISA-Lab/MultiHeadDepth-HomoDepth/utils.py community (archive-listed) unverified MIT (permissive) · 04b60886e9a88a2d · report
readPFM UCI-ISA-Lab/MultiHeadDepth-HomoDepth/utils.py community (archive-listed) unverified MIT (permissive) · a8f2a79258b4f21b · report

Tasks

Depth EstimationDisparity EstimationStereo Depth EstimationStereo Matching

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Stereo Depth Estimation KITTI2015 3D-MobileStereoNet three pixel error 1.69 #2 of 7 Archive leaderboard report
Stereo Depth Estimation KITTI2015 2D-MobileStereoNet three pixel error 2.67 #5 of 7 Archive leaderboard report
Stereo Depth Estimation sceneflow 3D-MobileStereoNet Average End-Point Error 0.80 #1 of 3 Archive leaderboard report
Stereo Depth Estimation sceneflow 3D-MobileStereoNet EPE 0.80 #1 of 3 Archive leaderboard report
Stereo Depth Estimation sceneflow 2D-MobileStereoNet Average End-Point Error 1.14 #3 of 3 Archive leaderboard report
Stereo Depth Estimation sceneflow 2D-MobileStereoNet EPE 1.14 #3 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionGlobal Average PoolingInverted Residual BlockMobileNetV1Pointwise ConvolutionReLUSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections