Papers › Anytime Stereo Image Depth Estimation on Mobile Devices

Anytime Stereo Image Depth Estimation on Mobile Devices

26 Oct 2018arXiv:1810.11408archive 2025-07-28

Yan Wang, Zihang Lai, Gao Huang, Brian H. Wang, Laurens van der Maaten, Mark Campbell, Kilian Q. Weinberger

Many applications of stereo depth estimation in robotics require the generation of accurate disparity maps in real time under significant computational constraints. Current state-of-the-art algorithms force a choice between either generating accurate mappings at a slow pace, or quickly generating inaccurate ones, and additionally these methods typically require far too many parameters to be usable on power- or memory-constrained devices. Motivated by these shortcomings, we propose a novel approach for disparity prediction in the anytime setting. In contrast to prior work, our end-to-end learned approach can trade off computation and accuracy at inference time. Depth estimation is performed in stages, during which the model can be queried at any time to output its current best estimate. Our final model can process 1242$ \times $375 resolution images within a range of 10-35 FPS on an NVIDIA Jetson TX2 module with only marginal increases in error -- using two orders of magnitude fewer parameters than the most competitive baseline. The source code is available at https://github.com/mileyan/AnyNet .

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="1810.11408")

Code

Syntology Ran 3 of 26 code samples harvested from 3 repositories linked to this paper; 23 have no recorded run. Of those that ran: 2 ran · violated contract; 1 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 1 ran; community (archive-listed): 10 samples from 2 repositories, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

mileyan/AnyNet officialmentioned in papermentioned on GitHubpytorchMIT report
mamoanwar97/Anynet_modified mentioned on GitHubpytorchMIT report
rajeevpatwari/anynet mentioned on GitHubpytorchMIT 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

26 samples harvested; 3 ran; 0 honoured the contract we drafted; 23 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.

2ran · violated contract
1ran
23unverified

Licence: 0 of the 26 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.

is_image_file mileyan/AnyNet/dataloader/KITTILoader.py official repository ran · violated contract MIT (permissive) · ab4109634b75ef8b · report
batch_relu_conv3d mileyan/AnyNet/models/submodules.py official repository unverified MIT (permissive) · 6cca995f3adaee16 · report
dataloader mileyan/AnyNet/dataloader/KITTIloader2012.py official repository unverified MIT (permissive) · 337eab65fc60395a · report
dataloader mileyan/AnyNet/dataloader/KITTIloader2015.py official repository unverified MIT (permissive) · 164ddc7f85f5e375 · report
dataloader mileyan/AnyNet/dataloader/diy_dataset.py official repository unverified MIT (permissive) · f372bd977f385406 · report
dataloader mileyan/AnyNet/dataloader/listflowfile.py official repository unverified MIT (permissive) · aa7e13ed905b10f3 · report
default_loader mileyan/AnyNet/dataloader/KITTILoader.py official repository unverified MIT (permissive) · 0b3ce8456d675a8c · report
disparity_loader mileyan/AnyNet/dataloader/SecenFlowLoader.py official repository unverified MIT (permissive) · aaf877e27c4a3c3e · report
disparity_loader mileyan/AnyNet/dataloader/KITTILoader.py official repository unverified MIT (permissive) · c0ce2ceaa41309b3 · report
error_estimating mileyan/AnyNet/finetune.py official repository unverified MIT (permissive) · 229724b86f1fdcbf · report
inception_preproccess mileyan/AnyNet/dataloader/preprocess.py official repository unverified MIT (permissive) · f407103e88c43c4d · report
pad_random_crop mileyan/AnyNet/dataloader/preprocess.py official repository unverified MIT (permissive) · 8050fdcf3ccf70b9 · report
post_3dconvs mileyan/AnyNet/models/submodules.py official repository unverified MIT (permissive) · c9513ac7441c6dc6 · report
preconv2d mileyan/AnyNet/models/submodules.py official repository unverified MIT (permissive) · 484f0f80ebcb2bfb · report
readPFM mileyan/AnyNet/dataloader/readpfm.py official repository unverified MIT (permissive) · aaea02c311c902eb · report
scale_crop mileyan/AnyNet/dataloader/preprocess.py official repository unverified MIT (permissive) · 7d64bf848e8100c3 · report
default_loader mamoanwar97/Anynet_modified/dataloader/KITTILoader3D.py community (archive-listed) ran MIT (permissive) · ac269a0e4b8d946e · report
is_image_file rajeevpatwari/anynet/dataloader/diy_dataset.py community (archive-listed) ran · violated contract MIT (permissive) · 59848503040bbdac · report
conv_disp_to_depth mamoanwar97/Anynet_modified/evaluate.py community (archive-listed) unverified MIT (permissive) · cbae2621f9e8e508 · report
dataloader mamoanwar97/Anynet_modified/dataloader/KITTI_dataset.py community (archive-listed) unverified MIT (permissive) · b59b91ff9420dc34 · report
dataloader mamoanwar97/Anynet_modified/dataloader/KITTIloader2012.py community (archive-listed) unverified MIT (permissive) · 86dc9ef96c0417c9 · report
dataloader mamoanwar97/Anynet_modified/dataloader/KITTIloader2015.py community (archive-listed) unverified MIT (permissive) · 0212e19ca5cc4ab5 · report
dataloader rajeevpatwari/anynet/dataloader/listflowfile.py community (archive-listed) unverified MIT (permissive) · 2502fc54633e5cb4 · report
disparity_loader mamoanwar97/Anynet_modified/dataloader/KITTILoader3D.py community (archive-listed) unverified MIT (permissive) · 8d9f5f6ce951aa15 · report
error_estimating mamoanwar97/Anynet_modified/openCV.py community (archive-listed) unverified MIT (permissive) · db6b53b61db9cbf6 · report
is_image_file mamoanwar97/Anynet_modified/dataloader/KITTI_dataset.py community (archive-listed) unverified MIT (permissive) · 44b43878a62b8e71 · report

Tasks

Depth EstimationStereo Depth Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Stereo Depth Estimation KITTI2012 AnyNet three pixel error 6.1 #1 of 1 Archive leaderboard report
Stereo Depth Estimation KITTI2015 AnyNet three pixel error 6.2 #1 of 7 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.

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