Papers › GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose

GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose

6 Mar 2018CVPR 2018 6arXiv:1803.02276archive 2025-07-28

Zhichao Yin, Jianping Shi

We propose GeoNet, a jointly unsupervised learning framework for monocular depth, optical flow and ego-motion estimation from videos. The three components are coupled by the nature of 3D scene geometry, jointly learned by our framework in an end-to-end manner. Specifically, geometric relationships are extracted over the predictions of individual modules and then combined as an image reconstruction loss, reasoning about static and dynamic scene parts separately. Furthermore, we propose an adaptive geometric consistency loss to increase robustness towards outliers and non-Lambertian regions, which resolves occlusions and texture ambiguities effectively. Experimentation on the KITTI driving dataset reveals that our scheme achieves state-of-the-art results in all of the three tasks, performing better than previously unsupervised methods and comparably with supervised ones.

PaperPDFConference PDFCodeCode 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="1803.02276")

Code

Syntology Ran 0 of 8 code samples harvested from 1 repository linked to this paper; 8 have no recorded run.

By repository: official repository: 8 samples from 1 repository, 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.

yzcjtr/GeoNet officialmentioned in papermentioned on GitHubtfMIT report
raunaks13/GeoNet-PyTorch mentioned on GitHubpytorch report
yijie0710/GeoNet_pytorch mentioned on GitHubpytorch 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; 0 ran; 0 honoured the contract we drafted; 8 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.

8unverified

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 yzcjtr/GeoNet. “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.

compute_errors yzcjtr/GeoNet/kitti_eval/depth_evaluation_utils.py official repository unverified MIT (permissive) · d83582de454a0b40 · report
convert_disps_to_depths_kitti yzcjtr/GeoNet/kitti_eval/depth_evaluation_utils.py official repository unverified MIT (permissive) · cf98eb3840092327 · report
euler2mat yzcjtr/GeoNet/utils.py official repository unverified MIT (permissive) · 46a3f7669dcd8ad5 · report
load_gt_disp_kitti yzcjtr/GeoNet/kitti_eval/depth_evaluation_utils.py official repository unverified MIT (permissive) · 6f8a54ff22b913e2 · report
load_image_sequence yzcjtr/GeoNet/geonet_test_pose.py official repository unverified MIT (permissive) · 8fc3bf3cf5e6a6ba · report
pixel2cam yzcjtr/GeoNet/utils.py official repository unverified MIT (permissive) · 883ac80de85205ef · report
pose_vec2mat yzcjtr/GeoNet/utils.py official repository unverified MIT (permissive) · 82c27adf53eb9d69 · report
unpack_image_sequence yzcjtr/GeoNet/geonet_test_flow.py official repository unverified MIT (permissive) · 65362a4a8daa0fdd · report

Tasks

Camera Pose EstimationImage ReconstructionMotion EstimationOptical Flow EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Camera Pose Estimation KITTI Odometry Benchmark GeoNet Absolute Trajectory Error [m] 100.75 #5 of 7 Archive leaderboard report
Camera Pose Estimation KITTI Odometry Benchmark GeoNet Average Rotational Error er[%] 9.40 #5 of 7 Archive leaderboard report
Camera Pose Estimation KITTI Odometry Benchmark GeoNet Average Translational Error et[%] 26.31 #5 of 7 Archive leaderboard report
Pose Estimation KITTI 2015 GeoNet Average End-Point Error 10.81 #1 of 1 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