Papers › Deep Two-View Structure-from-Motion Revisited

Deep Two-View Structure-from-Motion Revisited

1 Apr 2021CVPR 2021 1arXiv:2104.00556archive 2025-07-28

Jianyuan Wang, Yiran Zhong, Yuchao Dai, Stan Birchfield, Kaihao Zhang, Nikolai Smolyanskiy, Hongdong Li

Two-view structure-from-motion (SfM) is the cornerstone of 3D reconstruction and visual SLAM. Existing deep learning-based approaches formulate the problem by either recovering absolute pose scales from two consecutive frames or predicting a depth map from a single image, both of which are ill-posed problems. In contrast, we propose to revisit the problem of deep two-view SfM by leveraging the well-posedness of the classic pipeline. Our method consists of 1) an optical flow estimation network that predicts dense correspondences between two frames; 2) a normalized pose estimation module that computes relative camera poses from the 2D optical flow correspondences, and 3) a scale-invariant depth estimation network that leverages epipolar geometry to reduce the search space, refine the dense correspondences, and estimate relative depth maps. Extensive experiments show that our method outperforms all state-of-the-art two-view SfM methods by a clear margin on KITTI depth, KITTI VO, MVS, Scenes11, and SUN3D datasets in both relative pose and depth estimation.

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="2104.00556")

Code

Syntology Ran 5 of 21 code samples harvested from 1 repository linked to this paper; 16 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 4 ran with no contract checked.

By repository: official repository: 21 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jytime/Deep-SfM-Revisited officialmentioned 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

21 samples harvested; 5 ran; 0 honoured the contract we drafted; 16 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
4ran
16unverified

Licence: 0 of the 21 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 jytime/Deep-SfM-Revisited. “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_color jytime/Deep-SfM-Revisited/flow_viz.py official repository ran MIT (permissive) · abcbf43ad9fe6129 · report
load_velodyne_points jytime/Deep-SfM-Revisited/kitti_utils.py official repository ran MIT (permissive) · 8bfc895e86bfc7bc · report
predict_flow jytime/Deep-SfM-Revisited/models/DICL_shallow.py official repository ran · our draft was wrong MIT (permissive) · c3f23a008d953af5 · report
read_calib_file jytime/Deep-SfM-Revisited/kitti_utils.py official repository ran MIT (permissive) · ff833c099a80a327 · report
sub2ind jytime/Deep-SfM-Revisited/kitti_utils.py official repository ran MIT (permissive) · 04e9b96b63844176 · report
MSE_loss jytime/Deep-SfM-Revisited/models/CVPMVS.py official repository unverified MIT (permissive) · c904f0e9da049f2a · report
compute_valid_depth_mask jytime/Deep-SfM-Revisited/demon_metrics.py official repository unverified MIT (permissive) · 0d38c54288d1ecd2 · report
convbn jytime/Deep-SfM-Revisited/models/DICL_shallow.py official repository unverified MIT (permissive) · cd9d415e756ddad5 · report
coord2flow jytime/Deep-SfM-Revisited/epipolar_utils.py official repository unverified MIT (permissive) · 5053cba75a330c97 · report
disparity_loader_png jytime/Deep-SfM-Revisited/KITTI_loader.py official repository unverified MIT (permissive) · 1abf6f49a505fcbe · report
flow2coord jytime/Deep-SfM-Revisited/epipolar_utils.py official repository unverified MIT (permissive) · a99f9e38ae607fd8 · report
flow_compute_color jytime/Deep-SfM-Revisited/flow_viz.py official repository unverified MIT (permissive) · 215f62561b03c262 · report
flow_to_color jytime/Deep-SfM-Revisited/flow_viz.py official repository unverified MIT (permissive) · d59fe7ab39463182 · report
l1 jytime/Deep-SfM-Revisited/demon_metrics.py official repository unverified MIT (permissive) · 94676aa789a890f5 · report
l1_inverse jytime/Deep-SfM-Revisited/demon_metrics.py official repository unverified MIT (permissive) · 8d573359b9ccf5f6 · report
load_flow_from_png jytime/Deep-SfM-Revisited/KITTI_loader.py official repository unverified MIT (permissive) · 914690083c05e41c · report
mask_loader_png jytime/Deep-SfM-Revisited/KITTI_loader.py official repository unverified MIT (permissive) · 3eee763265fa66e7 · report
photometric_reconstruction_loss_Charbonnier jytime/Deep-SfM-Revisited/loss_functions.py official repository unverified MIT (permissive) · 48b6598aa92d35a5 · report
resize_sparse_map jytime/Deep-SfM-Revisited/flow_transforms.py official repository unverified MIT (permissive) · bfabd42bc420f7f0 · report
sL1_loss jytime/Deep-SfM-Revisited/models/CVPMVS.py official repository unverified MIT (permissive) · 646d6725b699091e · report
weighted_smooth_depth_loss jytime/Deep-SfM-Revisited/loss_functions.py official repository unverified MIT (permissive) · dff279c368fc0d20 · report

Tasks

3D ReconstructionDepth EstimationMonocular Depth EstimationOptical Flow EstimationPose EstimationVocal Bursts Valence Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation KITTI Eigen split SfM-Revisited RMSE 2.273 #30 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split SfM-Revisited Sq Rel 0.224 #30 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split SfM-Revisited absolute relative error 0.055 #30 of 79 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