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 View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 21 code samples harvested from 1 repository linked to this paper: 18 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 21 samples from 1 repository, 18 ran (16 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

jytime/Deep-SfM-Revisited officialmentioned on GitHubpytorchMITSyntology: 21 samples, 18 ran (2 instrument-failed) · 3 unverified 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: 18 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
2ran · our draft was wrong
14ran
3unverified

Licence: 2 of the 21 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

jytime/Deep-SfM-Revisited official repository 21 samples, 18 ran (2 instrument-failed) · 3 unverified
compute_color in 11 papers flow_viz.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · abcbf43ad9fe6129 · report fixture: signature u:ndarray/2/float, v:ndarray/2/float · returned ndarray · level recorded 2026-09-24
compute_valid_depth_mask demon_metrics.py ran MIT (permissive) · 0d38c54288d1ecd2 · report fixture: signature d1:ndarray/2/float, d2:ndarray/2/float · returned ndarray · level recorded 2026-09-25
convbn in 26 papers models/DICL_shallow.py ran MIT (permissive) · cd9d415e756ddad5 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, kernel_size:int/0/int, stride:int/0/int, pad:int/0/int, dilation:int/0/int · returned Sequential · level recorded 2026-09-25
coord2flow epipolar_utils.py ran MIT (permissive) · 5053cba75a330c97 · report fixture: signature coord1:Tensor/3/float, coord2:Tensor/3/float, b:int/0/int, h:int/0/int, w:int/0/int · returned Tensor · level recorded 2026-09-25
disparity_loader_png KITTI_loader.py ran fingerprinted MIT (permissive) · 1abf6f49a505fcbe · report fixture: signature path:str/0/str · returned ndarray · level recorded 2026-09-25
flow2coord epipolar_utils.py ran MIT (permissive) · a99f9e38ae607fd8 · report fixture: signature flow:Tensor/4/float · returned tuple · level recorded 2026-09-25
flow_compute_color in 7 papers flow_viz.py ran MIT (permissive) · 215f62561b03c262 · report fixture: signature u:ndarray/2/float, v:ndarray/2/float, convert_to_bgr:bool/0/bool · returned ndarray · level recorded 2026-09-25
flow_to_color in 10 papers flow_viz.py ran MIT (permissive) · d59fe7ab39463182 · report fixture: signature flow_uv:ndarray/3/float, clip_flow:float/0/float, convert_to_bgr:bool/0/bool · returned ndarray · level recorded 2026-09-25
l1 in 25 papers demon_metrics.py ran MIT (permissive) · 94676aa789a890f5 · report fixture: signature depth1:ndarray/2/float, depth2:ndarray/2/float · returned float32 · level recorded 2026-09-25
l1_inverse demon_metrics.py ran MIT (permissive) · 8d573359b9ccf5f6 · report fixture: signature depth1:ndarray/2/float, depth2:ndarray/2/float · returned float32 · level recorded 2026-09-25
load_flow_from_png KITTI_loader.py ran MIT (permissive) · 914690083c05e41c · report fixture: signature png_path:str/0/str · returned ndarray · level recorded 2026-09-25
load_velodyne_points in 8 papers kitti_utils.py ran · honoured contract MIT (permissive) · 8bfc895e86bfc7bc · report fixture: signature filename:str/0/str · returned ndarray · level recorded 2026-09-24
mask_loader_png KITTI_loader.py ran fingerprinted MIT (permissive) · 3eee763265fa66e7 · report fixture: signature path:str/0/str · returned ndarray · level recorded 2026-09-25
predict_flow in 23 papers models/DICL_shallow.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · c3f23a008d953af5 · report fixture: signature in_planes:int/0/int · returned Conv2d · level recorded 2026-09-22
read_calib_file in 14 papers kitti_utils.py ran · our draft was wrong MIT (permissive) · ff833c099a80a327 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-24
resize_sparse_map flow_transforms.py ran MIT (permissive) · bfabd42bc420f7f0 · report fixture: signature flow:ndarray/2/float, valid:ndarray/2/float, fx:float/0/float, fy:float/0/float · returned ndarray · level recorded 2026-09-25
sub2ind in 11 papers kitti_utils.py ran MIT (permissive) · 04e9b96b63844176 · report fixture: signature matrixSize:tuple/1/int, rowSub:int/0/int, colSub:int/0/int · returned int · level recorded 2026-09-24
weighted_smooth_depth_loss loss_functions.py ran MIT (permissive) · dff279c368fc0d20 · report fixture: signature pred_disp:Tensor/3/float, im:Tensor/4/float · returned Tensor · level recorded 2026-09-25
MSE_loss models/CVPMVS.py unverified MIT (permissive) · c904f0e9da049f2a · report
photometric_reconstruction_loss_Charbonnier loss_functions.py unverified MIT (permissive) · 48b6598aa92d35a5 · report
sL1_loss models/CVPMVS.py unverified MIT (permissive) · 646d6725b699091e · 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