Papers › Self-Supervised Multi-Frame Monocular Scene Flow

Self-Supervised Multi-Frame Monocular Scene Flow

5 May 2021CVPR 2021 1arXiv:2105.02216archive 2025-07-28

Junhwa Hur, Stefan Roth

Estimating 3D scene flow from a sequence of monocular images has been gaining increased attention due to the simple, economical capture setup. Owing to the severe ill-posedness of the problem, the accuracy of current methods has been limited, especially that of efficient, real-time approaches. In this paper, we introduce a multi-frame monocular scene flow network based on self-supervised learning, improving the accuracy over previous networks while retaining real-time efficiency. Based on an advanced two-frame baseline with a split-decoder design, we propose (i) a multi-frame model using a triple frame input and convolutional LSTM connections, (ii) an occlusion-aware census loss for better accuracy, and (iii) a gradient detaching strategy to improve training stability. On the KITTI dataset, we observe state-of-the-art accuracy among monocular scene flow methods based on self-supervised learning.

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="2105.02216")

Code

Syntology Ran 0 of 6 code samples harvested from 1 repository linked to this paper; 6 have no recorded run.

By repository: official repository: 6 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.

visinf/multi-mono-sf officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

6 samples harvested; 0 ran; 0 honoured the contract we drafted; 6 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.

6unverified

Licence: 0 of the 6 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 visinf/multi-mono-sf. “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_cost_volume visinf/multi-mono-sf/models/modules_sceneflow.py official repository unverified Apache-2.0 (permissive) · 4640753688ad1189 · report
get_date_from_width visinf/multi-mono-sf/datasets/common.py official repository unverified Apache-2.0 (permissive) · 9c8882cf7ca73c32 · report
list_chunks visinf/multi-mono-sf/datasets/common.py official repository unverified Apache-2.0 (permissive) · 8bbf084c3aa928a7 · report
list_chunks_overlap visinf/multi-mono-sf/datasets/common.py official repository unverified Apache-2.0 (permissive) · fb8543f34813ad8b · report
merge_lists visinf/multi-mono-sf/models/modules_sceneflow.py official repository unverified Apache-2.0 (permissive) · 3d5b2b464da59e1b · report
normalize_features visinf/multi-mono-sf/models/modules_sceneflow.py official repository unverified Apache-2.0 (permissive) · 9926e17e3fdfd75d · report

Tasks

DecoderScene Flow EstimationSelf-Supervised Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Flow Estimation KITTI 2015 Scene Flow Test Multi-Mono-SF D1-all 30.78 #3 of 4 Archive leaderboard report
Scene Flow Estimation KITTI 2015 Scene Flow Test Multi-Mono-SF D2-all 34.41 #3 of 4 Archive leaderboard report
Scene Flow Estimation KITTI 2015 Scene Flow Test Multi-Mono-SF Fl-all 19.54 #3 of 4 Archive leaderboard report
Scene Flow Estimation KITTI 2015 Scene Flow Test Multi-Mono-SF Runtime (s) 0.063 #3 of 4 Archive leaderboard report
Scene Flow Estimation KITTI 2015 Scene Flow Test Multi-Mono-SF SF-all 44.04 #3 of 4 Archive leaderboard report
Scene Flow Estimation KITTI 2015 Scene Flow Training Multi-Mono-SF Runtime (s) 0.063 #3 of 4 Archive leaderboard report
Scene Flow Estimation KITTI 2015 Scene Flow Training Multi-Mono-SF D1-all 27.33 #3 of 4 Archive leaderboard report
Scene Flow Estimation KITTI 2015 Scene Flow Training Multi-Mono-SF D2-all 30.44 #3 of 4 Archive leaderboard report
Scene Flow Estimation KITTI 2015 Scene Flow Training Multi-Mono-SF Fl-all 18.92 #3 of 4 Archive leaderboard report
Scene Flow Estimation KITTI 2015 Scene Flow Training Multi-Mono-SF SF-all 39.82 #3 of 4 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

LSTMSigmoid ActivationTanh Activation

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