Papers › PWOC-3D: Deep Occlusion-Aware End-to-End Scene Flow Estimation

PWOC-3D: Deep Occlusion-Aware End-to-End Scene Flow Estimation

12 Apr 2019arXiv:1904.06116archive 2025-07-28

Rohan Saxena, René Schuster, Oliver Wasenmüller, Didier Stricker

In the last few years, convolutional neural networks (CNNs) have demonstrated increasing success at learning many computer vision tasks including dense estimation problems such as optical flow and stereo matching. However, the joint prediction of these tasks, called scene flow, has traditionally been tackled using slow classical methods based on primitive assumptions which fail to generalize. The work presented in this paper overcomes these drawbacks efficiently (in terms of speed and accuracy) by proposing PWOC-3D, a compact CNN architecture to predict scene flow from stereo image sequences in an end-to-end supervised setting. Further, large motion and occlusions are well-known problems in scene flow estimation. PWOC-3D employs specialized design decisions to explicitly model these challenges. In this regard, we propose a novel self-supervised strategy to predict occlusions from images (learned without any labeled occlusion data). Leveraging several such constructs, our network achieves competitive results on the KITTI benchmark and the challenging FlyingThings3D dataset. Especially on KITTI, PWOC-3D achieves the second place among end-to-end deep learning methods with 48 times fewer parameters than the top-performing method.

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="1904.06116")

Code

Syntology Ran 0 of 12 code samples harvested from 1 repository linked to this paper; 12 have no recorded run.

By repository: official repository: 12 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.

dfki-av/pwoc-3d officialtfMIT 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

12 samples harvested; 0 ran; 0 honoured the contract we drafted; 12 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.

12unverified

Licence: 0 of the 12 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 dfki-av/pwoc-3d. “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.

ContextNetwork dfki-av/pwoc-3d/modules.py official repository unverified MIT (permissive) · 1f67eea1467aebaa · report
FeaturePyramidNetwork dfki-av/pwoc-3d/modules.py official repository unverified MIT (permissive) · fee9a2fca6892a27 · report
SceneFlowEstimator dfki-av/pwoc-3d/modules.py official repository unverified MIT (permissive) · 1ca3acaeab51cd2c · report
finetuning_loss dfki-av/pwoc-3d/losses.py official repository unverified MIT (permissive) · 30adef1baad9e220 · report
get_ft3d_dataset dfki-av/pwoc-3d/datasets.py official repository unverified MIT (permissive) · 3bf1984356663fec · report
get_kitti_dataset dfki-av/pwoc-3d/datasets.py official repository unverified MIT (permissive) · 08ca9fdab4094786 · report
get_spring_dataset dfki-av/pwoc-3d/datasets.py official repository unverified MIT (permissive) · f82a91175fcdb4fa · report
load_kitti_images dfki-av/pwoc-3d/utils.py official repository unverified MIT (permissive) · 073f8ee6988dd609 · report
load_pfm dfki-av/pwoc-3d/utils.py official repository unverified MIT (permissive) · a946b59a08ddf4e9 · report
loss_per_scale dfki-av/pwoc-3d/losses.py official repository unverified MIT (permissive) · 311eef1ba88e22c8 · report
multi_scale_loss dfki-av/pwoc-3d/losses.py official repository unverified MIT (permissive) · 943cea4c9f6c8d4e · report
read_sfl_file dfki-av/pwoc-3d/utils.py official repository unverified MIT (permissive) · e54e5bdb1c932798 · report

Tasks

Optical Flow EstimationScene Flow EstimationStereo MatchingStereo Matching Hand

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Flow Estimation KITTI 2015 Scene Flow Test PWOC-3D D1-all 5.13 #2 of 4 Archive leaderboard report
Scene Flow Estimation KITTI 2015 Scene Flow Test PWOC-3D D2-all 8.46 #2 of 4 Archive leaderboard report
Scene Flow Estimation KITTI 2015 Scene Flow Test PWOC-3D Fl-all 12.96 #2 of 4 Archive leaderboard report
Scene Flow Estimation KITTI 2015 Scene Flow Test PWOC-3D Runtime (s) 0.13 #2 of 4 Archive leaderboard report
Scene Flow Estimation KITTI 2015 Scene Flow Test PWOC-3D SF-all 15.69 #2 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

SPEED

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