Papers › 3D Object Detection with a Self-supervised Lidar Scene Flow Backbone

3D Object Detection with a Self-supervised Lidar Scene Flow Backbone

2 May 2022arXiv:2205.00705archive 2025-07-28

Ekim Yurtsever, Emeç Erçelik, MingYu Liu, Zhijie Yang, Hanzhen Zhang, Pınar Topçam, Maximilian Listl, Yılmaz Kaan Çaylı, Alois Knoll

State-of-the-art lidar-based 3D object detection methods rely on supervised learning and large labeled datasets. However, annotating lidar data is resource-consuming, and depending only on supervised learning limits the applicability of trained models. Self-supervised training strategies can alleviate these issues by learning a general point cloud backbone model for downstream 3D vision tasks. Against this backdrop, we show the relationship between self-supervised multi-frame flow representations and single-frame 3D detection hypotheses. Our main contribution leverages learned flow and motion representations and combines a self-supervised backbone with a supervised 3D detection head. First, a self-supervised scene flow estimation model is trained with cycle consistency. Then, the point cloud encoder of this model is used as the backbone of a single-frame 3D object detection head model. This second 3D object detection model learns to utilize motion representations to distinguish dynamic objects exhibiting different movement patterns. Experiments on KITTI and nuScenes benchmarks show that the proposed self-supervised pre-training increases 3D detection performance significantly. https://github.com/emecercelik/ssl-3d-detection.git

PaperPDFCodeCode Syntology ranMethod as code

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

The archive's official repository (emecercelik/ssl-3d-detection) was not harvested; the 16 samples below come from 2 repositories the archive does not mark official.

Syntology 16 code samples harvested from 2 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: found in paper text by Syntology: 16 samples from 2 repositories, 10 ran (10 with no instrument failure; 0 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

emecercelik/ssl-3d-detection officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
zhijie-yang/zhijie-yang.github.io mentioned on GitHubSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

16 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

10ran
6unverified

Licence: 0 of the 16 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

WeijingShi/Point-GNN found in paper text by Syntology 15 samples, 10 ran (0 instrument-failed) · 5 unverified
box3d_to_cam_points dataset/kitti_dataset.py ran MIT (permissive) · 0141f393c163c9c5 · report fixture: signature label:dict/0/?, expend_factor:tuple/1/float · returned Points · level recorded 2026-09-24
boxes_3d_to_corners models/nms.py ran MIT (permissive) · 7283711d920302c1 · report fixture: signature boxes_3d:ndarray/2/float · returned ndarray · level recorded 2026-09-24
center_box_encoding models/box_encoding.py ran MIT (permissive) · 4855767c4a56c8c8 · report fixture: signature cls_labels:Tensor/1/int, points_xyz:Tensor/2/float, boxes_3d:Tensor/2/float · returned Tensor · level recorded 2026-09-24
direct_box_decoding models/box_encoding.py ran MIT (permissive) · be80ed9b38980068 · report fixture: signature cls_labels:Tensor/1/int, points_xyz:Tensor/2/float, encoded_boxes:Tensor/2/float · returned Tensor · level recorded 2026-09-24
direct_box_encoding models/box_encoding.py ran MIT (permissive) · 9e3ebce01f03bd3d · report fixture: signature cls_labels:Tensor/1/int, points_xyz:Tensor/3/float, boxes_3d:Tensor/3/float · returned Tensor · level recorded 2026-09-24
downsample_by_average_voxel dataset/kitti_dataset.py ran MIT (permissive) · ee3750781dc56c2b · report fixture: signature points:Points/1/ndarray, voxel_size:float/0/float · returned Points · level recorded 2026-09-24
downsample_by_random_voxel dataset/kitti_dataset.py ran MIT (permissive) · 384b9e6949fc0b72 · report fixture: signature points:Points/1/ndarray, voxel_size:float/0/float, add_rnd3d:bool/0/bool · returned Points · level recorded 2026-09-24
load_config in 389 papers util/config_util.py ran MIT (permissive) · 434c5a9cd34a6dcc · report fixture: signature filename:str/0/str · returned dict · level recorded 2026-09-24
load_train_config util/config_util.py ran MIT (permissive) · 2df98c5f04b6fb17 · report fixture: signature filename:str/0/str · returned dict · level recorded 2026-09-24
multi_layer_downsampling_random models/graph_gen.py ran MIT (permissive) · 5794795650533553 · report fixture: signature points_xyz:ndarray/2/float, base_voxel_size:float/0/float, levels:list/1/int, add_rnd3d:bool/0/bool · returned tuple · level recorded 2026-09-24
average_gradients in 20 papers util/tf_util.py unverified MIT (permissive) · a0172c48afaa4a94 · report
focal_loss_sigmoid models/loss.py unverified MIT (permissive) · dce4ab6cd7b4540f · report
focal_loss_softmax models/loss.py unverified MIT (permissive) · 9fc528f84f0af21b · report
instance_normalization models/gnn.py unverified MIT (permissive) · cbc514a51f3ff453 · report
overlapped_boxes_3d models/nms.py unverified MIT (permissive) · 487eda418ebb9106 · report
HimangiM/Just-Go-with-the-Flow-Self-Supervised-Scene-Flow-Estimation found in paper text by Syntology 1 sample, 0 ran · 1 unverified
get_model_flow src/model_concat_upsa_cycle.py unverified BSD-3-Clause (permissive) · e1762f3d022bfacd · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for self-supervised Lidar Scene Flow Backbone (graph method: self-supervised Lidar Scene Flow Backbone). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

  1. get_model_flow entry · level 0 · unverified · e1762f3d022bfacd

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2205.00705") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Object DetectionObjectObject DetectionScene Flow EstimationSelf-Supervised LearningSelf-supervised Scene Flow Estimationobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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