Papers › Commonsense Prototype for Outdoor Unsupervised 3D Object Detection

Commonsense Prototype for Outdoor Unsupervised 3D Object Detection

25 Apr 2024CVPR 2024 1arXiv:2404.16493archive 2025-07-28

Hai Wu, Shijia Zhao, Xun Huang, Chenglu Wen, Xin Li, Cheng Wang

The prevalent approaches of unsupervised 3D object detection follow cluster-based pseudo-label generation and iterative self-training processes. However, the challenge arises due to the sparsity of LiDAR scans, which leads to pseudo-labels with erroneous size and position, resulting in subpar detection performance. To tackle this problem, this paper introduces a Commonsense Prototype-based Detector, termed CPD, for unsupervised 3D object detection. CPD first constructs Commonsense Prototype (CProto) characterized by high-quality bounding box and dense points, based on commonsense intuition. Subsequently, CPD refines the low-quality pseudo-labels by leveraging the size prior from CProto. Furthermore, CPD enhances the detection accuracy of sparsely scanned objects by the geometric knowledge from CProto. CPD outperforms state-of-the-art unsupervised 3D detectors on Waymo Open Dataset (WOD), PandaSet, and KITTI datasets by a large margin. Besides, by training CPD on WOD and testing on KITTI, CPD attains 90.85% and 81.01% 3D Average Precision on easy and moderate car classes, respectively. These achievements position CPD in close proximity to fully supervised detectors, highlighting the significance of our method. The code will be available at https://github.com/hailanyi/CPD.

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 20 code samples harvested from 1 repository linked to this paper: 19 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 4 honoured, 3 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 1 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: 20 samples from 1 repository, 19 ran (17 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

hailanyi/cpd officialmentioned in papermentioned on GitHubpytorchSyntology: 20 samples, 19 ran (2 instrument-failed) · 1 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

20 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 4 honoured, 3 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 1 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.

4ran · honoured contract
3ran · violated contract
2ran · our draft was wrong
10ran
1unverified

Licence: 20 of the 20 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 hailanyi/cpd. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

hailanyi/cpd official repository 20 samples, 19 ran (2 instrument-failed) · 1 unverified
ang_weight cpd/utils/bbloss.py ran fingerprinted no licence file found · pointer only · d1eaa89118501a15 · report fixture: signature pred:Tensor/2/float, gt:Tensor/2/float · returned Tensor · level recorded 2026-09-24
box_cut cpd/unsupervised_core/ob_op.py ran no licence file found · pointer only · d7c9b1efed44e3dc · report fixture: signature box:ndarray/1/float, cloud_in:ndarray/2/float, scale:float/0/float · returned tuple · level recorded 2026-09-24
cfg_from_yaml_file in 59 papers cpd/config.py ran no licence file found · pointer only · d0ffc76cfe4004c0 · report fixture: signature cfg_file:str/0/str, config:dict/0/? · returned EasyDict · level recorded 2026-09-24
compute_ephe_score cpd/unsupervised_core/precompute_ppscore.py ran · honoured contract fingerprinted no licence file found · pointer only · 26c831b550748998 · report fixture: signature count:ndarray/2/float · returned ndarray · level recorded 2026-09-24
compute_fg_mask in 36 papers cpd/utils/loss_utils.py ran no licence file found · pointer only · 65fe32ede00e7dcb · report fixture: signature gt_boxes2d:Tensor/3/float, shape:Size/1/int, downsample_factor:int/0/int, device:device/0/? · returned Tensor · level recorded 2026-09-25
compute_iou in 68 papers cpd/utils/bbloss.py ran no licence file found · pointer only · f940cdda72e1a568 · report fixture: signature x:Tensor/1/float, w:Tensor/1/float, y:Tensor/1/float, l:Tensor/1/float · returned Tensor · level recorded 2026-09-24
compute_ppscore cpd/unsupervised_core/precompute_ppscore.py ran no licence file found · pointer only · faf8996eb002472f · report fixture: signature cur_frame:ndarray/2/float, neighbor_traversals:list/1/ndarray, max_neighbor_dist:float/0/float · returned ndarray · level recorded 2026-09-24
convex_hull_intersection cpd/unsupervised_core/rotate_iou_cpu_eval.py ran · our draft was wrong no licence file found · pointer only · 31c0e5a46ae6999a · report fixture: signature p1:list/1/tuple, p2:list/1/tuple · returned tuple · level recorded 2026-09-24
count_neighbors cpd/unsupervised_core/precompute_ppscore.py ran no licence file found · pointer only · 0ca66141200cc919 · report fixture: signature ptc:ndarray/2/float, trees:dict/0/?, max_neighbor_dist:float/0/float · returned ndarray · level recorded 2026-09-24
la_sampling cpd/unsupervised_core/ob_op.py ran fingerprinted no licence file found · pointer only · 9429fa9d860f3979 · report fixture: signature points:ndarray/2/float, vert_res:float/0/float, hor_res:float/0/float · returned ndarray · level recorded 2026-09-24
limit cpd/utils/bbloss.py ran · violated contract fingerprinted no licence file found · pointer only · 998ef04f661de96c · report fixture: signature ang:ndarray/1/float · returned ndarray · level recorded 2026-09-24
merge_new_config in 59 papers cpd/config.py ran no licence file found · pointer only · 392c0cf3a1b07b12 · report fixture: signature config:dict/0/?, new_config:dict/0/? · returned EasyDict · level recorded 2026-09-25
neg_loss_cornernet in 36 papers cpd/utils/loss_utils.py ran no licence file found · pointer only · 488b91d67a807558 · report fixture: signature pred:Tensor/4/float, gt:Tensor/4/float, mask:Tensor/3/float · returned Tensor · level recorded 2026-09-25
norm in 120 papers
census: 23 implementations from 26 papers, 15 distinct outputs across 6 buckets, one shared input per bucket
cpd/unsupervised_core/outline_utils.py ran · violated contract fingerprinted no licence file found · pointer only · 3713fc3b4eb6a572 · report fixture: signature z:Tensor/1/float · returned Tensor · level recorded 2026-09-24
poly_area in 7 papers cpd/unsupervised_core/rotate_iou_cpu_eval.py ran · violated contract fingerprinted no licence file found · pointer only · e5929ca970405ef7 · report fixture: signature x:ndarray/1/float, y:ndarray/1/float · returned float64 · level recorded 2026-09-24
polygon_clip cpd/unsupervised_core/rotate_iou_cpu_eval.py ran · our draft was wrong no licence file found · pointer only · 05b20b55c5918c4a · report fixture: signature subjectPolygon:list/1/tuple, clipPolygon:list/1/tuple · returned list · level recorded 2026-09-24
sigmoid in 216 papers
census: 36 implementations from 56 papers, 7 distinct outputs across 3 buckets, one shared input per bucket
cpd/unsupervised_core/outline_utils.py ran · honoured contract fingerprinted no licence file found · pointer only · c2f8b16d86cde8e1 · report fixture: signature x:float/0/float · returned float64 · level recorded 2026-09-24
softmax in 240 papers
census: 53 implementations from 63 papers, 16 distinct outputs across 8 buckets, one shared input per bucket
cpd/unsupervised_core/outline_utils.py ran · honoured contract fingerprinted no licence file found · pointer only · 777a44a7613e767e · report fixture: signature z:ndarray/2/float · returned ndarray · level recorded 2026-09-24
to_sphere_coords cpd/unsupervised_core/ob_op.py ran · honoured contract fingerprinted no licence file found · pointer only · a0564afa0a884968 · report fixture: signature points:ndarray/2/float · returned ndarray · level recorded 2026-09-24
get_corner_loss_lidar in 51 papers cpd/utils/loss_utils.py unverified no licence file found · pointer only · 1780d388cc532a6d · report

Tasks

3D Object DetectionObjectObject DetectionPseudo Labelobject-detection

1 archive task tag without a task page not shown.

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