Papers › Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration

Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration

23 Jan 2024arXiv:2401.12452archive 2025-07-28

Yifan Zhang, Siyu Ren, Junhui Hou, Jinjian Wu, Yixuan Yuan, Guangming Shi

This paper introduces a novel self-supervised learning framework for enhancing 3D perception in autonomous driving scenes. Specifically, our approach, namely NCLR, focuses on 2D-3D neural calibration, a novel pretext task that estimates the rigid pose aligning camera and LiDAR coordinate systems. First, we propose the learnable transformation alignment to bridge the domain gap between image and point cloud data, converting features into a unified representation space for effective comparison and matching. Second, we identify the overlapping area between the image and point cloud with the fused features. Third, we establish dense 2D-3D correspondences to estimate the rigid pose. The framework not only learns fine-grained matching from points to pixels but also achieves alignment of the image and point cloud at a holistic level, understanding their relative pose. We demonstrate the efficacy of NCLR by applying the pre-trained backbone to downstream tasks, such as LiDAR-based 3D semantic segmentation, object detection, and panoptic segmentation. Comprehensive experiments on various datasets illustrate the superiority of NCLR over existing self-supervised methods. The results confirm that joint learning from different modalities significantly enhances the network's understanding abilities and effectiveness of learned representation. The code is publicly available at https://github.com/Eaphan/NCLR.

PaperPDFCodeCode 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 26 code samples: 23 from 2 repositories linked to this paper, 3 identical to code harvested from another paper's repository. Across all 26: 24 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 2 violated, 8 with no contract checked; 11 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 6 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 10 ran (7 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 12 samples from 1 repository, 11 ran (5 with no instrument failure; 6 where Syntology's instrument failed); 3 identical to code first harvested elsewhere. 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 24 samples that ran have no recorded date.

eaphan/nclr officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 11 samples, 10 ran (3 instrument-failed) · 1 unverified report
rsy6318/CorrI2P mentioned on GitHubpytorchSyntology: 12 samples, 11 ran (6 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

26 samples harvested: 24 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 2 violated, 8 with no contract checked; 11 where Syntology's instrument failed) · 2 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.

3ran · honoured contract
2ran · violated contract
5ran · our draft was wrong
6ran; the contract check could not run
8ran
2unverified

Licence: 26 of the 26 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. 3 samples are listed last, in a group without a repository. “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.

eaphan/nclr official repository 11 samples, 10 ran (3 instrument-failed) · 1 unverified
bilinear_interpolate_torch bevlab/models.py ran licence not identified · pointer only · d30c03f27e494c3c · report fixture: signature im:Tensor/3/float, x:Tensor/1/float, y:Tensor/1/float · returned Tensor · level recorded 2026-09-24
convert_pointclouds_to_tensor bevlab/pnp.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · fd2ccb302a5c2310 · report fixture: signature pcl:Tensor/3/float · returned tuple · level recorded 2026-09-24
create_correspondence_matrix bevlab/models.py ran licence not identified · pointer only · 3d7f0e7dd8fdeb74 · report fixture: signature cam_coords:ndarray/2/float, H:int/0/int, W:int/0/int, dist_thres:float/0/float, neg_margin:int/0/int · returned Tensor · level recorded 2026-09-24
eigh bevlab/pnp.py ran · our draft was wrong licence not identified · pointer only · 408a3d02069cff3a · report fixture: signature A:Tensor/2/float · returned linalg_eigh · level recorded 2026-09-24
get_P_from_Rt bevlab/datasets.py ran licence not identified · pointer only · 497ee1ee5d05dcd0 · report fixture: signature R:ndarray/2/float, t:ndarray/1/float · returned ndarray · level recorded 2026-09-24
interpolate_from_bev_features bevlab/models.py ran licence not identified · pointer only · 70596f28650426a1 · report fixture: signature keypoints:Tensor/2/float, coordinates:Tensor/2/int, bev_features:Tensor/4/float, batch_size:int/0/int, bev_stride:int/0/int · returned Tensor · level recorded 2026-09-24
is_pointclouds bevlab/pnp.py ran · violated contract licence not identified · pointer only · d08e64b2d73c665b · report fixture: signature pcl:MockPointclouds/0/? · returned bool · level recorded 2026-09-24
revtrans_jittering bevlab/transforms.py ran · honoured contract licence not identified · pointer only · def5efb3f261d1c1 · report fixture: signature pc:ndarray/2/float, trans_dict:dict/0/? · returned tuple · level recorded 2026-09-24
revtrans_rotation bevlab/transforms.py ran; the contract check could not run (RAISES) licence not identified · pointer only · ce2dbefef7a9a194 · report fixture: signature pc:ndarray/2/float, trans_dict:dict/0/? · returned tuple · level recorded 2026-09-24
revtrans_translation bevlab/transforms.py ran licence not identified · pointer only · d8fbeeb1bc0bfeee · report fixture: signature pc:ndarray/2/float, trans_dict:dict/0/? · returned tuple · level recorded 2026-09-24
adapt_weights in 6 papers bevlab/imagenet.py unverified licence not identified · pointer only · 6f7320d8f113ebd6 · report
rsy6318/CorrI2P community (archive-listed) 12 samples, 11 ran (6 instrument-failed) · 1 unverified
FPS pointnet.py ran · our draft was wrong fingerprinted no licence file found · pointer only · fc333893f7271b90 · report fixture: signature pc:Tensor/3/float, k:int/0/int · returned Tensor · level recorded 2026-09-24
angles2rotation_matrix nuscenes_pc_img_dataloader.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 60f2f4207ae20ab9 · report fixture: signature angles:ndarray/1/float · returned ndarray · level recorded 2026-09-24
camera_matrix_cropping nuscenes_pc_img_dataloader.py ran fingerprinted no licence file found · pointer only · 80730c3bb0cf7118 · report fixture: signature K:ndarray/2/float, dx:float/0/float, dy:float/0/float · returned ndarray · level recorded 2026-09-24
camera_matrix_scaling nuscenes_pc_img_dataloader.py ran · honoured contract fingerprinted no licence file found · pointer only · 857b8f722d0dcda1 · report fixture: signature K:ndarray/2/float, s:float/0/float · returned ndarray · level recorded 2026-09-24
conv1x1 in 691 papers imagenet.py ran · our draft was wrong no licence file found · pointer only · d9def42110729a85 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers imagenet.py ran · our draft was wrong no licence file found · pointer only · 160bb14bd76201b4 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded
desc_loss2 loss.py ran no licence file found · pointer only · 4af84e33621075ff · report fixture: signature img_features:Tensor/3/float, pc_features:Tensor/3/float, mask:Tensor/3/float, pos_margin:float/0/float, neg_margin:float/0/float, log_scale:int/0/int, num_kpt:int/0/int · returned tuple · level recorded 2026-09-24
det_loss loss.py ran no licence file found · pointer only · 77bbbfa9a1d1b7f5 · report fixture: signature img_score_inline:Tensor/3/float, img_score_outline:Tensor/2/float, pc_score_inline:Tensor/3/float, pc_score_outline:Tensor/2/float, dists:Tensor/3/float, mask:Tensor/3/float · returned Tensor · level recorded 2026-09-24
get_P_diff cal_error_all.py ran · honoured contract no licence file found · pointer only · 685179cc383d2145 · report fixture: signature P_pred_np:ndarray/2/float, P_gt_np:ndarray/2/float · returned tuple · level recorded 2026-09-24
index_points in 49 papers pointnet.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 573cb024ea47999f · report fixture: returned Tensor · level recorded 2026-09-22
square_distance in 89 papers
census: 11 implementations from 18 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 3, kind float, dtype float32 · arg 2: rank 3, kind float, dtype float32
pointnet.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 580dee6761649b29 · report fixture: returned Tensor · level recorded 2026-09-22
desc_loss loss.py unverified no licence file found · pointer only · 457b688bce1b0ffe · report
Repository not located 3 samples, 3 ran (2 instrument-failed) · 0 unverified
3 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
get_savedir_name repository not located ran · our draft was wrong licence of this copy not recorded · 6fef16c520722b39 · report fixture: signature config:dict/0/? · returned str · level recorded 2026-09-22
isnan in 24 papers
census: 3 implementations from 8 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 1, kind float, dtype float32
repository not located ran · violated contract fingerprinted licence of this copy not recorded · 5f4f4355be28c01e · report fixture: signature x:Tensor/1/float · returned Tensor · level recorded 2026-09-22
mean in 84 papers repository not located ran; the contract check could not run (RAISES) · metamorphic tier: well formed licence of this copy not recorded · ed2a67a7b19a5c07 · report fixture: signature ls:list/1/float, ignore_nan:bool/0/bool, empty:int/0/int · returned float · level recorded 2026-09-22

Tasks

3D Semantic SegmentationAutonomous DrivingObject DetectionPanoptic SegmentationSelf-Supervised LearningSemantic Segmentationobject-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