Papers › M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with...

M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers

24 Apr 2021arXiv:2104.11896archive 2025-07-28

Tianrui Guan, Jun Wang, Shiyi Lan, Rohan Chandra, Zuxuan Wu, Larry Davis, Dinesh Manocha

We present a novel architecture for 3D object detection, M3DeTR, which combines different point cloud representations (raw, voxels, bird-eye view) with different feature scales based on multi-scale feature pyramids. M3DeTR is the first approach that unifies multiple point cloud representations, feature scales, as well as models mutual relationships between point clouds simultaneously using transformers. We perform extensive ablation experiments that highlight the benefits of fusing representation and scale, and modeling the relationships. Our method achieves state-of-the-art performance on the KITTI 3D object detection dataset and Waymo Open Dataset. Results show that M3DeTR improves the baseline significantly by 1.48% mAP for all classes on Waymo Open Dataset. In particular, our approach ranks 1st on the well-known KITTI 3D Detection Benchmark for both car and cyclist classes, and ranks 1st on Waymo Open Dataset with single frame point cloud input. Our code is available at: https://github.com/rayguan97/M3DETR.

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="2104.11896")

Code

Syntology Ran 0 of 7 code samples harvested from 1 repository linked to this paper; 7 have no recorded run.

By repository: official repository: 7 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.

rayguan97/M3DeTR 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

7 samples harvested; 0 ran; 0 honoured the contract we drafted; 7 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.

7unverified

Licence: 0 of the 7 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 rayguan97/M3DeTR. “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.

build_transformer rayguan97/M3DeTR/pcdet/models/backbones_2d/transformer.py official repository unverified Apache-2.0 (permissive) · 87f4c841962a967b · report
cfg_from_yaml_file rayguan97/M3DeTR/pcdet/config.py official repository unverified Apache-2.0 (permissive) · 44db2351bcc0bffe · report
compute_fg_mask rayguan97/M3DeTR/pcdet/utils/loss_utils.py official repository unverified Apache-2.0 (permissive) · 65fe32ede00e7dcb · report
get_corner_loss_lidar rayguan97/M3DeTR/pcdet/utils/loss_utils.py official repository unverified Apache-2.0 (permissive) · 1780d388cc532a6d · report
merge_new_config rayguan97/M3DeTR/pcdet/config.py official repository unverified Apache-2.0 (permissive) · 50e8e8cdfc5129f0 · report
neg_loss_cornernet rayguan97/M3DeTR/pcdet/utils/loss_utils.py official repository unverified Apache-2.0 (permissive) · 488b91d67a807558 · report
post_act_block rayguan97/M3DeTR/pcdet/models/backbones_3d/spconv_backbone.py official repository unverified Apache-2.0 (permissive) · 2b4e0558df870bf9 · report

Tasks

3D Object DetectionObject Detectionobject-detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection KITTI Cars Easy M3DeTR AP 90.28% #7 of 26 Archive leaderboard report
3D Object Detection KITTI Cars Easy val M3DeTR AP 92.29 #3 of 11 Archive leaderboard report
3D Object Detection KITTI Cars Hard M3DeTR AP 76.96% #7 of 25 Archive leaderboard report
3D Object Detection KITTI Cars Hard val M3DeTR AP 82.85 #1 of 10 Archive leaderboard report
3D Object Detection KITTI Cars Moderate val M3DeTR AP 85.41 #2 of 11 Archive leaderboard report
3D Object Detection KITTI Cyclist Easy val M3DeTR AP 89.13 #1 of 4 Archive leaderboard report
3D Object Detection KITTI Cyclist Hard val M3DeTR AP 68.29 #1 of 4 Archive leaderboard report
3D Object Detection KITTI Cyclist Moderate val M3DeTR AP 71.70 #1 of 4 Archive leaderboard report
3D Object Detection KITTI Cyclists Easy M3DeTR AP 83.83% #2 of 12 Archive leaderboard report
3D Object Detection KITTI Cyclists Hard M3DeTR AP 59.03% #2 of 12 Archive leaderboard report
3D Object Detection KITTI Cyclists Moderate M3DeTR AP 66.74% #2 of 13 Archive leaderboard report
3D Object Detection KITTI Pedestrian Easy val M3DeTR AP 67.64 #3 of 4 Archive leaderboard report
3D Object Detection KITTI Pedestrian Hard val M3DeTR AP 56.49 #2 of 4 Archive leaderboard report
3D Object Detection KITTI Pedestrian Moderate val M3DeTR AP 60.63 #3 of 4 Archive leaderboard report
3D Object Detection KITTI Pedestrians Easy M3DeTR AP 47.05% #8 of 9 Archive leaderboard report
3D Object Detection KITTI Pedestrians Hard M3DeTR AP 38.75% #8 of 9 Archive leaderboard report
3D Object Detection KITTI Pedestrians Moderate M3DeTR AP 41.02% #11 of 12 Archive leaderboard report
3D Object Detection waymo cyclist M3DeTR APH/L2 67.28 #7 of 7 Archive leaderboard report
3D Object Detection waymo pedestrian M3DeTR APH/L2 68.20 #7 of 7 Archive leaderboard report
3D Object Detection waymo vehicle M3DeTR AP 77.09 #6 of 8 Archive leaderboard report
3D Object Detection waymo vehicle M3DeTR APH/L2 70.54 #6 of 8 Archive leaderboard report
3D Object Detection waymo vehicle M3DeTR L1 mAP 77.66 #6 of 8 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.

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