Papers › RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving

RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving

10 Jan 2020ECCV 2020 8arXiv:2001.03343archive 2025-07-28

Peixuan Li, Huaici Zhao, PengFei Liu, Feidao Cao

In this work, we propose an efficient and accurate monocular 3D detection framework in single shot. Most successful 3D detectors take the projection constraint from the 3D bounding box to the 2D box as an important component. Four edges of a 2D box provide only four constraints and the performance deteriorates dramatically with the small error of the 2D detector. Different from these approaches, our method predicts the nine perspective keypoints of a 3D bounding box in image space, and then utilize the geometric relationship of 3D and 2D perspectives to recover the dimension, location, and orientation in 3D space. In this method, the properties of the object can be predicted stably even when the estimation of keypoints is very noisy, which enables us to obtain fast detection speed with a small architecture. Training our method only uses the 3D properties of the object without the need for external networks or supervision data. Our method is the first real-time system for monocular image 3D detection while achieves state-of-the-art performance on the KITTI benchmark. Code will be released at https://github.com/Banconxuan/RTM3D.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2001.03343")

Code

Syntology Ran 11 of 16 code samples harvested from 2 repositories linked to this paper; 5 have no recorded run. Of those that ran: 3 ran · honoured contract; 3 ran · our draft was wrong; 5 ran with no contract checked.

By repository: official repository: 3 samples from 1 repository, 3 ran; community (archive-listed): 13 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Banconxuan/RTM3D officialmentioned in papermentioned on GitHubpytorch report
maudzung/RTM3D mentioned on GitHubpytorchMIT 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

16 samples harvested; 11 ran; 3 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

3ran · honoured contract
3ran · our draft was wrong
5ran
5unverified

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; each sample names its own and says which. “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.

read_clib Banconxuan/RTM3D/src/tools/kitti.py official repository ran · honoured contract MIT (permissive) · de329cc98c9f786d · report
read_clib0 Banconxuan/RTM3D/src/tools/kitti.py official repository ran · honoured contract MIT (permissive) · 9daaaaf61eccf5c9 · report
read_clib3 Banconxuan/RTM3D/src/tools/kitti.py official repository ran · honoured contract MIT (permissive) · 3252b60b8cec216a · report
compute_bin_loss maudzung/RTM3D/src/losses/losses.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 65d7a40d70c53ed9 · report
compute_box_3d maudzung/RTM3D/src/data_process/kitti_data_utils.py community (archive-listed) ran MIT (permissive) · 480409d49471d790 · report
compute_res_loss maudzung/RTM3D/src/losses/losses.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 7df13fb9e54d592b · report
conv3x3 maudzung/RTM3D/src/models/fpn_resnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
get_alpha maudzung/RTM3D/src/utils/evaluation_utils.py community (archive-listed) ran MIT (permissive) · f1dbc18e2080c03e · report
get_num_parameters maudzung/RTM3D/src/models/model_utils.py community (archive-listed) ran MIT (permissive) · 7bf982cd2568c239 · report
get_pred_depth maudzung/RTM3D/src/utils/evaluation_utils.py community (archive-listed) ran fingerprinted MIT (permissive) · 80a8f885a0f16ba6 · report
roty maudzung/RTM3D/src/data_process/kitti_data_utils.py community (archive-listed) ran fingerprinted MIT (permissive) · f83dc76e5a02776d · report
compute_rot_loss maudzung/RTM3D/src/losses/losses.py community (archive-listed) unverified MIT (permissive) · 9d749234d255406c · report
get_pose_net maudzung/RTM3D/src/models/fpn_resnet.py community (archive-listed) unverified MIT (permissive) · 53da3f0e2c240363 · report
get_pose_net maudzung/RTM3D/src/models/resnet.py community (archive-listed) unverified MIT (permissive) · da3cdf1c124aa18f · report
make_data_parallel maudzung/RTM3D/src/models/model_utils.py community (archive-listed) unverified MIT (permissive) · cbb1e79cf3f516f7 · report
rtm3d_decode maudzung/RTM3D/src/utils/evaluation_utils.py community (archive-listed) unverified MIT (permissive) · 296d581d9aac4538 · report

Tasks

Autonomous DrivingVehicle Pose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Vehicle Pose Estimation KITTI Cars Hard RTM-3D Average Orientation Similarity 77.18 #6 of 19 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