Papers › M3D-RPN: Monocular 3D Region Proposal Network for Object Detection

M3D-RPN: Monocular 3D Region Proposal Network for Object Detection

13 Jul 2019ICCV 2019 10arXiv:1907.06038archive 2025-07-28

Garrick Brazil, Xiaoming Liu

Understanding the world in 3D is a critical component of urban autonomous driving. Generally, the combination of expensive LiDAR sensors and stereo RGB imaging has been paramount for successful 3D object detection algorithms, whereas monocular image-only methods experience drastically reduced performance. We propose to reduce the gap by reformulating the monocular 3D detection problem as a standalone 3D region proposal network. We leverage the geometric relationship of 2D and 3D perspectives, allowing 3D boxes to utilize well-known and powerful convolutional features generated in the image-space. To help address the strenuous 3D parameter estimations, we further design depth-aware convolutional layers which enable location specific feature development and in consequence improved 3D scene understanding. Compared to prior work in monocular 3D detection, our method consists of only the proposed 3D region proposal network rather than relying on external networks, data, or multiple stages. M3D-RPN is able to significantly improve the performance of both monocular 3D Object Detection and Bird's Eye View tasks within the KITTI urban autonomous driving dataset, while efficiently using a shared multi-class model.

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 21 code samples harvested from 2 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 5 ran (4 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 6 samples from 1 repository, 4 ran (4 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 between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

garrickbrazil/M3D-RPN officialmentioned on GitHubpytorchMITSyntology: 15 samples, 5 ran (1 instrument-failed) · 10 unverified report
JuliaChae/M3D-RPN-Waymo mentioned on GitHubMITSyntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
Nicholasli1995/EgoNet mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Kinematic 3D Object Detection in Monocular Video (arXiv:2007.09548; that paper's own run record: 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
abhi1kumar/M3D-RPN mentioned on GitHubpytorchMITSyntology: 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

21 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 12 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.

1ran; the contract check could not run
8ran
12unverified

Licence: 1 of the 21 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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.

garrickbrazil/M3D-RPN official repository 15 samples, 5 ran (1 instrument-failed) · 10 unverified
absolute_import lib/util.py ran MIT (permissive) · 1f9619e12d3bd0b1 · report fixture: signature file_path:str/0/str · returned module · level recorded 2026-09-25
init_config in 12 papers lib/core.py ran MIT (permissive) · 241163a78260b639 · report fixture: signature conf_name:str/0/str · returned dict · level recorded 2026-09-25
init_log_file lib/util.py ran MIT (permissive) · 992842247d4e98e5 · report fixture: signature folder_path:str/0/str, suffix:str/0/str, log_level:int/0/int · returned str · level recorded 2026-09-25
pretty_print in 8 papers lib/util.py ran MIT (permissive) · aacaef36624e2635 · report fixture: signature name:str/0/str, input:dict/0/?, val_width:int/0/int, key_width:int/0/int · returned str · level recorded 2026-09-25
py_cpu_nms in 13 papers lib/nms/py_cpu_nms.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only · 5502a789c2da0e5e · report fixture: signature dets:ndarray/2/float, thresh:float/0/float · returned list · level recorded 2026-09-22
anchor_center lib/rpn_util.py unverified MIT (permissive) · 86a6965b9bf27579 · report
build in 31 papers models/densenet121_3d_dilate.py unverified MIT (permissive) · 1c47eb3c9a5da30c · report
build in 31 papers models/densenet121_3d_dilate_depth_aware.py unverified MIT (permissive) · 2e3da10ee5eae517 · report
cluster_anchors lib/rpn_util.py unverified MIT (permissive) · 1469325b29d17885 · report
compute_targets lib/rpn_util.py unverified MIT (permissive) · 7f925af944ec63a0 · report
init_training_model lib/core.py unverified MIT (permissive) · b5c639f7e9d994b4 · report
intersect in 33 papers lib/core.py unverified MIT (permissive) · e214e5ed10c86a42 · report
read_kitti_cal lib/imdb_util.py unverified MIT (permissive) · 94692e33979fd4e6 · report
read_kitti_label lib/imdb_util.py unverified MIT (permissive) · 4d197b1fa08418dd · report
read_kitti_poses lib/imdb_util.py unverified MIT (permissive) · 09bdf9f5b1f17bb7 · report
JuliaChae/M3D-RPN-Waymo community (archive-listed) 6 samples, 4 ran (0 instrument-failed) · 2 unverified
get_frame_path eval/kitti_eval.py ran MIT (permissive) · dd9fd89ee08ba7b7 · report fixture: signature db:MockDB/0/?, mode:str/0/str, eval_type:str/0/str · returned str · level recorded 2026-09-24
get_image_index_str in 7 papers eval/kitti_common.py ran fingerprinted MIT (permissive) · 1dc11b0b2fb74958 · report fixture: signature img_idx:int/0/int · returned str · level recorded 2026-09-24
get_image_path in 15 papers eval/kitti_common.py ran MIT (permissive) · 36f5f743192471d9 · report fixture: signature idx:int/0/int, prefix:str/0/str, training:bool/0/bool, relative_path:bool/0/bool · returned str · level recorded 2026-09-24
read_waymo_label lib/waymo_imdb_util.py ran MIT (permissive) · 1629055176e9c1ba · report fixture: returned list · level recorded 2026-09-24
get_kitti_info_path in 7 papers eval/kitti_common.py unverified MIT (permissive) · 5c106ea84838b5a0 · report
read_waymo_cal lib/waymo_imdb_util.py unverified MIT (permissive) · 2f75951e005a412e · report

Tasks

3D Object Detection3D Object Detection From Monocular ImagesAutonomous DrivingMonocular 3D Object DetectionObject DetectionRegion ProposalScene UnderstandingVehicle Pose Estimationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection Rope3D M3D-RPN+(G) AP@0.7 16.75 #7 of 8 Archive leaderboard report
3D Object Detection From Monocular Images Waymo Open Dataset M3D-RPN 3D mAPH Vehicle (Front Camera Only) 0.65 #3 of 3 Archive leaderboard report
Monocular 3D Object Detection KITTI Cars Moderate M3D-RPN AP Medium 9.71 #25 of 29 Archive leaderboard report
Vehicle Pose Estimation KITTI Cars Hard M3D-RPN Average Orientation Similarity 67.08 #15 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.

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