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 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="1907.06038")

Code

Syntology Ran 5 of 21 code samples harvested from 2 repositories linked to this paper; 16 have no recorded run. Of those that ran: 1 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 15 samples from 1 repository, 1 ran; community (archive-listed): 6 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

garrickbrazil/M3D-RPN officialmentioned on GitHubpytorchMIT report
JuliaChae/M3D-RPN-Waymo mentioned on GitHubMIT report
Nicholasli1995/EgoNet mentioned on GitHubpytorchMIT report
abhi1kumar/M3D-RPN 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

21 samples harvested; 5 ran; 0 honoured the contract we drafted; 16 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.

1ran · fixture could not drive it
4ran
16unverified

Licence: 0 of the 21 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.

py_cpu_nms garrickbrazil/M3D-RPN/lib/nms/py_cpu_nms.py official repository ran · fixture could not drive it MIT (permissive) · 5502a789c2da0e5e · report
absolute_import garrickbrazil/M3D-RPN/lib/util.py official repository unverified MIT (permissive) · 1f9619e12d3bd0b1 · report
anchor_center garrickbrazil/M3D-RPN/lib/rpn_util.py official repository unverified MIT (permissive) · 86a6965b9bf27579 · report
build garrickbrazil/M3D-RPN/models/densenet121_3d_dilate.py official repository unverified MIT (permissive) · 1c47eb3c9a5da30c · report
build garrickbrazil/M3D-RPN/models/densenet121_3d_dilate_depth_aware.py official repository unverified MIT (permissive) · 2e3da10ee5eae517 · report
cluster_anchors garrickbrazil/M3D-RPN/lib/rpn_util.py official repository unverified MIT (permissive) · 1469325b29d17885 · report
compute_targets garrickbrazil/M3D-RPN/lib/rpn_util.py official repository unverified MIT (permissive) · 7f925af944ec63a0 · report
init_config garrickbrazil/M3D-RPN/lib/core.py official repository unverified MIT (permissive) · 241163a78260b639 · report
init_log_file garrickbrazil/M3D-RPN/lib/util.py official repository unverified MIT (permissive) · 992842247d4e98e5 · report
init_training_model garrickbrazil/M3D-RPN/lib/core.py official repository unverified MIT (permissive) · b5c639f7e9d994b4 · report
intersect garrickbrazil/M3D-RPN/lib/core.py official repository unverified MIT (permissive) · e214e5ed10c86a42 · report
pretty_print garrickbrazil/M3D-RPN/lib/util.py official repository unverified MIT (permissive) · aacaef36624e2635 · report
read_kitti_cal garrickbrazil/M3D-RPN/lib/imdb_util.py official repository unverified MIT (permissive) · 94692e33979fd4e6 · report
read_kitti_label garrickbrazil/M3D-RPN/lib/imdb_util.py official repository unverified MIT (permissive) · 4d197b1fa08418dd · report
read_kitti_poses garrickbrazil/M3D-RPN/lib/imdb_util.py official repository unverified MIT (permissive) · 09bdf9f5b1f17bb7 · report
get_frame_path JuliaChae/M3D-RPN-Waymo/eval/kitti_eval.py community (archive-listed) ran MIT (permissive) · dd9fd89ee08ba7b7 · report
get_image_index_str JuliaChae/M3D-RPN-Waymo/eval/kitti_common.py community (archive-listed) ran fingerprinted MIT (permissive) · 1dc11b0b2fb74958 · report
get_image_path JuliaChae/M3D-RPN-Waymo/eval/kitti_common.py community (archive-listed) ran MIT (permissive) · 36f5f743192471d9 · report
read_waymo_label JuliaChae/M3D-RPN-Waymo/lib/waymo_imdb_util.py community (archive-listed) ran MIT (permissive) · 1629055176e9c1ba · report
get_kitti_info_path JuliaChae/M3D-RPN-Waymo/eval/kitti_common.py community (archive-listed) unverified MIT (permissive) · 5c106ea84838b5a0 · report
read_waymo_cal JuliaChae/M3D-RPN-Waymo/lib/waymo_imdb_util.py community (archive-listed) 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