Papers › Learning Depth-Guided Convolutions for Monocular 3D Object Detection

Learning Depth-Guided Convolutions for Monocular 3D Object Detection

10 Dec 2019CVPR 2020 6arXiv:1912.04799archive 2025-07-28

Mingyu Ding, Yuqi Huo, Hongwei Yi, Zhe Wang, Jianping Shi, Zhiwu Lu, Ping Luo

3D object detection from a single image without LiDAR is a challenging task due to the lack of accurate depth information. Conventional 2D convolutions are unsuitable for this task because they fail to capture local object and its scale information, which are vital for 3D object detection. To better represent 3D structure, prior arts typically transform depth maps estimated from 2D images into a pseudo-LiDAR representation, and then apply existing 3D point-cloud based object detectors. However, their results depend heavily on the accuracy of the estimated depth maps, resulting in suboptimal performance. In this work, instead of using pseudo-LiDAR representation, we improve the fundamental 2D fully convolutions by proposing a new local convolutional network (LCN), termed Depth-guided Dynamic-Depthwise-Dilated LCN (D⁴LCN), where the filters and their receptive fields can be automatically learned from image-based depth maps, making different pixels of different images have different filters. D⁴LCN overcomes the limitation of conventional 2D convolutions and narrows the gap between image representation and 3D point cloud representation. Extensive experiments show that D⁴LCN outperforms existing works by large margins. For example, the relative improvement of D⁴LCN against the state-of-the-art on KITTI is 9.1\% in the moderate setting. The code is available at https://github.com/dingmyu/D4LCN.

PaperPDFConference PDFCodeCode 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="1912.04799")

Code

Syntology Ran 2 of 16 code samples harvested from 1 repository linked to this paper; 14 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 16 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

dingmyu/D4LCN officialmentioned in paperpytorchMIT report
Chenzixi1/D4LCNpaddle mentioned on GitHubpaddle 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; 2 ran; 0 honoured the contract we drafted; 14 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.

1ran · our draft was wrong
1ran · fixture could not drive it
14unverified

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 dingmyu/D4LCN. “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.

conv3x3 dingmyu/D4LCN/models/resnet.py official repository ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
py_cpu_nms dingmyu/D4LCN/lib/nms/py_cpu_nms.py official repository ran · fixture could not drive it MIT (permissive) · 5502a789c2da0e5e · report
absolute_import dingmyu/D4LCN/lib/util.py official repository unverified MIT (permissive) · 1f9619e12d3bd0b1 · report
anchor_center dingmyu/D4LCN/lib/rpn_util.py official repository unverified MIT (permissive) · 86a6965b9bf27579 · report
cluster_anchors dingmyu/D4LCN/lib/rpn_util.py official repository unverified MIT (permissive) · 1469325b29d17885 · report
compute_targets dingmyu/D4LCN/lib/rpn_util.py official repository unverified MIT (permissive) · 9e27707b6ba89592 · report
dynamic_local_filtering dingmyu/D4LCN/models/resnet_dilate.py official repository unverified MIT (permissive) · 9a981aab334c245b · report
init_config dingmyu/D4LCN/lib/core.py official repository unverified MIT (permissive) · 241163a78260b639 · report
init_log_file dingmyu/D4LCN/lib/util.py official repository unverified MIT (permissive) · 992842247d4e98e5 · report
intersect dingmyu/D4LCN/lib/core.py official repository unverified MIT (permissive) · e214e5ed10c86a42 · report
pretty_print dingmyu/D4LCN/lib/util.py official repository unverified MIT (permissive) · aacaef36624e2635 · report
read_kitti_cal dingmyu/D4LCN/lib/imdb_util.py official repository unverified MIT (permissive) · 94692e33979fd4e6 · report
read_kitti_label dingmyu/D4LCN/lib/imdb_util.py official repository unverified MIT (permissive) · 9bba40886e60c915 · report
read_kitti_poses dingmyu/D4LCN/lib/imdb_util.py official repository unverified MIT (permissive) · 09bdf9f5b1f17bb7 · report
resnet18 dingmyu/D4LCN/models/resnet.py official repository unverified MIT (permissive) · e72da04e104d0cd4 · report
resnet34 dingmyu/D4LCN/models/resnet.py official repository unverified MIT (permissive) · aa939462813f803e · report

Tasks

3D Object DetectionMonocular 3D Object DetectionObjectObject DetectionVehicle Pose Estimationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular 3D Object Detection KITTI Cars Moderate D4LCN AP Medium 11.72 #22 of 29 Archive leaderboard report
Vehicle Pose Estimation KITTI Cars Hard D4LCN Average Orientation Similarity 63.98 #17 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