Papers › Kinematic 3D Object Detection in Monocular Video

Kinematic 3D Object Detection in Monocular Video

19 Jul 2020ECCV 2020 8arXiv:2007.09548archive 2025-07-28

Garrick Brazil, Gerard Pons-Moll, Xiaoming Liu, Bernt Schiele

Perceiving the physical world in 3D is fundamental for self-driving applications. Although temporal motion is an invaluable resource to human vision for detection, tracking, and depth perception, such features have not been thoroughly utilized in modern 3D object detectors. In this work, we propose a novel method for monocular video-based 3D object detection which carefully leverages kinematic motion to improve precision of 3D localization. Specifically, we first propose a novel decomposition of object orientation as well as a self-balancing 3D confidence. We show that both components are critical to enable our kinematic model to work effectively. Collectively, using only a single model, we efficiently leverage 3D kinematics from monocular videos to improve the overall localization precision in 3D object detection while also producing useful by-products of scene dynamics (ego-motion and per-object velocity). We achieve state-of-the-art performance on monocular 3D object detection and the Bird's Eye View tasks within the KITTI self-driving dataset.

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="2007.09548")

Code

Syntology Ran 3 of 20 code samples harvested from 1 repository linked to this paper; 17 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 20 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Nicholasli1995/EgoNet mentioned on GitHubpytorchMIT report
garrickbrazil/kinematic3d mentioned on GitHubpytorch 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

20 samples harvested; 3 ran; 0 honoured the contract we drafted; 17 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.

2ran · our draft was wrong
1ran · fixture could not drive it
17unverified

Licence: 0 of the 20 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 Nicholasli1995/EgoNet. “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.

affine_transform Nicholasli1995/EgoNet/libs/common/img_proc.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · 83abf1ce90db7100 · report
basicdownsample Nicholasli1995/EgoNet/libs/model/heatmapModel/hrnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 01a97ab430ea6b53 · report
conv3x3 Nicholasli1995/EgoNet/libs/model/heatmapModel/hrnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
camera_to_world_frame Nicholasli1995/EgoNet/libs/common/transformation.py community (archive-listed) unverified MIT (permissive) · 60a783020da65982 · report
format_str_submission Nicholasli1995/EgoNet/libs/common/format.py community (archive-listed) unverified MIT (permissive) · 3cc14f34cae92fb1 · report
get_PCK Nicholasli1995/EgoNet/libs/metric/criterions.py community (archive-listed) unverified MIT (permissive) · 368190b1b5b3b5fc · report
get_affine_transform Nicholasli1995/EgoNet/libs/common/img_proc.py community (archive-listed) unverified MIT (permissive) · 0749713c6ab68724 · report
get_angle_error Nicholasli1995/EgoNet/libs/metric/criterions.py community (archive-listed) unverified MIT (permissive) · c7bcfcd2a2856ad7 · report
get_comp_dict Nicholasli1995/EgoNet/libs/loss/function.py community (archive-listed) unverified MIT (permissive) · 00e9a2fcfbd05cf8 · report
get_dirs Nicholasli1995/EgoNet/libs/logger/logger.py community (archive-listed) unverified MIT (permissive) · ec239c087bc001fa · report
get_distance Nicholasli1995/EgoNet/libs/metric/criterions.py community (archive-listed) unverified MIT (permissive) · a11733449ce5e5e0 · report
get_fc_model Nicholasli1995/EgoNet/libs/model/FCmodel.py community (archive-listed) unverified MIT (permissive) · 41632cbbe6ec6dc1 · report
get_instance_str Nicholasli1995/EgoNet/libs/common/format.py community (archive-listed) unverified MIT (permissive) · ff857105336a55b1 · report
get_model_summary Nicholasli1995/EgoNet/libs/common/utils.py community (archive-listed) unverified MIT (permissive) · adf71efd4bd77c7e · report
get_pred_str Nicholasli1995/EgoNet/libs/common/format.py community (archive-listed) unverified MIT (permissive) · b853d5c9bc73035c · report
is_freezed Nicholasli1995/EgoNet/libs/model/heatmapModel/hrnet.py community (archive-listed) unverified MIT (permissive) · 16cfb496b9f7fcee · report
move_to Nicholasli1995/EgoNet/libs/common/transformation.py community (archive-listed) unverified MIT (permissive) · 4367e9e28855609c · report
read_yaml_file Nicholasli1995/EgoNet/libs/arguments/parse.py community (archive-listed) unverified MIT (permissive) · b4f9a04dd604efae · report
transform_preds Nicholasli1995/EgoNet/libs/common/img_proc.py community (archive-listed) unverified MIT (permissive) · 22240ba992aac7c7 · report
world_to_camera_frame Nicholasli1995/EgoNet/libs/common/transformation.py community (archive-listed) unverified MIT (permissive) · 06dd3c5363dff6f9 · report

Tasks

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

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection Rope3D Kinematic3D+(G) AP@0.7 17.74 #6 of 8 Archive leaderboard report
Monocular 3D Object Detection KITTI Cars Moderate Kinematic3D AP Medium 12.72 #15 of 29 Archive leaderboard report
Vehicle Pose Estimation KITTI Cars Hard Kinematic3D Average Orientation Similarity 34.81 #19 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