Papers › DSGN: Deep Stereo Geometry Network for 3D Object Detection

DSGN: Deep Stereo Geometry Network for 3D Object Detection

10 Jan 2020CVPR 2020 6arXiv:2001.03398archive 2025-07-28

Yilun Chen, Shu Liu, Xiaoyong Shen, Jiaya Jia

Most state-of-the-art 3D object detectors heavily rely on LiDAR sensors because there is a large performance gap between image-based and LiDAR-based methods. It is caused by the way to form representation for the prediction in 3D scenarios. Our method, called Deep Stereo Geometry Network (DSGN), significantly reduces this gap by detecting 3D objects on a differentiable volumetric representation -- 3D geometric volume, which effectively encodes 3D geometric structure for 3D regular space. With this representation, we learn depth information and semantic cues simultaneously. For the first time, we provide a simple and effective one-stage stereo-based 3D detection pipeline that jointly estimates the depth and detects 3D objects in an end-to-end learning manner. Our approach outperforms previous stereo-based 3D detectors (about 10 higher in terms of AP) and even achieves comparable performance with several LiDAR-based methods on the KITTI 3D object detection leaderboard. Our code is publicly available at https://github.com/chenyilun95/DSGN.

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="2001.03398")

Code

Syntology Ran 1 of 5 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: official repository: 5 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

chenyilun95/DSGN officialmentioned in papermentioned 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

5 samples harvested; 1 ran; 0 honoured the contract we drafted; 4 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
4unverified

Licence: 0 of the 5 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 chenyilun95/DSGN. “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.

smooth_l1_loss chenyilun95/DSGN/dsgn/layers/smooth_l1_loss.py official repository ran MIT (permissive) · e261fa29066b37e5 · report
interpolate chenyilun95/DSGN/dsgn/layers/misc.py official repository unverified MIT (permissive) · 2902bf4410253ff7 · report
l1_loss chenyilun95/DSGN/dsgn/layers/smooth_l1_loss.py official repository unverified MIT (permissive) · 0c5a325edc5437d7 · report
l2_loss chenyilun95/DSGN/dsgn/layers/smooth_l1_loss.py official repository unverified MIT (permissive) · d6b3dd6ab8cd27d8 · report
sigmoid_focal_loss_cpu chenyilun95/DSGN/dsgn/layers/sigmoid_focal_loss.py official repository unverified MIT (permissive) · 426fd02a2beaf826 · report

Tasks

3D Object Detection3D Object Detection From Stereo ImagesObjectObject DetectionVehicle Pose Estimationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection From Stereo Images KITTI Cars Moderate DSGN AP75 52.18 #5 of 12 Archive leaderboard report
3D Object Detection From Stereo Images KITTI Cyclists Moderate DSGN AP50 18.17 #4 of 5 Archive leaderboard report
3D Object Detection From Stereo Images KITTI Pedestrians Moderate DSGN AP50 15.55 #6 of 6 Archive leaderboard report
Vehicle Pose Estimation KITTI Cars Hard DSGN (Stereo) Average Orientation Similarity 78.27 #5 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