Papers › LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector

LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector

18 Aug 2021ICCV 2021 10arXiv:2108.08258archive 2025-07-28

Xiaoyang Guo, Shaoshuai Shi, Xiaogang Wang, Hongsheng Li

Stereo-based 3D detection aims at detecting 3D object bounding boxes from stereo images using intermediate depth maps or implicit 3D geometry representations, which provides a low-cost solution for 3D perception. However, its performance is still inferior compared with LiDAR-based detection algorithms. To detect and localize accurate 3D bounding boxes, LiDAR-based models can encode accurate object boundaries and surface normal directions from LiDAR point clouds. However, the detection results of stereo-based detectors are easily affected by the erroneous depth features due to the limitation of stereo matching. To solve the problem, we propose LIGA-Stereo (LiDAR Geometry Aware Stereo Detector) to learn stereo-based 3D detectors under the guidance of high-level geometry-aware representations of LiDAR-based detection models. In addition, we found existing voxel-based stereo detectors failed to learn semantic features effectively from indirect 3D supervisions. We attach an auxiliary 2D detection head to provide direct 2D semantic supervisions. Experiment results show that the above two strategies improved the geometric and semantic representation capabilities. Compared with the state-of-the-art stereo detector, our method has improved the 3D detection performance of cars, pedestrians, cyclists by 10.44%, 5.69%, 5.97% mAP respectively on the official KITTI benchmark. The gap between stereo-based and LiDAR-based 3D detectors is further narrowed.

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="2108.08258")

Code

Syntology Ran 4 of 8 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 4 ran with no contract checked.

By repository: official repository: 8 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.

xy-guo/LIGA-Stereo officialpytorchApache-2.0 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

8 samples harvested; 4 ran; 0 honoured the contract we drafted; 4 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.

4ran
4unverified

Licence: 0 of the 8 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 xy-guo/LIGA-Stereo. “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.

convbn xy-guo/LIGA-Stereo/liga/models/backbones_3d_stereo/submodule.py official repository ran Apache-2.0 (permissive) · 576fc9a704db460c · report
convbn_3d xy-guo/LIGA-Stereo/liga/models/backbones_3d_stereo/submodule.py official repository ran Apache-2.0 (permissive) · 480bf7306505e398 · report
project_pseudo_lidar_to_rectcam xy-guo/LIGA-Stereo/liga/models/backbones_3d_stereo/liga_backbone.py official repository ran fingerprinted Apache-2.0 (permissive) · a5a2d3ad76c124dc · report
project_rectcam_to_pseudo_lidar xy-guo/LIGA-Stereo/liga/models/backbones_3d_stereo/liga_backbone.py official repository ran fingerprinted Apache-2.0 (permissive) · 370605cfbaea4721 · report
cfg_from_yaml_file xy-guo/LIGA-Stereo/liga/config.py official repository unverified Apache-2.0 (permissive) · 696fe155f9990d38 · report
get_corner_loss_lidar xy-guo/LIGA-Stereo/liga/utils/loss_utils.py official repository unverified Apache-2.0 (permissive) · 8a7cbf962b631fa2 · report
merge_new_config xy-guo/LIGA-Stereo/liga/config.py official repository unverified Apache-2.0 (permissive) · 392c0cf3a1b07b12 · report
project_rect_to_image xy-guo/LIGA-Stereo/liga/models/backbones_3d_stereo/liga_backbone.py official repository unverified Apache-2.0 (permissive) · ccdb34a9a05a58c5 · report

Tasks

3D Object Detection From Stereo Images3D geometryStereo Matching

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection From Stereo Images KITTI Cars Moderate LIGA-Stereo AP75 64.66 #2 of 12 Archive leaderboard report
3D Object Detection From Stereo Images KITTI Cyclists Moderate LIGA-Stereo AP50 36.86 #2 of 5 Archive leaderboard report
3D Object Detection From Stereo Images KITTI Pedestrians Moderate LIGA-Stereo AP50 30.00 #2 of 6 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.

Methods

AWARE

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