CoChat
Sign Up
Cited by 158Advanced Neural Network ApplicationsAutonomous Vehicle Technology and SafetyAdvanced Vision and Imaging

Geometry-based Distance Decomposition for Monocular 3D Object Detection

Open access
Shi, Xuepeng, Ye, Qi, Chen, Xiaozhi, Chen, Chuangrong, Chen, Zhixiang, Kim, Tae-Kyun·2021·2021 IEEE/CVF International Conference on Computer Vision (ICCV)
DOI 10.1109/iccv48922.2021.01489
Open this paper in CoChat — free accountOpen PDF

Abstract

Monocular 3D object detection is of great significance for autonomous driving but remains challenging. The core challenge is to predict the distance of objects in the absence of explicit depth information. Unlike regressing the distance as a single variable in most existing methods, we propose a novel geometry-based distance decomposition to recover the distance by its factors. The decomposition factors the distance of objects into the most representative and stable variables, i.e. the physical height and the projected visual height in the image plane. Moreover, the decomposition maintains the self-consistency between the two heights, leading to robust distance prediction when both predicted heights are inaccurate. The decomposition also enables us to trace the causes of the distance uncertainty for different scenarios. Such decomposition makes the distance prediction interpretable, accurate, and robust. Our method directly predicts 3D bounding boxes from RGB images with a compact architecture, making the training and inference simple and efficient. The experimental results show that our method achieves the state-of-the-art performance on the monocular 3D Object Detection and Bird’s Eye View tasks of the KITTI dataset, and can generalize to images with different camera intrinsics1.

Integrity signals

Registry

Crossref · 10.1109/iccv48922.2021.01489

Cites

50 of 50 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Traditional approaches that use only RGB images have perceptual limitations in complex real-world tasks, including occlusions, lighting changes, sparse textures, and insufficient semantic information.

    “Traditional unimodal approaches (such as relying solely on RGB images) often encounter perceptual limitations when dealing with complex tasks in real-world environments-such as occlusions, lighting variations, sparse textures, and insufficient semantic information [1,2,3].”

    From Multimodal fusion and vision–language models: A survey for robot vision (2026) · cites this paper as [2]

  • Camera-based single-modal 3D object detection infers 3D information from 2D images; RGB images provide rich visual data but lack direct depth perception, requiring complex estimation, making detection vulnerable to occlusions, poor angles, and adverse weather.

    “Camera-based single-modal 3D object detection [1, 72, 2, 3] infers 3D information from 2D images.While RGB images provide rich visual data, the lack of direct depth perception requires complex estimation techniques, making detection vulnerable to occlusions, poor angles, and adverse weather conditions.”

    From Multimodal fusion and vision–language models: A survey for robot vision (2026) · cites this paper as [2]

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
Shi, X., Ye, Q., Chen, X., Chen, C., Chen, Z., & Kim, T.-K.
Affiliations
  • Imperial College London (GB)
  • Zhejiang University (CN)
  • Deutsches Jugendinstitut (DE)
  • Korea Advanced Institute of Science and Technology (KR)
ORCID
Venue
2021 IEEE/CVF International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2021-10
Pages
15152-15161
DOI
10.1109/iccv48922.2021.01489
OpenAlex
W3148242781
Cited by
158
References
50
Citations by year
2026: 13 · 2025: 40 · 2024: 44 · 2023: 35 · 2022: 25 · 2021: 1
FWCI
8.59
Type
conference paper
Language
en
Open access
Licence
Locations
  • IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
Keywords
monocular 3D object detection, height, 3D bounding box regression, autonomous driving, bird's-eye view, distance uncertainty

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review