Research map / Detection and segmentation / 3D detection and driving
Monocular 3D object detection
Improve single-image 3D detection with auxiliary contexts, distillation, and depth-aware losses.
56 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in 3D detection and driving, keyword cluster “3d object · monocular · kitti”
State History Benchmarks Tried Baselines Checklist Preprints Who Export
Where it stands
Quiet None of the tracked benchmarks has a report from 2025–26.
13 papers in 2023–24 and 11 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 8.2% to 7.2%.
No longer reported by papers here: KITTI test, Car moderate (AP3D, last in 2024).
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2016 · Monocular 3D Object Detection for Autonomous Driving (CVPR 2016 · 1,095 citations)
- 2018 · Multi-Level Fusion Based 3D Object Detection From Monocular Images (CVPR 2018 · 402 citations)
- 2019 · Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction (CVPR 2019 · 336 citations)
- 2020 · MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships (CVPR 2020 · 321 citations)
- 2021 · Categorical Depth Distribution Network for Monocular 3D Object Detection (CVPR 2021 · 563 citations)
- 2022 · MonoDTR: Monocular 3D Object Detection With Depth-Aware Transformer (CVPR 2022 · 226 citations)
- 2023 · RADIANT: Radar-Image Association Network for 3D Object Detection (AAAI 2023 · 46 citations)
- 2024 · MonoCD: Monocular 3D Object Detection with Complementary Depths (CVPR 2024 · 73 citations)
- 2025 · MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · 25 citations)
- 2026 · MonoCLUE: Object-Aware Clustering Enhances Monocular 3D Object Detection (AAAI 2026 · 4 citations)
Earliest papers here
- Monocular 3D Object Detection for Autonomous Driving (CVPR 2016 · 1,095 citations)
- Multi-Level Fusion Based 3D Object Detection From Monocular Images (CVPR 2018 · 402 citations)
- 3D Box Proposals From a Single Monocular Image of an Indoor Scene (AAAI 2018 · 5 citations)
Benchmark records
The best number each year that beat every earlier one, among papers of this approach reporting their own method. Numbers are extracted by AI from each paper's text; check the paper before citing.
KITTI test, Car moderate · AP3D (higher is better)
4 papers, 2019–2024 · not reported since 2024
| Year | Best so far | Set by |
|---|---|---|
| 2019 | 10.85 | Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction (CVPR 2019 · 336 citations) |
| 2022 | 17.74 | Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving (CVPR 2022 · 94 citations) |
What has been tried
45 papers here report 497 measured changes (a component added, removed or swapped, compared with a baseline): helped 78%, no clear effect 4%, hurt 16%, mixed 2%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| predict y from global rather than local clues | KITTI val Car · AP3D Moderate | 13.49 -> 17.85 | Helped | MonoCD: Monocular 3D Object Detection with Complementary Depths (CVPR 2024 · 73 citations) |
| add occupancy learning in frustum space | KITTI val Car · AP3D (IoU=0.7) Moderate | 17.05 -> 17.79 | Helped | Learning Occupancy for Monocular 3D Object Detection (CVPR 2024 · 31 citations) |
| add decoupled query | KITTI val, Car Moderate · AP3D | 21.48 -> 22.34 | Helped | MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · 25 citations) |
| add the proposal head | Omni3D unified detection · AP3D | 12.3% -> 15.9% | Helped | UniMODE: Unified Monocular 3D Object Detection (CVPR 2024 · 22 citations) |
| Use cross-attention instead of direct concatenation-plus-MLP association | KITTI validation, Car · AP3D@IoU=0.7 moderate | 57.32 -> 57.45 | Helped | FD3D: Exploiting Foreground Depth Map for Feature-Supervised Monocular 3D Object Detection (AAAI 2024 · 17 citations) |
| Replace the naive raw pseudo-LiDAR and tight-box pipeline with the proposed pseudo-LiDAR and box refinement | KITTI · AP | 7.3 -> 18.5 | Helped | Training an Open-Vocabulary Monocular 3D Detection Model without 3D Data (NeurIPS 2024 · 11 citations) |
| Add the Completion Network to NOQG + DAM | KITTI 3D val, Moderate · AP3D | 15.71 -> 20.90 | Helped | MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders (NeurIPS 2024 · 10 citations) |
| Add Dice loss to BEV segmentation | KITTI-360 Val · AP3D50 APLrg (%) | 4.86 -> 8.71 | Helped | SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects (CVPR 2024 · 9 citations) |
| add intrinsic parameter unification | nuScenes→KITTI · AP40 3D, Moderate | 5.27 -> 16.94 | Helped | Geometry-Guided Domain Generalization for Monocular 3D Object Detection (AAAI 2024 · 7 citations) |
Baseline numbers that disagree
The same baseline on the same benchmark and metric, reported more than 5% apart by different papers here. Training budgets, data splits and reimplementations differ, so state which number you compare with.
| Baseline | Benchmark | Metric | Reported | Papers |
|---|---|---|---|---|
| MonoDETR | KITTI test, car | AP3D Hard | 12.99 – 13.95 | 3 papers, e.g. CVPR 2023 and CVPR 2024 |
| MonoDETR | KITTI test, car | AP3D Easy | 23.65 – 25 | 3 papers, e.g. CVPR 2023 and CVPR 2024 |
What reviewers will expect
Datasets and baselines named in the 11 papers of this approach from 2024–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- KITTI · 7 of 11 papers
- nuScenes · 7 of 11 papers
- Omni3D · 2 of 11 papers
- SUN-RGBD · 2 of 11 papers
- ARKitScenes · 2 of 11 papers
Baselines
- GUPNet · 5 of 11 papers
- MonoDTR · 4 of 11 papers
- Cube R-CNN · 4 of 11 papers
- MonoDETR · 4 of 11 papers
- MonoDLE · 3 of 11 papers
- MonoJSG · 3 of 11 papers
- CaDDN · 3 of 11 papers
- DID-M3D · 3 of 11 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 24 papers; from OpenAlex and the papers' affiliations).
- Huazhong University of Science and Technology · 2 papers
- ZongmuTech · 2 papers
- Fudan University · 2 papers
- Michigan State University · 2 papers
- Tsinghua University · 2 papers
Use it
Download BibTeX of 39 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Unified LiDAR 3D detection (107 papers)
- Depth-based and label-free 3D detection (58 papers)
- 3D objectness and scene segmentation (57 papers)
Elsewhere in the topic
- LiDAR perception for driving (75 papers)
- Multi-camera BEV detection (69 papers)
- Camera-radar fusion detection (36 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).