Research map / Point clouds / Segmentation and detection
Single-stage point-voxel detection
Detect 3D objects directly from point clouds with proposal-based and hybrid voxel-point networks.
45 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Segmentation and detection, keyword cluster “detection · 3d object · detectors”
State History Benchmarks Tried Preprints Who Export
Where it stands
Quiet None of the tracked benchmarks has a report from 2025–26.
7 papers in 2023–24 and 4 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 7.0% to 4.4%.
No longer reported by papers here: nuScenes validation (NDS, last in 2024); nuScenes validation (mAP, 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 · Three-Dimensional Object Detection and Layout Prediction Using Clouds of Oriented Gradients (CVPR 2016 · 158 citations)
- 2018 · VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection (CVPR 2018 · 4,733 citations)
- 2019 · PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud (CVPR 2019 · 3,063 citations)
- 2020 · PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection (CVPR 2020 · 2,171 citations)
- 2021 · 3D Object Detection With Pointformer (CVPR 2021 · 460 citations)
- 2022 · Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection From Point Clouds (CVPR 2022 · 234 citations)
- 2023 · PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection (CVPR 2023 · 81 citations)
- 2024 · LION: Linear Group RNN for 3D Object Detection in Point Clouds (NeurIPS 2024 · 29 citations)
- 2025 · Geometry-Aware 3D Salient Object Detection Network (AAAI 2025 · 2 citations)
- 2026 · Real-time 3D Object Detection with Inference-Aligned Learning (AAAI 2026 · 2 citations)
Earliest papers here
- Three-Dimensional Object Detection and Layout Prediction Using Clouds of Oriented Gradients (CVPR 2016 · 158 citations)
- VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection (CVPR 2018 · 4,733 citations)
- Frustum PointNets for 3D Object Detection From RGB-D Data (CVPR 2018 · 2,820 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.
nuScenes validation · NDS (higher is better)
4 papers, 2022–2024 · not reported since 2024
| Year | Best so far | Set by |
|---|---|---|
| 2022 | 61 | SASA: Semantics-Augmented Set Abstraction for Point-Based 3D Object Detection (AAAI 2022 · 161 citations) |
| 2023 | 65 | PVT-SSD: Single-Stage 3D Object Detector With Point-Voxel Transformer (CVPR 2023 · 79 citations) |
| 2024 | 72.1 | LION: Linear Group RNN for 3D Object Detection in Point Clouds (NeurIPS 2024 · 29 citations) |
nuScenes validation · mAP (higher is better)
4 papers, 2022–2024 · not reported since 2024
| Year | Best so far | Set by |
|---|---|---|
| 2022 | 45 | SASA: Semantics-Augmented Set Abstraction for Point-Based 3D Object Detection (AAAI 2022 · 161 citations) |
| 2023 | 53.6 | PVT-SSD: Single-Stage 3D Object Detector With Point-Voxel Transformer (CVPR 2023 · 79 citations) |
| 2024 | 68 | LION: Linear Group RNN for 3D Object Detection in Point Clouds (NeurIPS 2024 · 29 citations) |
What has been tried
42 papers here report 483 measured changes (a component added, removed or swapped, compared with a baseline): helped 75%, no clear effect 6%, hurt 18%, mixed 1%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Add large group sizes | Waymo validation, 20% training data · mAPH L2 | 65.8 -> 66.9 | Helped | LION: Linear Group RNN for 3D Object Detection in Point Clouds (NeurIPS 2024 · 29 citations) |
| add superpoint partition (SP) | PCSOD test · MAE | 0.116 -> 0.050 | Helped | Geometry-Aware 3D Salient Object Detection Network (AAAI 2025 · 2 citations) |
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 11 papers; from OpenAlex and the papers' affiliations).
- The University of Hong Kong · 2 papers
- Tsinghua University · 2 papers
- Huazhong University of Science and Technology · 2 papers
Use it
Download BibTeX of 25 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
- LiDAR voxel and pillar detectors (56 papers)
- Multimodal and open-vocabulary 3D detection (24 papers)
Elsewhere in the topic
- Point cloud semantic segmentation (108 papers)
- LiDAR segmentation for driving (47 papers)
- Scene completion and instance segmentation (44 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).