Research map / Detection and segmentation / 3D detection and driving
Distribution Aware VoteNet for 3D Object Detection
Junxiong Liang, Pei An, Jie Ma
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Replace direct box regression with distribution-aware regression and JLQE | VoteNet · ScanNet V2 validation | mAP@0.5: 48.1 -> 50.2 | Improved |
| Add the SA encoder (ablation) | VoteNet · ScanNet V2 validation | mAP@0.25: 64.13 -> 65.55 | Improved |
| Add the SA encoder (ablation) | VoteNet · SUN RGB-D validation | mAP@0.25: 57.79 -> 58.77 | Improved |
| Add distribution regression after the SA encoder (ablation) | DAVNet · ScanNet V2 validation | mAP@0.25: 65.55 -> 66.49 | Improved |
| Use JLQE location scoring with distribution regression (ablation) | DAVNet · ScanNet V2 validation | mAP@0.25: 66.37 -> 67.11 | Improved |
| Add the standard deviation feature to the distribution encoder (ablation) | DAVNet · ScanNet V2 validation | mAP@0.25: 65.8 -> 66.2 | Improved |
| Use SIoU instead of Scenterness alone for location scoring (ablation) | VoteNet · ScanNet V2 validation | mAP@0.25: 64.13 -> 64.82 | Improved |
| Add aggregation features to SIoU-based location scoring (ablation) | VoteNet · ScanNet V2 validation | mAP@0.25: 64.82 -> 65.4 | Improved |
| Use distribution-aware regression with the full method | VoteNet · SUN RGB-D validation | mAP@0.25: 57.7 -> 60.3 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- H3DNet — H3DNet: 3D Object Detection Using Hybrid Geometric Primitives (ECCV 2020) · better on 3 of 4 shared results
- MLCVNet — MLCVNet: Multi-Level Context VoteNet for 3D Object Detection (CVPR 2020) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection (AAAI 2020 · similarity 0.87)
- Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection (CVPR 2021 · similarity 0.86)
- An End-to-End Transformer Model for 3D Object Detection (ICCV 2021 · similarity 0.86)
- 3D Bounding Box Estimation Using Deep Learning and Geometry (CVPR 2017 · similarity 0.86)
- GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation (IJCV 2023 · similarity 0.86)
- MsSVT++: Mixed-Scale Sparse Voxel Transformer With Center Voting for 3D Object Detection (TPAMI 2023 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
