Methods › Computer Vision › RoI Feature Extractors › Voxel RoI Pooling
Voxel RoI Pooling
Introduced by Jiajun Deng et al. in Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Voxel RoI Pooling is a RoI feature extractor extracts RoI features directly from voxel features for further refinement. It starts by dividing a region proposal into G ×G ×G regular sub-voxels. The center point is taken as the grid point of the corresponding sub-voxel. Since 3 D feature volumes are extremely sparse (non-empty voxels account for <3 % spaces), we cannot directly utilize max pooling over features of each sub-voxel. Instead, features are integrated from neighboring voxels into the grid points for feature extraction. Specifically, given a grid point gᵢ, we first exploit voxel query to group a set of neighboring voxels Γᵢ=𝐯ᵢ¹, 𝐯ᵢ², ⋯, 𝐯ᵢᴷ . Then, we aggregate the neighboring voxel features with a PointNet module a as:
ηᵢ=max_(k=1,2, ⋯, K)Ψ([𝐯ᵢᵏ-𝐠ᵢ ; ϕᵢᵏ])
where 𝐯ᵢ-𝐠ᵢ represents the relative coordinates, ϕᵢᵏ is the voxel feature of 𝐯ᵢᵏ, and Ψ(·) indicates an MLP. The max pooling operation max(·) is performed along the channels to obtain the aggregated feature vector ηᵢ . Particularly, Voxel RoI pooling is exploited to extract voxel features from the 3D feature volumes out of the last two stages in the 3 D backbone network. And for each stage, two Manhattan distance thresholds are set to group voxels with multiple scales. Then, we concatenate the aggregated features pooled from different stages and scales to obtain the RoI features.
Papers archive 2025-07-28
5 shown of 5, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
VoxelNextFusion: A Simple, Unified and Effective Voxel Fusion Framework for Multi-Modal 3D Object Detection 5 Jan 2024 · 0 repositories · arXiv:2401.02702
-
Reviewing 3D Object Detectors in the Context of High-Resolution 3+1D Radar 10 Aug 2023 · 0 repositories · arXiv:2308.05478
-
Cost-Aware Evaluation and Model Scaling for LiDAR-Based 3D Object Detection 2 May 2022 · 0 repositories · arXiv:2205.01142
-
From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object Detection 30 Jul 2021 · 1 repository · arXiv:2107.14391
-
Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection 31 Dec 2020 · 5 repositories · arXiv:2012.15712
Tasks archive 2025-07-28
9 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| 3D Object Detection | 5 |
| Object Detection | 5 |
| object-detection | 5 |
| Object | 2 |
| Feature Importance | 1 |
| GPU | 1 |
| Region Proposal | 1 |
| Scene Understanding | 1 |
| Vocal Bursts Intensity Prediction | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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