EUVIMEDEUVIMED entdecken
Crossref

A Proposal-Based Transformer With Point-Voxel Cross Attention for Accurate 3D Object Detection

Guangyu Ji, Jun Lu, Chengtao Cai, Kaibin Qin

IEEE Signal Processing Letters · 2026 · 33 · 2320-2324

DOI: 10.1109/lsp.2026.3700522 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Guangyu Ji und 3 weiteren Autor:innen. Die Arbeit nennt 15 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing point-voxel hybrid two-stage 3D detectors mainly rely on point-based feature extraction in the second stage, while insufficiently exploiting the voxel features generated in the first stage. To address this limitation, we propose a novel two-stage 3D object detection framework that combines a voxel-based Region Proposal Network with a Proposal-Based Transformer using Point-Voxel Cross Attention (PVCAT). PVCAT integrates point and voxel features within the detection head, enhancing the detection performance of small objects while introducing only marginal computational overhead. The module consists of a Proposal Embedding Module, three Spatial-Aware Encoder layers, and three Channel-Aware Decoder layers in a three-layer encoder-decoder architecture. For each proposal, point-wise embeddings are first generated and then enhanced with voxel features from the RPN stage. In the encoder, Voxel features are leveraged as positional cues to model the local spatial context among points. In the decoder, a weighted fusion strategy strengthens query-key interactions by integrating global and local channel information from both point and voxel features. Experiments indicate that PVCAT is compatible with different voxel-based backbones and remains effective in improving detection performance, demonstrating its potential to enhance the accuracy of 3D object detectors.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Ji, G., Lu, J., Cai, C., & Qin, K. (2026). A Proposal-Based Transformer With Point-Voxel Cross Attention for Accurate 3D Object Detection. IEEE Signal Processing Letters, 33, 2320-2324. https://doi.org/10.1109/lsp.2026.3700522

Vancouver

Ji G, Lu J, Cai C, Qin K. A Proposal-Based Transformer With Point-Voxel Cross Attention for Accurate 3D Object Detection. IEEE Signal Processing Letters. 2026;33:2320-2324. doi:10.1109/lsp.2026.3700522

BibTeX
@article{Ji2026,
  author = {Ji, Guangyu and Lu, Jun and Cai, Chengtao and Qin, Kaibin},
  title = {A Proposal-Based Transformer With Point-Voxel Cross Attention for Accurate 3D Object Detection},
  journal = {IEEE Signal Processing Letters},
  year = {2026},
  volume = {33},
  pages = {2320--2324},
  doi = {10.1109/lsp.2026.3700522}
}
Kostenlos starten →