Unifying Voxel-based Representation with Transformer for 3D Object Detection

By Yanwei Li, Yilun Chen, Xiaojuan Qi, Zeming Li, Jian‐Yuan Sun, Jiaya Jia. Neural Information Processing Systems, 2022

391 citations recorded by the source corpus.

In this work, we present a unified framework for multi-modality 3D object detection, named UVTR. The proposed method aims to unify multi-modality representations in the voxel space for accurate and robust single- or cross-modality 3D detection. To this end, the modality-specific space is first designed to represent different inputs in the voxel feature space. Different from previous work, our approach preserves the voxel space without height compression to alleviate semantic ambiguity and enable spatial connections. To make full use of the inputs from different sensors, the cross-modality interaction is then proposed, including knowledge transfer and modality fusion. In this way, geometry-aware expressions in point clouds and context-rich features in images are well utilized for better performance and robustness. The transformer decoder is applied to efficiently sample features from the unified space with learnable positions, which facilitates object-level interactions. In general, UVTR presents an early attempt to represent different modalities in a unified framework. It surpasses previous work in single- or multi-modality entries. The proposed method achieves leading performance in the nuScenes test set for both object detection and the following object tracking task. Code is made publicly available at https://github.com/dvlab-research/UVTR.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/20114810f64a7ca05b3b9acbc873a74d9de9c13a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Xiaojuan Qi
2. Jiwen Lu
3. Jiaya Jia
4. Yunpeng Zhang
5. Yukang Chen
6. Xiangyu Zhang
7. Jianhui Liu
8. Jie Zhou

In Computer Vision and Pattern Recognition

1. Jie Zhou
2. Jiwen Lu
3. Luc Van Gool
4. Jiaya Jia
5. Dacheng Tao
6. Ming-Hsuan Yang
7. Chen Change Loy
8. Yi Yang

Citations in the corpus

• VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking (2023, methodology): “Results denoted as † [13,28,40] are reported with the double-flip testing augmentation [57].”
• Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction (2023, background): “Despite the success of voxel-based representations in LiDAR-centric surrounding perception, only a few works have explored voxel-based representations for vision-centric autonomous driving [5,26].”