# Point Virtual Transformer

arXiv: https://arxiv.org/abs/2602.06406 · HTML: https://mlsanity.com/paper/2602.06406/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 44 references that are in the map.
- First posted on arXiv 4 Feb 2026.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [PointPainting: Sequential Fusion for 3D Object Detection](https://mlsanity.com/paper/1911.10150/) (2019)
- [3DSSD: Point-based 3D Single Stage Object Detector](https://mlsanity.com/paper/2002.10187/) (2020)
- [Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud](https://mlsanity.com/paper/2003.01251/) (2020)
- [STD: Sparse-to-Dense 3D Object Detector for Point Cloud](https://mlsanity.com/paper/1907.10471/) (2019)
- [Voxel Transformer for 3D Object Detection](https://mlsanity.com/paper/2109.02497/) (2021)
- [PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection](https://mlsanity.com/paper/2102.00463/) (2021)
- [Rethinking and Improving Relative Position Encoding for Vision Transformer](https://mlsanity.com/paper/2107.14222/) (2021)
- [MVX-Net: Multimodal VoxelNet for 3D Object Detection](https://mlsanity.com/paper/1904.01649/) (2019)
- [CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection](https://mlsanity.com/paper/2009.00784/) (2020)
- [PENet: Towards Precise and Efficient Image Guided Depth Completion](https://mlsanity.com/paper/2103.00783/) (2021)
- [TANet: Robust 3D Object Detection from Point Clouds with Triple Attention](https://mlsanity.com/paper/1912.05163/) (2019)
- [Improving 3D Object Detection with Channel-wise Transformer](https://mlsanity.com/paper/2108.10723/) (2021)
- [SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation](https://mlsanity.com/paper/2108.06709/) (2021)
- [Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion](https://mlsanity.com/paper/2203.09780/) (2022)
- [Virtual Sparse Convolution for Multimodal 3D Object Detection](https://mlsanity.com/paper/2303.02314/) (2023)
- [Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection](https://mlsanity.com/paper/2109.02499/) (2021)
- [M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers](https://mlsanity.com/paper/2104.11896/) (2021)
- [Point Density-Aware Voxels for LiDAR 3D Object Detection](https://mlsanity.com/paper/2203.05662/) (2022)
- [Bilateral Propagation Network for Depth Completion](https://mlsanity.com/paper/2403.11270/) (2024)
- [SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection](https://mlsanity.com/paper/2201.01976/) (2022)
- [Transformation-Equivariant 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/2211.11962/) (2022)
- [VPFNet: Improving 3D Object Detection with Virtual Point based LiDAR and Stereo Data Fusion](https://mlsanity.com/paper/2111.14382/) (2021)
- [Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph](https://mlsanity.com/paper/2208.03624/) (2022)
- [A Unified Query-based Paradigm for Point Cloud Understanding](https://mlsanity.com/paper/2203.01252/) (2022)

## Abstract (arXiv)

LiDAR-based 3D object detectors often struggle to detect far-field objects due to the sparsity of point clouds at long ranges, which limits the availability of reliable geometric cues. To address this, prior approaches augment LiDAR data with depth-completed virtual points derived from RGB images; however, directly incorporating all virtual points leads to increased computational cost and introduces challenges in effectively fusing real and virtual information. We present Point Virtual Transformer (PointViT), a transformer-based 3D object detection framework that jointly reasons over raw LiDAR points and selectively sampled virtual points. The framework examines multiple fusion strategies, ranging from early point-level fusion to BEV-based gated fusion, and analyses their trade-offs in terms of accuracy and efficiency. The fused point cloud is voxelized and encoded using sparse convolutions to form a BEV representation, from which a compact set of high-confidence object queries is initialised and refined through a transformer-based context aggregation module. Experiments on the KITTI benchmark report 91.16% 3D AP, 95.94% BEV AP, and 99.36% AP on the KITTI 2D detection benchmark for the Car class.