# Faraway-Frustum: Dealing with Lidar Sparsity for 3D Object Detection using Fusion

arXiv: https://arxiv.org/abs/2011.01404 · HTML: https://mlsanity.com/paper/2011.01404/

## Key facts

- Cited by 15 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 3 Nov 2020.

## Built on by (most cited first, 15 of 15)

- [Multimodal Virtual Point 3D Detection](https://mlsanity.com/paper/2111.06881/) (2021)
- [Multi-modal Sensor Fusion for Auto Driving Perception: A Survey](https://mlsanity.com/paper/2202.02703/) (2022)
- [Multi-Modal 3D Object Detection in Autonomous Driving: a Survey](https://mlsanity.com/paper/2106.12735/) (2021)
- [GraphAlign: Enhancing Accurate Feature Alignment by Graph matching for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2310.08261/) (2023)
- [FrustumFormer: Adaptive Instance-aware Resampling for Multi-view 3D Detection](https://mlsanity.com/paper/2301.04467/) (2023)
- [Recent Advances in Multi-modal 3D Intelligence: A Comprehensive Survey and Evaluation](https://mlsanity.com/paper/2310.15676/) (2023)
- [LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object Detection](https://mlsanity.com/paper/2407.10164/) (2024)
- [Towards Long-Range 3D Object Detection for Autonomous Vehicles](https://mlsanity.com/paper/2310.04800/) (2023)
- [Survey and Systematization of 3D Object Detection Models and Methods](https://mlsanity.com/paper/2201.09354/) (2022)
- [VPFNet: Voxel-Pixel Fusion Network for Multi-class 3D Object Detection](https://mlsanity.com/paper/2111.00966/) (2021)
- [3D Harmonic Loss: Towards Task-consistent and Time-friendly 3D Object Detection on Edge for V2X Orchestration](https://mlsanity.com/paper/2211.03407/) (2022)
- [A Multimodal Hybrid Late-Cascade Fusion Network for Enhanced 3D Object Detection](https://mlsanity.com/paper/2504.18419/) (2025)
- [What You See Is What You Detect: Towards better Object Densification in 3D detection](https://mlsanity.com/paper/2310.17842/) (2023)
- [Boosting 3D Object Detection with Semantic-Aware Multi-Branch Framework](https://mlsanity.com/paper/2407.05769/) (2024)
- [LiDAR-Guided Monocular 3D Object Detection for Long-Range Railway Monitoring](https://mlsanity.com/paper/2504.18203/) (2025)

## Abstract (arXiv)

Learned pointcloud representations do not generalize well with an increase in distance to the sensor. For example, at a range greater than 60 meters, the sparsity of lidar pointclouds reaches to a point where even humans cannot discern object shapes from each other. However, this distance should not be considered very far for fast-moving vehicles: A vehicle can traverse 60 meters under two seconds while moving at 70 mph. For safe and robust driving automation, acute 3D object detection at these ranges is indispensable. Against this backdrop, we introduce faraway-frustum: a novel fusion strategy for detecting faraway objects. The main strategy is to depend solely on the 2D vision for recognizing object class, as object shape does not change drastically with an increase in depth, and use pointcloud data for object localization in the 3D space for faraway objects. For closer objects, we use learned pointcloud representations instead, following state-of-the-art. This strategy alleviates the main shortcoming of object detection with learned pointcloud representations. Experiments on the KITTI dataset demonstrate that our method outperforms state-of-the-art by a considerable margin for faraway object detection in bird's-eye-view and 3D. Our code is open-source and publicly available: https://github.com/dongfang-steven-yang/faraway-frustum.