# The Impact of 2D Segmentation Backbones on Point Cloud Predictions Using 4D Radar

arXiv: https://arxiv.org/abs/2509.19644 · HTML: https://mlsanity.com/paper/2509.19644/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 23 Sep 2025.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention](https://mlsanity.com/paper/2004.01389/) (2020)
- [Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis](https://mlsanity.com/paper/2203.03311/) (2022)
- [RAMP-CNN: A Novel Neural Network for Enhanced Automotive Radar Object Recognition](https://mlsanity.com/paper/2011.08981/) (2020)
- [4D Millimeter-Wave Radar in Autonomous Driving: A Survey](https://mlsanity.com/paper/2306.04242/) (2023)
- [Deep Radar Detector](https://mlsanity.com/paper/1906.12187/) (2019)
- [Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches](https://mlsanity.com/paper/2206.08016/) (2022)
- [A Deep Automotive Radar Detector using the RaDelft Dataset](https://mlsanity.com/paper/2406.04723/) (2024)
- [R2P: A Deep Learning Model from mmWave Radar to Point Cloud](https://mlsanity.com/paper/2207.10690/) (2022)
- [See Further Than CFAR: a Data-Driven Radar Detector Trained by Lidar](https://mlsanity.com/paper/2402.12970/) (2024)
- [Sequential Point Clouds: A Survey](https://mlsanity.com/paper/2204.09337/) (2022)
- [Resilient Sensor Architecture Design and Tradespace Analysis for Autonomous Vehicle Localization and Mapping](https://mlsanity.com/paper/1907.08541/) (2019)
- [Semantic-Supervised Spatial-Temporal Fusion for LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2503.10579/) (2025)

## Abstract (arXiv)

LiDAR's dense, sharp point cloud (PC) representations of the surrounding environment enable accurate perception and significantly improve road safety by offering greater scene awareness and understanding. However, LiDAR's high cost continues to restrict the broad adoption of high-level Autonomous Driving (AD) systems in commercially available vehicles. Prior research has shown progress towards circumventing the need for LiDAR by training a neural network, using LiDAR point clouds as ground truth (GT), to produce LiDAR-like 3D point clouds using only 4D Radars. One of the best examples is a neural network created to train a more efficient radar target detector with a modular 2D convolutional neural network (CNN) backbone and a temporal coherence network at its core that uses the RaDelft dataset for training (see arXiv:2406.04723). In this work, we investigate the impact of higher-capacity segmentation backbones on the quality of the produced point clouds. Our results show that while very high-capacity models may actually hurt performance, an optimal segmentation backbone can provide a 23.7% improvement over the state-of-the-art (SOTA).