# POD: Predictive Object Detection with Single-Frame FMCW LiDAR Point Cloud

arXiv: https://arxiv.org/abs/2504.05649 · HTML: https://mlsanity.com/paper/2504.05649/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 8 Apr 2025.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers](https://mlsanity.com/paper/2203.11496/) (2022)
- [Embracing Single Stride 3D Object Detector with Sparse Transformer](https://mlsanity.com/paper/2112.06375/) (2021)
- [DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets](https://mlsanity.com/paper/2301.06051/) (2023)
- [Fully Sparse 3D Object Detection](https://mlsanity.com/paper/2207.10035/) (2022)
- [Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving](https://mlsanity.com/paper/2210.08061/) (2022)
- [LION: Linear Group RNN for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/2407.18232/) (2024)
- [FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxels](https://mlsanity.com/paper/2308.03755/) (2023)
- [Super Sparse 3D Object Detection](https://mlsanity.com/paper/2301.02562/) (2023)
- [HeLiPR: Heterogeneous LiDAR Dataset for inter-LiDAR Place Recognition under Spatiotemporal Variations](https://mlsanity.com/paper/2309.14590/) (2023)
- [Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation](https://mlsanity.com/paper/2407.07995/) (2024)
- [DeTra: A Unified Model for Object Detection and Trajectory Forecasting](https://mlsanity.com/paper/2406.04426/) (2024)
- [DICP: Doppler Iterative Closest Point Algorithm](https://mlsanity.com/paper/2201.11944/) (2022)
- [Picking Up Speed: Continuous-Time Lidar-Only Odometry using Doppler Velocity Measurements](https://mlsanity.com/paper/2209.03304/) (2022)
- [Predict to Detect: Prediction-guided 3D Object Detection using Sequential Images](https://mlsanity.com/paper/2306.08528/) (2023)
- [Learning Moving-Object Tracking with FMCW LiDAR](https://mlsanity.com/paper/2203.00959/) (2022)
- [Need for Speed: Fast Correspondence-Free Lidar-Inertial Odometry Using Doppler Velocity](https://mlsanity.com/paper/2303.06511/) (2023)

## Built on by (most cited first, 1 of 1)

- [AevaScenes: An FMCW LiDAR Dataset and Benchmark for Long-Range Perception](https://mlsanity.com/paper/2609.33230/) (2026)

## Abstract (arXiv)

LiDAR-based 3D object detection is a fundamental task in the field of autonomous driving. This paper explores the unique advantage of Frequency Modulated Continuous Wave (FMCW) LiDAR in autonomous perception. Given a single frame FMCW point cloud with radial velocity measurements, we expect that our object detector can detect the short-term future locations of objects using only the current frame sensor data and demonstrate a fast ability to respond to intermediate danger. To achieve this, we extend the standard object detection task to a novel task named predictive object detection (POD), which aims to predict the short-term future location and dimensions of objects based solely on current observations. Typically, a motion prediction task requires historical sensor information to process the temporal contexts of each object, while our detector's avoidance of multi-frame historical information enables a much faster response time to potential dangers. The core advantage of FMCW LiDAR lies in the radial velocity associated with every reflected point. We propose a novel POD framework, the core idea of which is to generate a virtual future point using a ray casting mechanism, create virtual two-frame point clouds with the current and virtual future frames, and encode these two-frame voxel features with a sparse 4D encoder. Subsequently, the 4D voxel features are separated by temporal indices and remapped into two Bird's Eye View (BEV) features: one decoded for standard current frame object detection and the other for future predictive object detection. Extensive experiments on our in-house dataset demonstrate the state-of-the-art standard and predictive detection performance of the proposed POD framework.