# Semantic-Supervised Spatial-Temporal Fusion for LiDAR-based 3D Object Detection

arXiv: https://arxiv.org/abs/2503.10579 · HTML: https://mlsanity.com/paper/2503.10579/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 46 references that are in the map.
- First posted on arXiv 13 Mar 2025.

## Builds on (most cited first, 30 of 38)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [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)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers](https://mlsanity.com/paper/2203.11496/) (2022)
- [STD: Sparse-to-Dense 3D Object Detector for Point Cloud](https://mlsanity.com/paper/1907.10471/) (2019)
- [VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking](https://mlsanity.com/paper/2303.11301/) (2023)
- [Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion](https://mlsanity.com/paper/2211.10581/) (2022)
- [Offboard 3D Object Detection from Point Cloud Sequences](https://mlsanity.com/paper/2103.05073/) (2021)
- [Pillar-based Object Detection for Autonomous Driving](https://mlsanity.com/paper/2007.10323/) (2020)
- [Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds](https://mlsanity.com/paper/2203.11139/) (2022)
- [Fast Point R-CNN](https://mlsanity.com/paper/1908.02990/) (2019)
- [RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection](https://mlsanity.com/paper/2106.13365/) (2021)
- [Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection](https://mlsanity.com/paper/2005.09927/) (2020)
- [MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection](https://mlsanity.com/paper/2205.05979/) (2022)
- [4D-Net for Learned Multi-Modal Alignment](https://mlsanity.com/paper/2109.01066/) (2021)
- [Towards Efficient 3D Object Detection with Knowledge Distillation](https://mlsanity.com/paper/2205.15156/) (2022)
- [LinK: Linear Kernel for LiDAR-based 3D Perception](https://mlsanity.com/paper/2303.16094/) (2023)
- [MGTANet: Encoding Sequential LiDAR Points Using Long Short-Term Motion-Guided Temporal Attention for 3D Object Detection](https://mlsanity.com/paper/2212.00442/) (2022)

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

- [The Impact of 2D Segmentation Backbones on Point Cloud Predictions Using 4D Radar](https://mlsanity.com/paper/2509.19644/) (2025)

## Abstract (arXiv)

LiDAR-based 3D object detection presents significant challenges due to the inherent sparsity of LiDAR points. A common solution involves long-term temporal LiDAR data to densify the inputs. However, efficiently leveraging spatial-temporal information remains an open problem. In this paper, we propose a novel Semantic-Supervised Spatial-Temporal Fusion (ST-Fusion) method, which introduces a novel fusion module to relieve the spatial misalignment caused by the object motion over time and a feature-level semantic supervision to sufficiently unlock the capacity of the proposed fusion module. Specifically, the ST-Fusion consists of a Spatial Aggregation (SA) module and a Temporal Merging (TM) module. The SA module employs a convolutional layer with progressively expanding receptive fields to aggregate the object features from the local regions to alleviate the spatial misalignment, the TM module dynamically extracts object features from the preceding frames based on the attention mechanism for a comprehensive sequential presentation. Besides, in the semantic supervision, we propose a Semantic Injection method to enrich the sparse LiDAR data via injecting the point-wise semantic labels, using it for training a teacher model and providing a reconstruction target at the feature level supervised by the proposed object-aware loss. Extensive experiments on various LiDAR-based detectors demonstrate the effectiveness and universality of our proposal, yielding an improvement of approximately +2.8% in NDS based on the nuScenes benchmark.