# Seg2Box: 3D Object Detection by Point-Wise Semantics Supervision

arXiv: https://arxiv.org/abs/2503.16811 · HTML: https://mlsanity.com/paper/2503.16811/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 23 references that are in the map.
- First posted on arXiv 21 Mar 2025.

## Builds on (most cited first, 9 of 9)

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1503.01640/) (2015)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/2012.04355/) (2020)
- [Learning to Detect Mobile Objects from LiDAR Scans Without Labels](https://mlsanity.com/paper/2203.15882/) (2022)
- [Weakly Supervised 3D Object Detection from Point Clouds](https://mlsanity.com/paper/2007.13970/) (2020)
- [VILENS: Visual, Inertial, Lidar, and Leg Odometry for All-Terrain Legged Robots](https://mlsanity.com/paper/2107.07243/) (2021)
- [Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery](https://mlsanity.com/paper/2310.19080/) (2023)

## Built on by (most cited first, 2 of 2)

- [OWL: Unsupervised 3D Object Detection by Occupancy Guided Warm-up and Large Model Priors Reasoning](https://mlsanity.com/paper/2512.05698/) (2025)
- [PS-MOT: Cultivating Instance Awareness from Point Seeds for Multi-Object Tracking](https://mlsanity.com/paper/2606.30476/) (2026)

## Abstract (arXiv)

LiDAR-based 3D object detection and semantic segmentation are critical tasks in 3D scene understanding. Traditional detection and segmentation methods supervise their models through bounding box labels and semantic mask labels. However, these two independent labels inherently contain significant redundancy. This paper aims to eliminate the redundancy by supervising 3D object detection using only semantic labels. However, the challenge arises due to the incomplete geometry structure and boundary ambiguity of point-cloud instances, leading to inaccurate pseudo labels and poor detection results. To address these challenges, we propose a novel method, named Seg2Box. We first introduce a Multi-Frame Multi-Scale Clustering (MFMS-C) module, which leverages the spatio-temporal consistency of point clouds to generate accurate box-level pseudo-labels. Additionally, the Semantic?Guiding Iterative-Mining Self-Training (SGIM-ST) module is proposed to enhance the performance by progressively refining the pseudo-labels and mining the instances without generating pseudo-labels. Experiments on the Waymo Open Dataset and nuScenes Dataset show that our method significantly outperforms other competitive methods by 23.7% and 10.3% in mAP, respectively. The results demonstrate the great label-efficient potential and advancement of our method.