# Detecting 3D Line Segments for 6DoF Pose Estimation with Limited Data

arXiv: https://arxiv.org/abs/2601.12090 · HTML: https://mlsanity.com/paper/2601.12090/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 32 references that are in the map.
- First posted on arXiv 17 Jan 2026.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/1901.02970/) (2019)
- [FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects](https://mlsanity.com/paper/2312.08344/) (2023)
- [Real-Time Seamless Single Shot 6D Object Pose Prediction](https://mlsanity.com/paper/1711.08848/) (2017)
- [EPOS: Estimating 6D Pose of Objects with Symmetries](https://mlsanity.com/paper/2004.00605/) (2020)
- [BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects](https://mlsanity.com/paper/2303.14158/) (2023)
- [Line Segment Detection Using Transformers without Edges](https://mlsanity.com/paper/2101.01909/) (2021)
- [DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients](https://mlsanity.com/paper/2212.07766/) (2022)
- [BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objects](https://mlsanity.com/paper/2403.09799/) (2024)
- [HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation](https://mlsanity.com/paper/2303.15743/) (2023)
- [ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformers](https://mlsanity.com/paper/2309.11986/) (2023)
- [3D Line Mapping Revisited](https://mlsanity.com/paper/2303.17504/) (2023)
- [Learning to Reconstruct 3D Manhattan Wireframes from a Single Image](https://mlsanity.com/paper/1905.07482/) (2019)
- [On Object Symmetries and 6D Pose Estimation from Images](https://mlsanity.com/paper/1908.07640/) (2019)
- [6D Object Pose Regression via Supervised Learning on Point Clouds](https://mlsanity.com/paper/2001.08942/) (2020)
- [PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds](https://mlsanity.com/paper/2103.02766/) (2021)
- [FSD: Fast Self-Supervised Single RGB-D to Categorical 3D Objects](https://mlsanity.com/paper/2310.12974/) (2023)
- [PLMP -- Point-Line Minimal Problems in Complete Multi-View Visibility](https://mlsanity.com/paper/1903.10008/) (2019)
- [Fast 3D Line Segment Detection From Unorganized Point Cloud](https://mlsanity.com/paper/1901.02532/) (2019)
- [Towards Deep Learning-based 6D Bin Pose Estimation in 3D Scans](https://mlsanity.com/paper/2112.09598/) (2021)

## Abstract (arXiv)

The task of 6DoF object pose estimation is one of the fundamental problems of 3D vision with many practical applications such as industrial automation. Traditional deep learning approaches for this task often require extensive training data or CAD models, limiting their application in real-world industrial settings where data is scarce and object instances vary. We propose a novel method for 6DoF pose estimation focused specifically on bins used in industrial settings. We exploit the cuboid geometry of bins by first detecting intermediate 3D line segments corresponding to their top edges. Our approach extends the 2D line segment detection network LeTR to operate on structured point cloud data. The detected 3D line segments are then processed using a simple geometric procedure to robustly determine the bin's 6DoF pose. To evaluate our method, we extend an existing dataset with a newly collected and annotated dataset, which we make publicly available. We show that incorporating synthetic training data significantly improves pose estimation accuracy on real scans. Moreover, we show that our method significantly outperforms current state-of-the-art 6DoF pose estimation methods in terms of the pose accuracy (3 cm translation error, 8.2^circ rotation error) while not requiring instance-specific CAD models during inference.