# DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization

arXiv: https://arxiv.org/abs/2007.09217 · HTML: https://mlsanity.com/paper/2007.09217/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2020.

## Built on by (most cited first, 30 of 42)

- [SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition](https://mlsanity.com/paper/2102.11603/) (2021)
- [MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition](https://mlsanity.com/paper/2104.05327/) (2021)
- [BEVPlace: Learning LiDAR-based Place Recognition using Bird's Eye View Images](https://mlsanity.com/paper/2302.14325/) (2023)
- [BVMatch: Lidar-based Place Recognition Using Bird's-eye View Images](https://mlsanity.com/paper/2109.00317/) (2021)
- [EgoNN: Egocentric Neural Network for Point Cloud Based 6DoF Relocalization at the City Scale](https://mlsanity.com/paper/2110.12486/) (2021)
- [Learning Sequential Descriptors for Sequence-based Visual Place Recognition](https://mlsanity.com/paper/2207.03868/) (2022)
- [SSC: Semantic Scan Context for Large-Scale Place Recognition](https://mlsanity.com/paper/2107.00382/) (2021)
- [Deep Multi-Task Learning for Joint Localization, Perception, and Prediction](https://mlsanity.com/paper/2101.06720/) (2021)
- [CASSPR: Cross Attention Single Scan Place Recognition](https://mlsanity.com/paper/2211.12542/) (2022)
- [Efficient 3D Point Cloud Feature Learning for Large-Scale Place Recognition](https://mlsanity.com/paper/2101.02374/) (2021)
- [Spectral Geometric Verification: Re-Ranking Point Cloud Retrieval for Metric Localization](https://mlsanity.com/paper/2210.04432/) (2022)
- [FD-SLAM: 3-D Reconstruction Using Features and Dense Matching](https://mlsanity.com/paper/2203.13861/) (2022)
- [I2P-Rec: Recognizing Images on Large-scale Point Cloud Maps through Bird's Eye View Projections](https://mlsanity.com/paper/2303.01043/) (2023)
- [Residual 3D Scene Flow Learning with Context-Aware Feature Extraction](https://mlsanity.com/paper/2109.04685/) (2021)
- [MinkLoc3D-SI: 3D LiDAR place recognition with sparse convolutions, spherical coordinates, and intensity](https://mlsanity.com/paper/2112.06539/) (2021)
- [HiTPR: Hierarchical Transformer for Place Recognition in Point Cloud](https://mlsanity.com/paper/2204.05481/) (2022)
- [CrossLoc3D: Aerial-Ground Cross-Source 3D Place Recognition](https://mlsanity.com/paper/2303.17778/) (2023)
- [CGiS-Net: Aggregating Colour, Geometry and Implicit Semantic Features for Indoor Place Recognition](https://mlsanity.com/paper/2202.02070/) (2022)
- [CMMLoc: Advancing Text-to-PointCloud Localization with Cauchy-Mixture-Model Based Framework](https://mlsanity.com/paper/2503.02593/) (2025)
- [Object-Augmented RGB-D SLAM for Wide-Disparity Relocalisation](https://mlsanity.com/paper/2108.02522/) (2021)
- [WSDesc: Weakly Supervised 3D Local Descriptor Learning for Point Cloud Registration](https://mlsanity.com/paper/2108.02740/) (2021)
- [SALSA: Swift Adaptive Lightweight Self-Attention for Enhanced LiDAR Place Recognition](https://mlsanity.com/paper/2407.08260/) (2024)
- [Attention Models for Point Clouds in Deep Learning: A Survey](https://mlsanity.com/paper/2102.10788/) (2021)
- [LinK3D: Linear Keypoints Representation for 3D LiDAR Point Cloud](https://mlsanity.com/paper/2206.05927/) (2022)
- [Learning to Register Unbalanced Point Pairs](https://mlsanity.com/paper/2207.04221/) (2022)
- [RING#: PR-by-PE Global Localization with Roto-translation Equivariant Gram Learning](https://mlsanity.com/paper/2409.00206/) (2024)
- [Large-Scale Topological Radar Localization Using Learned Descriptors](https://mlsanity.com/paper/2110.03081/) (2021)
- [Translation Invariant Global Estimation of Heading Angle Using Sinogram of LiDAR Point Cloud](https://mlsanity.com/paper/2203.00924/) (2022)
- [AEGIS-Net: Attention-guided Multi-Level Feature Aggregation for Indoor Place Recognition](https://mlsanity.com/paper/2312.09538/) (2023)
- [HOTFLoc++: End-to-End Hierarchical LiDAR Place Recognition, Re-Ranking, and 6-DoF Metric Localisation in Forests](https://mlsanity.com/paper/2511.09170/) (2025)

## Abstract (arXiv)

For relocalization in large-scale point clouds, we propose the first approach that unifies global place recognition and local 6DoF pose refinement. To this end, we design a Siamese network that jointly learns 3D local feature detection and description directly from raw 3D points. It integrates FlexConv and Squeeze-and-Excitation (SE) to assure that the learned local descriptor captures multi-level geometric information and channel-wise relations. For detecting 3D keypoints we predict the discriminativeness of the local descriptors in an unsupervised manner. We generate the global descriptor by directly aggregating the learned local descriptors with an effective attention mechanism. In this way, local and global 3D descriptors are inferred in one single forward pass. Experiments on various benchmarks demonstrate that our method achieves competitive results for both global point cloud retrieval and local point cloud registration in comparison to state-of-the-art approaches. To validate the generalizability and robustness of our 3D keypoints, we demonstrate that our method also performs favorably without fine-tuning on the registration of point clouds that were generated by a visual SLAM system. Code and related materials are available at https://vision.in.tum.de/research/vslam/dh3d.