# Deep Confidence Guided Distance for 3D Partial Shape Registration

arXiv: https://arxiv.org/abs/2201.11379 · HTML: https://mlsanity.com/paper/2201.11379/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 41 references that are in the map.
- First posted on arXiv 27 Jan 2022.

## Builds on (most cited first, 21 of 21)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions](https://mlsanity.com/paper/1603.08182/) (2016)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [PREDATOR: Registration of 3D Point Clouds with Low Overlap](https://mlsanity.com/paper/2011.13005/) (2020)
- [PointNetLK: Robust & Efficient Point Cloud Registration using PointNet](https://mlsanity.com/paper/1903.05711/) (2019)
- [Deep Global Registration](https://mlsanity.com/paper/2004.11540/) (2020)
- [RPM-Net: Robust Point Matching using Learned Features](https://mlsanity.com/paper/2003.13479/) (2020)
- [Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration](https://mlsanity.com/paper/1605.03344/) (2016)
- [Adaptive Graph Convolutional Neural Networks](https://mlsanity.com/paper/1801.03226/) (2018)
- [PRNet: Self-Supervised Learning for Partial-to-Partial Registration](https://mlsanity.com/paper/1910.12240/) (2019)
- [Dual Geometric Graph Network (DG2N) -- Iterative network for deformable shape alignment](https://mlsanity.com/paper/2011.14723/) (2020)
- [Cyclic Functional Mapping: Self-supervised correspondence between non-isometric deformable shapes](https://mlsanity.com/paper/1912.01249/) (2019)
- [Extreme Relative Pose Network under Hybrid Representations](https://mlsanity.com/paper/1912.11695/) (2019)
- [Learning 3D-3D Correspondences for One-shot Partial-to-partial Registration](https://mlsanity.com/paper/2006.04523/) (2020)
- [Deep Weighted Consensus: Dense correspondence confidence maps for 3D shape registration](https://mlsanity.com/paper/2105.02714/) (2021)
- [Consistent Two-Flow Network for Tele-Registration of Point Clouds](https://mlsanity.com/paper/2106.00329/) (2021)
- [Unsupervised Scale-Invariant Multispectral Shape Matching](https://mlsanity.com/paper/2012.10685/) (2020)

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

- [Category-Level Global Camera Pose Estimation with Multi-Hypothesis Point Cloud Correspondences](https://mlsanity.com/paper/2209.14419/) (2022)
- [VioLA: Aligning Videos to 2D LiDAR Scans](https://mlsanity.com/paper/2311.04783/) (2023)

## Abstract (arXiv)

We present a novel non-iterative learnable method for partial-to-partial 3D shape registration. The partial alignment task is extremely complex, as it jointly tries to match between points and identify which points do not appear in the corresponding shape, causing the solution to be non-unique and ill-posed in most cases. Until now, two principal methodologies have been suggested to solve this problem: sample a subset of points that are likely to have correspondences or perform soft alignment between the point clouds and try to avoid a match to an occluded part. These heuristics work when the partiality is mild or when the transformation is small but fails for severe occlusions or when outliers are present. We present a unique approach named Confidence Guided Distance Network (CGD-net), where we fuse learnable similarity between point embeddings and spatial distance between point clouds, inducing an optimized solution for the overlapping points while ignoring parts that only appear in one of the shapes. The point feature generation is done by a self-supervised architecture that repels far points to have different embeddings, therefore succeeds to align partial views of shapes, even with excessive internal symmetries or acute rotations. We compare our network to recently presented learning-based and axiomatic methods and report a fundamental boost in performance.