# ERNet: Efficient Non-Rigid Registration Network for Point Sequences

arXiv: https://arxiv.org/abs/2510.15800 · HTML: https://mlsanity.com/paper/2510.15800/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 17 Oct 2025.

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

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes](https://mlsanity.com/paper/2011.13084/) (2020)
- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement](https://mlsanity.com/paper/2306.08637/) (2023)
- [TAP-Vid: A Benchmark for Tracking Any Point in a Video](https://mlsanity.com/paper/2211.03726/) (2022)
- [FlowNet3D: Learning Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/1806.01411/) (2018)
- [SpatialTracker: Tracking Any 2D Pixels in 3D Space](https://mlsanity.com/paper/2404.04319/) (2024)
- [4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface](https://mlsanity.com/paper/2105.01905/) (2021)
- [Lepard: Learning partial point cloud matching in rigid and deformable scenes](https://mlsanity.com/paper/2111.12591/) (2021)
- [GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer](https://mlsanity.com/paper/2308.03768/) (2023)
- [Neural Deformation Graphs for Globally-consistent Non-rigid Reconstruction](https://mlsanity.com/paper/2012.01451/) (2020)
- [CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphism](https://mlsanity.com/paper/2203.16529/) (2022)
- [KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control](https://mlsanity.com/paper/2104.11224/) (2021)
- [Non-rigid Point Cloud Registration with Neural Deformation Pyramid](https://mlsanity.com/paper/2205.12796/) (2022)
- [Fast Neural Scene Flow](https://mlsanity.com/paper/2304.09121/) (2023)
- [ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generators](https://mlsanity.com/paper/2108.09432/) (2021)
- [Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstruction](https://mlsanity.com/paper/2103.16341/) (2021)
- [Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking](https://mlsanity.com/paper/2401.06614/) (2024)
- [Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registration](https://mlsanity.com/paper/2303.09950/) (2023)
- [Non-Rigid Point Set Registration Networks](https://mlsanity.com/paper/1904.01428/) (2019)

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

- [BridgeMatch: Conditional Transport Bridges in Matching Matrix Space for 3D Deformable Registration](https://mlsanity.com/paper/2609.11472/) (2026)

## Abstract (arXiv)

Registering an object shape to a sequence of point clouds undergoing non-rigid deformation is a long-standing challenge. The key difficulties stem from two factors: (i) the presence of local minima due to the non-convexity of registration objectives, especially under noisy or partial inputs, which hinders accurate and robust deformation estimation, and (ii) error accumulation over long sequences, leading to tracking failures. To address these challenges, we introduce to adopt a scalable data-driven approach and propose ERNet, an efficient feed-forward model trained on large deformation datasets. It is designed to handle noisy and partial inputs while effectively leveraging temporal information for accurate and consistent sequential registration. The key to our design is predicting a sequence of deformation graphs through a two-stage pipeline, which first estimates frame-wise coarse graph nodes for robust initialization, before refining their trajectories over time in a sliding-window fashion. Extensive experiments show that our proposed approach (i) outperforms previous state-of-the-art on both the DeformingThings4D and D-FAUST datasets, and (ii) achieves more than 4x speedup compared to the previous best, offering significant efficiency improvement.