ERNet: Efficient Non-Rigid Registration Network for Point Sequences

• URL: http://arxiv.org/abs/2510.15800v1
• Date: Fri, 17 Oct 2025 16:25:00 GMT
• Title: ERNet: Efficient Non-Rigid Registration Network for Point Sequences
• Abstract summary: We introduce a scalable data-driven approach to registering a sequence of point clouds undergoing non-rigid deformation.<n>It is designed to handle noisy and partial inputs while effectively leveraging consistent consistent registration.
• Score: 39.21668224811387
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• MATEY: multiscale adaptive foundation models for spatiotemporal physical systems [2.7767126393602726]
  We propose two adaptive tokenization schemes that dynamically adjust patch sizes based on local features.<n>We evaluate the performance of a proposed multiscale adaptive model, MATEY, in a sequence of experiments.<n>We also demonstrate fine-tuning tasks featuring different physics that models pretrained on PDE data.
  arXiv  Detail & Related papers  (2024-12-29T22:13:16Z)
• Towards Scalable and Deep Graph Neural Networks via Noise Masking [59.058558158296265]
  Graph Neural Networks (GNNs) have achieved remarkable success in many graph mining tasks.<n> scaling them to large graphs is challenging due to the high computational and storage costs.<n>We present random walk with noise masking (RMask), a plug-and-play module compatible with the existing model-simplification works.
  arXiv  Detail & Related papers  (2024-12-19T07:48:14Z)
• Efficient Grammatical Error Correction Via Multi-Task Training and Optimized Training Schedule [55.08778142798106]
  We propose auxiliary tasks that exploit the alignment between the original and corrected sentences. We formulate each task as a sequence-to-sequence problem and perform multi-task training. We find that the order of datasets used for training and even individual instances within a dataset may have important effects on the final performance.
  arXiv  Detail & Related papers  (2023-11-20T14:50:12Z)
• PREM: A Simple Yet Effective Approach for Node-Level Graph Anomaly Detection [65.24854366973794]
  Node-level graph anomaly detection (GAD) plays a critical role in identifying anomalous nodes from graph-structured data in domains such as medicine, social networks, and e-commerce. We introduce a simple method termed PREprocessing and Matching (PREM for short) to improve the efficiency of GAD. Our approach streamlines GAD, reducing time and memory consumption while maintaining powerful anomaly detection capabilities.
  arXiv  Detail & Related papers  (2023-10-18T02:59:57Z)
• Accelerating Scalable Graph Neural Network Inference with Node-Adaptive Propagation [80.227864832092]
  Graph neural networks (GNNs) have exhibited exceptional efficacy in a diverse array of applications. The sheer size of large-scale graphs presents a significant challenge to real-time inference with GNNs. We propose an online propagation framework and two novel node-adaptive propagation methods.
  arXiv  Detail & Related papers  (2023-10-17T05:03:00Z)
• CUTS: Neural Causal Discovery from Irregular Time-Series Data [27.06531262632836]
  Causal discovery from time-series data has been a central task in machine learning. We present CUTS, a neural Granger causal discovery algorithm to jointly impute unobserved data points and build causal graphs. Our approach constitutes a promising step towards applying causal discovery to real applications with non-ideal observations.
  arXiv  Detail & Related papers  (2023-02-15T04:16:34Z)
• Efficient Graph Neural Network Inference at Large Scale [54.89457550773165]
  Graph neural networks (GNNs) have demonstrated excellent performance in a wide range of applications. Existing scalable GNNs leverage linear propagation to preprocess the features and accelerate the training and inference procedure. We propose a novel adaptive propagation order approach that generates the personalized propagation order for each node based on its topological information.
  arXiv  Detail & Related papers  (2022-11-01T14:38:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.