Ordered Diffusion for 3D Human Registration

• URL: http://arxiv.org/abs/2608.05804v1
• Date: Thu, 06 Aug 2026 09:39:54 GMT
• Title: Ordered Diffusion for 3D Human Registration
• Abstract summary: 3D human registration has historically been treated as a regression task, assuming a unique ground-truth alignment exists between the template and an input point cloud.<n>We propose ODin, which formulates registration as a 3D diffusion process that generates a point cloud aligned with the target geometry.<n>To achieve this, ODin relies on global, local, and positional conditioning, guiding each point to its correct location.
• Score: 65.1333901549662
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 3D human registration has historically been treated as a regression task, assuming a unique ground-truth alignment exists between the template and an input point cloud. In reality, acquisition noise, occlusions, and unknown soft tissue dynamics introduce inherent ambiguity into human scans. Regression-based methods consequently converge to an average prediction, often failing to represent a plausible geometry. In our work, we embrace such uncertainty by modeling the registration as a distribution of alignments. We propose ODin, which formulates registration as a 3D diffusion process that generates a point cloud aligned with the target geometry while preserving template semantics through consistent point ordering. To achieve this, ODin relies on global, local, and positional conditioning, guiding each point to its correct location. Our experiments demonstrate that such a generative formulation not only outperforms its regression-based baseline, but also establishes a new state of the art, surpassing highly engineered methods while reducing the registration time by two-thirds. Pre-trained models and code are available at https://riccardomarin.github.io/odin/.

Related papers

• Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis [51.37795317716487]
  We propose the Adaptive Point-Prompt Tuning (APPT) method, which fine-tunes pre-trained models with a modest number of parameters.<n>We convert raw point clouds into point embeddings by aggregating local geometry to capture spatial features followed by linear layers.<n>To calibrate self-attention across source domains of any modality to 3D, we introduce a prompt generator that shares weights with the point embedding module.
  arXiv  Detail & Related papers  (2025-08-30T06:02:21Z)
• RecDreamer: Consistent Text-to-3D Generation via Uniform Score Distillation [35.85874404892182]
  Current text-to-3D generation methods often suffer from geometric inconsistencies, leading to repeated patterns across different poses of 3D assets.<n>We propose a solution called RecDreamer, which reshapes the underlying data distribution to achieve a more consistent pose representation.<n>Our experimental results demonstrate that RecDreamer effectively mitigates the Multi-Face Janus problem, leading to more consistent 3D asset generation across different poses.
  arXiv  Detail & Related papers  (2025-02-18T08:42:55Z)
• Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Models [19.795578581043745]
  Test-time adaptation of 3D point clouds is crucial for mitigating discrepancies between training and testing samples in real-world scenarios. We introduce a novel 3D test-time adaptation method, termed 3DD-TTA, which stands for 3D Denoising Diffusion Test-Time Adaptation.
  arXiv  Detail & Related papers  (2024-11-21T00:04:38Z)
• Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration [2.814748676983944]
  We propose a graph neural network model embedded with a local Spherical Euclidean 3D equivariance property through SE(3) message passing based propagation. Our model is composed mainly of a descriptor module, equivariant graph layers, match similarity, and the final regression layers. Experiments conducted on the 3DMatch and KITTI datasets exhibit the compelling and robust performance of our model compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-10-08T06:48:01Z)
• Diff-Reg v1: Diffusion Matching Model for Registration Problem [34.57825794576445]
  Existing methods commonly leverage geometric or semantic point features to generate potential correspondences. Previous methods, which rely on single-pass prediction, may struggle with local minima in complex scenarios. We introduce a diffusion matching model for robust correspondence estimation.
  arXiv  Detail & Related papers  (2024-03-29T02:10:38Z)
• NICP: Neural ICP for 3D Human Registration at Scale [35.631505786332454]
  We propose a neural scalable registration method, NSR, for 3D Human registration. NSR generalizes and scales across thousands of shapes and more than ten different data sources. Our essential contribution is NICP, an ICP-style self-supervised task tailored to neural fields.
  arXiv  Detail & Related papers  (2023-12-21T16:54:09Z)
• Adapting the Mean Teacher for keypoint-based lung registration under geometric domain shifts [75.51482952586773]
  deep neural networks generally require plenty of labeled training data and are vulnerable to domain shifts between training and test data. We present a novel approach to geometric domain adaptation for image registration, adapting a model from a labeled source to an unlabeled target domain. Our method consistently improves on the baseline model by 50%/47% while even matching the accuracy of models trained on target data.
  arXiv  Detail & Related papers  (2022-07-01T12:16:42Z)
• NeuralReshaper: Single-image Human-body Retouching with Deep Neural Networks [50.40798258968408]
  We present NeuralReshaper, a novel method for semantic reshaping of human bodies in single images using deep generative networks. Our approach follows a fit-then-reshape pipeline, which first fits a parametric 3D human model to a source human image. To deal with the lack-of-data problem that no paired data exist, we introduce a novel self-supervised strategy to train our network.
  arXiv  Detail & Related papers  (2022-03-20T09:02:13Z)
• Unsupervised 3D Human Mesh Recovery from Noisy Point Clouds [30.401088478228235]
  We present an unsupervised approach to reconstruct human shape and pose from noisy point cloud. Our network is trained from scratch with no need to warm-up the network with supervised data.
  arXiv  Detail & Related papers  (2021-07-15T18:07:47Z)
• LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration [123.62341095156611]
  LoopReg is an end-to-end learning framework to register a corpus of scans to a common 3D human model. A backward map, parameterized by a Neural Network, predicts the correspondence from every scan point to the surface of the human model. A forward map, parameterized by a human model, transforms the corresponding points back to the scan based on the model parameters (pose and shape)
  arXiv  Detail & Related papers  (2020-10-23T14:39:50Z)
• Learning Nonparametric Human Mesh Reconstruction from a Single Image without Ground Truth Meshes [56.27436157101251]
  We propose a novel approach to learn human mesh reconstruction without any ground truth meshes. This is made possible by introducing two new terms into the loss function of a graph convolutional neural network (Graph CNN)
  arXiv  Detail & Related papers  (2020-02-28T20:30:07Z)

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.