# ScanMove: Motion Prediction and Transfer for Unregistered Body Meshes

## TL;DR

This paper introduces a rig-free, data-driven framework for predicting and transferring motion on unregistered 3D body meshes, overcoming challenges posed by noise and lack of correspondences.

## Contribution

It presents a novel combination of a motion embedding network and a learned per-vertex feature field for deformation prediction on raw, unregistered meshes.

## Key findings

- Effective on challenging unregistered meshes
- Outperforms existing methods in benchmarks
- Versatile across different motion types

## Abstract

Unregistered surface meshes, especially raw 3D scans, present significant challenges for automatic computation of plausible deformations due to the lack of established point-wise correspondences and the presence of noise in the data. In this paper, we propose a new, rig-free, data-driven framework for motion prediction and transfer on such body meshes. Our method couples a robust motion embedding network with a learned per-vertex feature field to generate a spatio-temporal deformation field, which drives the mesh deformation. Extensive evaluations, including quantitative benchmarks and qualitative visuals on tasks such as walking and running, demonstrate the effectiveness and versatility of our approach on challenging unregistered meshes.