Saved in:
Bibliographic Details
Main Authors: Chen, Ruochen, Tran, Thuy, Parashar, Shaifali
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.05035
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909984914145280
author Chen, Ruochen
Tran, Thuy
Parashar, Shaifali
author_facet Chen, Ruochen
Tran, Thuy
Parashar, Shaifali
contents In this paper, we present a patch-based representation of surfaces, PolyFit, which is obtained by fitting jet functions locally on surface patches. Such a representation can be learned efficiently in a supervised fashion from both analytic functions and real data. Once learned, it can be generalized to various types of surfaces. Using PolyFit, the surfaces can be efficiently deformed by updating a compact set of jet coefficients rather than optimizing per-vertex degrees of freedom for many downstream tasks in computer vision and graphics. We demonstrate the capabilities of our proposed methodologies with two applications: 1) Shape-from-template (SfT): where the goal is to deform the input 3D template of an object as seen in image/video. Using PolyFit, we adopt test-time optimization that delivers competitive accuracy while being markedly faster than offline physics-based solvers, and outperforms recent physics-guided neural simulators in accuracy at modest additional runtime. 2) Garment draping. We train a self-supervised, mesh- and garment-agnostic model that generalizes across resolutions and garment types, delivering up to an order-of-magnitude faster inference than strong baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2601_05035
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Patch-based Representation and Learning for Efficient Deformation Modeling
Chen, Ruochen
Tran, Thuy
Parashar, Shaifali
Computer Vision and Pattern Recognition
In this paper, we present a patch-based representation of surfaces, PolyFit, which is obtained by fitting jet functions locally on surface patches. Such a representation can be learned efficiently in a supervised fashion from both analytic functions and real data. Once learned, it can be generalized to various types of surfaces. Using PolyFit, the surfaces can be efficiently deformed by updating a compact set of jet coefficients rather than optimizing per-vertex degrees of freedom for many downstream tasks in computer vision and graphics. We demonstrate the capabilities of our proposed methodologies with two applications: 1) Shape-from-template (SfT): where the goal is to deform the input 3D template of an object as seen in image/video. Using PolyFit, we adopt test-time optimization that delivers competitive accuracy while being markedly faster than offline physics-based solvers, and outperforms recent physics-guided neural simulators in accuracy at modest additional runtime. 2) Garment draping. We train a self-supervised, mesh- and garment-agnostic model that generalizes across resolutions and garment types, delivering up to an order-of-magnitude faster inference than strong baselines.
title Patch-based Representation and Learning for Efficient Deformation Modeling
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.05035