SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.09432 · ICCV · 2021

ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generators

U Austin, Qixing Huang, Xiangru Huang, Junfeng Jiang, Zaiwei Zhang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Without ARAPReg With ARAPReg Without ARAPReg Source Target Figure 1: Our approach learns a shape generator from a collection of deformable shapes. The shape generator is trained with a novel as-rigid-as-possible regularization (ARAPReg) loss that promotes the preservation of multi-scale shape features.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2108.09432")
get_code_for_paper("2108.09432")
have("2108.09432")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2108.09432.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2108.09432.svg)](https://syntology.ai/paper/2108.09432)

Connect an agent — have() is free.