Choreographing a World of Dynamic Objects

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lyu, Yanzhe, Geng, Chen, Dharmarajan, Karthik, Zhang, Yunzhi, Alzayer, Hadi, Wu, Shangzhe, Wu, Jiajun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917188574642176
author Lyu, Yanzhe
Geng, Chen
Dharmarajan, Karthik
Zhang, Yunzhi
Alzayer, Hadi
Wu, Shangzhe
Wu, Jiajun
author_facet Lyu, Yanzhe
Geng, Chen
Dharmarajan, Karthik
Zhang, Yunzhi
Alzayer, Hadi
Wu, Shangzhe
Wu, Jiajun
contents Dynamic objects in our physical 4D (3D + time) world are constantly evolving, deforming, and interacting with other objects, leading to diverse 4D scene dynamics. In this paper, we present a universal generative pipeline, CHORD, for CHOReographing Dynamic objects and scenes and synthesizing this type of phenomena. Traditional rule-based graphics pipelines to create these dynamics are based on category-specific heuristics, yet are labor-intensive and not scalable. Recent learning-based methods typically demand large-scale datasets, which may not cover all object categories in interest. Our approach instead inherits the universality from the video generative models by proposing a distillation-based pipeline to extract the rich Lagrangian motion information hidden in the Eulerian representations of 2D videos. Our method is universal, versatile, and category-agnostic. We demonstrate its effectiveness by conducting experiments to generate a diverse range of multi-body 4D dynamics, show its advantage compared to existing methods, and demonstrate its applicability in generating robotics manipulation policies. Project page: https://yanzhelyu.github.io/chord
format Preprint
id arxiv_https___arxiv_org_abs_2601_04194
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Choreographing a World of Dynamic Objects
Lyu, Yanzhe
Geng, Chen
Dharmarajan, Karthik
Zhang, Yunzhi
Alzayer, Hadi
Wu, Shangzhe
Wu, Jiajun
Computer Vision and Pattern Recognition
Graphics
Robotics
Dynamic objects in our physical 4D (3D + time) world are constantly evolving, deforming, and interacting with other objects, leading to diverse 4D scene dynamics. In this paper, we present a universal generative pipeline, CHORD, for CHOReographing Dynamic objects and scenes and synthesizing this type of phenomena. Traditional rule-based graphics pipelines to create these dynamics are based on category-specific heuristics, yet are labor-intensive and not scalable. Recent learning-based methods typically demand large-scale datasets, which may not cover all object categories in interest. Our approach instead inherits the universality from the video generative models by proposing a distillation-based pipeline to extract the rich Lagrangian motion information hidden in the Eulerian representations of 2D videos. Our method is universal, versatile, and category-agnostic. We demonstrate its effectiveness by conducting experiments to generate a diverse range of multi-body 4D dynamics, show its advantage compared to existing methods, and demonstrate its applicability in generating robotics manipulation policies. Project page: https://yanzhelyu.github.io/chord
title Choreographing a World of Dynamic Objects
topic Computer Vision and Pattern Recognition
Graphics
Robotics
url https://arxiv.org/abs/2601.04194