Choreographing a World of Dynamic Objects
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| 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 |