Saved in:
Bibliographic Details
Main Authors: Chen, Hongyuan, Chen, Xingyu, Zhang, Youjia, Xu, Zexiang, Chen, Anpei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.14253
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915741546053632
author Chen, Hongyuan
Chen, Xingyu
Zhang, Youjia
Xu, Zexiang
Chen, Anpei
author_facet Chen, Hongyuan
Chen, Xingyu
Zhang, Youjia
Xu, Zexiang
Chen, Anpei
contents We present Motion 3-to-4, a feed-forward framework for synthesising high-quality 4D dynamic objects from a single monocular video and an optional 3D reference mesh. While recent advances have significantly improved 2D, video, and 3D content generation, 4D synthesis remains difficult due to limited training data and the inherent ambiguity of recovering geometry and motion from a monocular viewpoint. Motion 3-to-4 addresses these challenges by decomposing 4D synthesis into static 3D shape generation and motion reconstruction. Using a canonical reference mesh, our model learns a compact motion latent representation and predicts per-frame vertex trajectories to recover complete, temporally coherent geometry. A scalable frame-wise transformer further enables robustness to varying sequence lengths. Evaluations on both standard benchmarks and a new dataset with accurate ground-truth geometry show that Motion 3-to-4 delivers superior fidelity and spatial consistency compared to prior work. Project page is available at https://motion3-to-4.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2601_14253
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis
Chen, Hongyuan
Chen, Xingyu
Zhang, Youjia
Xu, Zexiang
Chen, Anpei
Computer Vision and Pattern Recognition
We present Motion 3-to-4, a feed-forward framework for synthesising high-quality 4D dynamic objects from a single monocular video and an optional 3D reference mesh. While recent advances have significantly improved 2D, video, and 3D content generation, 4D synthesis remains difficult due to limited training data and the inherent ambiguity of recovering geometry and motion from a monocular viewpoint. Motion 3-to-4 addresses these challenges by decomposing 4D synthesis into static 3D shape generation and motion reconstruction. Using a canonical reference mesh, our model learns a compact motion latent representation and predicts per-frame vertex trajectories to recover complete, temporally coherent geometry. A scalable frame-wise transformer further enables robustness to varying sequence lengths. Evaluations on both standard benchmarks and a new dataset with accurate ground-truth geometry show that Motion 3-to-4 delivers superior fidelity and spatial consistency compared to prior work. Project page is available at https://motion3-to-4.github.io/.
title Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.14253