Saved in:
Bibliographic Details
Main Authors: Xu, Tianxing, Wang, Zixuan, Wang, Guangyuan, Hu, Li, Zhang, Zhongyi, Zhang, Peng, Zhang, Bang, Zhang, Song-Hai
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.22960
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911471530672128
author Xu, Tianxing
Wang, Zixuan
Wang, Guangyuan
Hu, Li
Zhang, Zhongyi
Zhang, Peng
Zhang, Bang
Zhang, Song-Hai
author_facet Xu, Tianxing
Wang, Zixuan
Wang, Guangyuan
Hu, Li
Zhang, Zhongyi
Zhang, Peng
Zhang, Bang
Zhang, Song-Hai
contents World models based on video generation demonstrate remarkable potential for simulating interactive environments but face persistent difficulties in two key areas: maintaining long-term content consistency when scenes are revisited and enabling precise camera control from user-provided inputs. Existing methods based on explicit 3D reconstruction often compromise flexibility in unbounded scenarios and fine-grained structures. Alternative methods rely directly on previously generated frames without establishing explicit spatial correspondence, thereby constraining controllability and consistency. To address these limitations, we present UCM, a novel framework that unifies long-term memory and precise camera control via a time-aware positional encoding warping mechanism. To reduce computational overhead, we design an efficient dual-stream diffusion transformer for high-fidelity generation. Moreover, we introduce a scalable data curation strategy utilizing point-cloud-based rendering to simulate scene revisiting, facilitating training on over 500K monocular videos. Extensive experiments on real-world and synthetic benchmarks demonstrate that UCM significantly outperforms state-of-the-art methods in long-term scene consistency, while also achieving precise camera controllability in high-fidelity video generation.
format Preprint
id arxiv_https___arxiv_org_abs_2602_22960
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle UCM: Unifying Camera Control and Memory with Time-aware Positional Encoding Warping for World Models
Xu, Tianxing
Wang, Zixuan
Wang, Guangyuan
Hu, Li
Zhang, Zhongyi
Zhang, Peng
Zhang, Bang
Zhang, Song-Hai
Computer Vision and Pattern Recognition
World models based on video generation demonstrate remarkable potential for simulating interactive environments but face persistent difficulties in two key areas: maintaining long-term content consistency when scenes are revisited and enabling precise camera control from user-provided inputs. Existing methods based on explicit 3D reconstruction often compromise flexibility in unbounded scenarios and fine-grained structures. Alternative methods rely directly on previously generated frames without establishing explicit spatial correspondence, thereby constraining controllability and consistency. To address these limitations, we present UCM, a novel framework that unifies long-term memory and precise camera control via a time-aware positional encoding warping mechanism. To reduce computational overhead, we design an efficient dual-stream diffusion transformer for high-fidelity generation. Moreover, we introduce a scalable data curation strategy utilizing point-cloud-based rendering to simulate scene revisiting, facilitating training on over 500K monocular videos. Extensive experiments on real-world and synthetic benchmarks demonstrate that UCM significantly outperforms state-of-the-art methods in long-term scene consistency, while also achieving precise camera controllability in high-fidelity video generation.
title UCM: Unifying Camera Control and Memory with Time-aware Positional Encoding Warping for World Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.22960