Dream4D: Lifting Camera‐Controlled I2V towards Spatiotemporally Consistent 4D Generation

Abstract Generating spatiotemporally consistent 4D content requires joint modeling of high‐fidelity spatial details and realistic temporal dynamics. However, existing methods typically lack world knowledge learned from expansive 4D observations. As a result, generated scenes often struggle to maintain pose and temporal consistency in complex dynamic environments, leading to degraded generation quality. To address these challenges, we propose Dream4D , a novel 4D generation framework that integrates spatiotemporal priors from video generation with explicit sequential camera control. Our method adopts a three‐stage pipeline. We first employ a vision–language model (VLM) to determine the camera trajectory that best captures the intended view from the input image and the instruction text. Next, a pose‐conditioned diffusion model generates geometrically consistent image sequences along this trajectory. Finally, we use an advanced 4D generator to reconstruct a coherent and persistent 4D representation conditioned on the generated video. Dream4D jointly leverages the rich temporal priors of video diffusion models and the geometric awareness of reconstruction models to achieve high‐quality image‐to‐4D generation. Extensive experiments demonstrate that our approach significantly outperforms existing methods in both pose and temporal consistency.

Authors

Institutions

Publication Details

Journal
Computer Graphics Forum
Published
2026-11-14
DOI
https://doi.org/10.1111/cgf.70617
Citations
1
Primary Topic
Generative Adversarial Networks and Image Synthesis
Type
article
Field-Weighted Citation Impact
1.46
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Dream4D: Lifting Camera‐Controlled I2V towards Spatiotemporally Consistent 4D Generation

Kun-Fang Li, Xiaoyan Liu, Yuehao Song, Jiaxin Liu
1 citations
Computer Graphics Forum
Generative Adversarial Networks and Image Synthesis
1.46
article

Dream4D: Lifting Camera‐Controlled I2V towards Spatiotemporally Consistent 4D Generation

Kun-Fang Li, Xiaoyan Liu, Yuehao Song, Jiaxin Liu
article en
1 citations

Abstract

Abstract Generating spatiotemporally consistent 4D content requires joint modeling of high‐fidelity spatial details and realistic temporal dynamics. However, existing methods typically lack world knowledge learned from expansive 4D observations. As a result, generated scenes often struggle to maintain pose and temporal consistency in complex dynamic environments, leading to degraded generation quality. To address these challenges, we propose Dream4D , a novel 4D generation framework that integrates spatiotemporal priors from video generation with explicit sequential camera control. Our method adopts a three‐stage pipeline. We first employ a vision–language model (VLM) to determine the camera trajectory that best captures the intended view from the input image and the instruction text. Next, a pose‐conditioned diffusion model generates geometrically consistent image sequences along this trajectory. Finally, we use an advanced 4D generator to reconstruct a coherent and persistent 4D representation conditioned on the generated video. Dream4D jointly leverages the rich temporal priors of video diffusion models and the geometric awareness of reconstruction models to achieve high‐quality image‐to‐4D generation. Extensive experiments demonstrate that our approach significantly outperforms existing methods in both pose and temporal consistency.

Computer Graphics Forum
Hong Kong Polytechnic University (HK), Chinese University of Hong Kong (HK), UNSW Sydney (AU), Huazhong University of Science and Technology (CN)
Openalex Percentile: Top 22%
Generative Adversarial Networks and Image Synthesis
1.46
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon