Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.18371 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909713519607808 |
|---|---|
| author | Yin, DongFu Chen, Xiaotian Yu, Fei Richard Li, Xuanchen Zhang, Xinhao |
| author_facet | Yin, DongFu Chen, Xiaotian Yu, Fei Richard Li, Xuanchen Zhang, Xinhao |
| contents | Advances in generative modeling have significantly enhanced digital content creation, extending from 2D images to complex 3D and 4D scenes. Despite substantial progress, producing high-fidelity and temporally consistent dynamic 4D content remains a challenge. In this paper, we propose MVG4D, a novel framework that generates dynamic 4D content from a single still image by combining multi-view synthesis with 4D Gaussian Splatting (4D GS). At its core, MVG4D employs an image matrix module that synthesizes temporally coherent and spatially diverse multi-view images, providing rich supervisory signals for downstream 3D and 4D reconstruction. These multi-view images are used to optimize a 3D Gaussian point cloud, which is further extended into the temporal domain via a lightweight deformation network. Our method effectively enhances temporal consistency, geometric fidelity, and visual realism, addressing key challenges in motion discontinuity and background degradation that affect prior 4D GS-based methods. Extensive experiments on the Objaverse dataset demonstrate that MVG4D outperforms state-of-the-art baselines in CLIP-I, PSNR, FVD, and time efficiency. Notably, it reduces flickering artifacts and sharpens structural details across views and time, enabling more immersive AR/VR experiences. MVG4D sets a new direction for efficient and controllable 4D generation from minimal inputs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_18371 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MVG4D: Image Matrix-Based Multi-View and Motion Generation for 4D Content Creation from a Single Image Yin, DongFu Chen, Xiaotian Yu, Fei Richard Li, Xuanchen Zhang, Xinhao Computer Vision and Pattern Recognition Advances in generative modeling have significantly enhanced digital content creation, extending from 2D images to complex 3D and 4D scenes. Despite substantial progress, producing high-fidelity and temporally consistent dynamic 4D content remains a challenge. In this paper, we propose MVG4D, a novel framework that generates dynamic 4D content from a single still image by combining multi-view synthesis with 4D Gaussian Splatting (4D GS). At its core, MVG4D employs an image matrix module that synthesizes temporally coherent and spatially diverse multi-view images, providing rich supervisory signals for downstream 3D and 4D reconstruction. These multi-view images are used to optimize a 3D Gaussian point cloud, which is further extended into the temporal domain via a lightweight deformation network. Our method effectively enhances temporal consistency, geometric fidelity, and visual realism, addressing key challenges in motion discontinuity and background degradation that affect prior 4D GS-based methods. Extensive experiments on the Objaverse dataset demonstrate that MVG4D outperforms state-of-the-art baselines in CLIP-I, PSNR, FVD, and time efficiency. Notably, it reduces flickering artifacts and sharpens structural details across views and time, enabling more immersive AR/VR experiences. MVG4D sets a new direction for efficient and controllable 4D generation from minimal inputs. |
| title | MVG4D: Image Matrix-Based Multi-View and Motion Generation for 4D Content Creation from a Single Image |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.18371 |