paper-with-me

홈 › Papers

Not All Frame Features Are Equal: Video-to-4D Generation via Decoupling Dynamic-Static Features

2025-02-12 · Liying Yang, Chen Liu, Zhenwei Zhu, Ajian Liu, Hui Ma, Jian Nong, Yanyan Liang

Recently, the generation of dynamic 3D objects from a video has shown impressive results. Existing methods directly optimize Gaussians using whole information in frames. However, when dynamic regions are interwoven with static regions within frames, particularly if the static regions account for a large proportion, existing methods often overlook information in dynamic regions and are prone to overfitting on static regions. This leads to producing results with blurry textures. We consider that decoupling dynamic-static features to enhance dynamic representations can alleviate this issue. Thus, we propose a dynamic-static feature decoupling module (DSFD). Along temporal axes, it regards the portions of current frame features that possess significant differences relative to reference frame features as dynamic features. Conversely, the remaining parts are the static features. Then, we acquire decoupled features driven by dynamic features and current frame features. Moreover, to further enhance the dynamic representation of decoupled features from different viewpoints and ensure accurate motion prediction, we design a temporal-spatial similarity fusion module (TSSF). Along spatial axes, it adaptively selects a similar information of dynamic regions. Hinging on the above, we construct a novel approach, DS4D. Experimental results verify our method achieves state-of-the-art (SOTA) results in video-to-4D. In addition, the experiments on a real-world scenario dataset demonstrate its effectiveness on the 4D scene. Our code will be publicly available.

📄 PDF Abstract BibTeX arXiv:2502.08377

Code (0)

등록된 구현이 없습니다.

Tasks

Allmotion prediction

Similar Papers 제목 키워드 기반

Customizing Video Portraits via Identity-ActionDecoupling

2026-06-21 · Junxiong Lin, Haoran Wang, Xinji Mai, Zeng Tao 외 arxiv

Identity-Preserving Text-to-Video Generation (IPT2V) seeks to synthesize a temporally coherent video from a reference image and a textual description, while simultaneously preserving the subject's identity and allowing f…

Text-to-Video Generation

STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation

2025-06-16 · Jiamin Wang, Yichen Yao, Xiang Feng, Hang Wu 외

The generation of temporally consistent, high-fidelity driving videos over extended horizons presents a fundamental challenge in autonomous driving world modeling. Existing approaches often suffer from error accumulation…

Autonomous DrivingDenoisingVideo Generation

EcoVideo: Entropy-Orchestrated Video Generation Paradigm in Cloud-Edge Dynamics

2026-06-29 · Jiayu Chen, Hengyi Zhang, Maoliang Li, Minyu Li 외 arxiv

DiT video generation is latency-intensive due to iterative full-frame denoising, while prior cloud-edge methods largely rely on static inter-step decoupling and cannot leverage inter-frame similarity or adapt to system d…

Video Generation

Decoupling Degradations with Recurrent Network for Video Restoration in Under-Display Camera

2024-03-08 · Chengxu Liu, Xuan Wang, Yuanting Fan, Shuai Li 외

Under-display camera (UDC) systems are the foundation of full-screen display devices in which the lens mounts under the display. The pixel array of light-emitting diodes used for display diffracts and attenuates incident…

Image RestorationVideo Restoration

On the Content Bias in Fréchet Video Distance

2024-04-18 · Songwei Ge, Aniruddha Mahapatra, Gaurav Parmar, Jun-Yan Zhu 외

Fr\'echet Video Distance (FVD), a prominent metric for evaluating video generation models, is known to conflict with human perception occasionally. In this paper, we aim to explore the extent of FVD's bias toward per-fra…

Video Generation