paper-with-me

홈 › Papers

Prior-Enhanced Gaussian Splatting for Dynamic Scene Reconstruction from Casual Video

2025-12-12 · Meng-Li Shih, Ying-Huan Chen, Yu-Lun Liu, Brian Curless arxiv

We introduce a fully automatic pipeline for dynamic scene reconstruction from casually captured monocular RGB videos. Rather than designing a new scene representation, we enhance the priors that drive Dynamic Gaussian Splatting. Video segmentation combined with epipolar-error maps yields object-level masks that closely follow thin structures; these masks (i) guide an object-depth loss that sharpens the consistent video depth, and (ii) support skeleton-based sampling plus mask-guided re-identification to produce reliable, comprehensive 2-D tracks. Two additional objectives embed the refined priors in the reconstruction stage: a virtual-view depth loss removes floaters, and a scaffold-projection loss ties motion nodes to the tracks, preserving fine geometry and coherent motion. The resulting system surpasses previous monocular dynamic scene reconstruction methods and delivers visibly superior renderings

📄 PDF Abstract BibTeX arXiv:2512.11356

Code (0)

등록된 구현이 없습니다.

Tasks

Video Segmentation

Similar Papers 제목 키워드 기반

VDEGaussian: Video Diffusion Enhanced 4D Gaussian Splatting for Dynamic Urban Scenes Modeling

2025-08-04 · Yuru Xiao, Zihan Lin, Chao Lu, Deming Zhai 외 arxiv

Dynamic urban scene modeling is a rapidly evolving area with broad applications. While current approaches leveraging neural radiance fields or Gaussian Splatting have achieved fine-grained reconstruction and high-fidelit…

Novel View Synthesis

PEGASUS: Physically Enhanced Gaussian Splatting Simulation System for 6DoF Object Pose Dataset Generation

2024-01-04 · Lukas Meyer, Floris Erich, Yusuke Yoshiyasu, Marc Stamminger 외

We introduce Physically Enhanced Gaussian Splatting Simulation System (PEGASUS) for 6DOF object pose dataset generation, a versatile dataset generator based on 3D Gaussian Splatting. Environment and object representation…

Dataset GenerationObjectPose Estimation

EVolSplat4D: Efficient Volume-based Gaussian Splatting for 4D Urban Scene Synthesis

2026-01-22 · Sheng Miao, Sijin Li, Pan Wang, Dongfeng Bai 외 arxiv

Novel view synthesis (NVS) of static and dynamic urban scenes is essential for autonomous driving simulation, yet existing methods often struggle to balance reconstruction time with quality. While state-of-the-art neural…

Novel View SynthesisAutonomous Driving

DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes

2023-12-13 · CVPR 2024 1 · Xiaoyu Zhou, Zhiwei Lin, Xiaojun Shan, Yongtao Wang 외

We present DrivingGaussian, an efficient and effective framework for surrounding dynamic autonomous driving scenes. For complex scenes with moving objects, we first sequentially and progressively model the static backgro…

Autonomous Driving

4D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenes

2024-02-05 · Yuanxing Duan, Fangyin Wei, Qiyu Dai, Yuhang He 외

We consider the problem of novel-view synthesis (NVS) for dynamic scenes. Recent neural approaches have accomplished exceptional NVS results for static 3D scenes, but extensions to 4D time-varying scenes remain non-trivi…

GPUNovel View Synthesis