Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Rendering
- URL: http://arxiv.org/abs/2311.18561v2
- Date: Wed, 20 Mar 2024 16:27:53 GMT
- Title: Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Rendering
- Authors: Yurui Chen, Chun Gu, Junzhe Jiang, Xiatian Zhu, Li Zhang,
- Abstract summary: We present a unified representation model, called Periodic Vibration Gaussian (PVG)
PVG builds upon the efficient 3D Gaussian splatting technique, originally designed for static scene representation.
PVG exhibits 900-fold acceleration in rendering over the best alternative.
- Score: 36.111845416439095
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Modeling dynamic, large-scale urban scenes is challenging due to their highly intricate geometric structures and unconstrained dynamics in both space and time. Prior methods often employ high-level architectural priors, separating static and dynamic elements, resulting in suboptimal capture of their synergistic interactions. To address this challenge, we present a unified representation model, called Periodic Vibration Gaussian (PVG). PVG builds upon the efficient 3D Gaussian splatting technique, originally designed for static scene representation, by introducing periodic vibration-based temporal dynamics. This innovation enables PVG to elegantly and uniformly represent the characteristics of various objects and elements in dynamic urban scenes. To enhance temporally coherent and large scene representation learning with sparse training data, we introduce a novel temporal smoothing mechanism and a position-aware adaptive control strategy respectively. Extensive experiments on Waymo Open Dataset and KITTI benchmarks demonstrate that PVG surpasses state-of-the-art alternatives in both reconstruction and novel view synthesis for both dynamic and static scenes. Notably, PVG achieves this without relying on manually labeled object bounding boxes or expensive optical flow estimation. Moreover, PVG exhibits 900-fold acceleration in rendering over the best alternative.
Related papers
- Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos [101.48581851337703]
We present BTimer, the first motion-aware feed-forward model for real-time reconstruction and novel view synthesis of dynamic scenes.
Our approach reconstructs the full scene in a 3D Gaussian Splatting representation at a given target ('bullet') timestamp by aggregating information from all the context frames.
Given a casual monocular dynamic video, BTimer reconstructs a bullet-time scene within 150ms while reaching state-of-the-art performance on both static and dynamic scene datasets.
arXiv Detail & Related papers (2024-12-04T18:15:06Z) - Urban4D: Semantic-Guided 4D Gaussian Splatting for Urban Scene Reconstruction [86.4386398262018]
Urban4D is a semantic-guided decomposition strategy inspired by advances in deep 2D semantic map generation.
Our approach distinguishes potentially dynamic objects through reliable semantic Gaussians.
Experiments on real-world datasets demonstrate that Urban4D achieves comparable or better quality than previous state-of-the-art methods.
arXiv Detail & Related papers (2024-12-04T16:59:49Z) - DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes [71.61083731844282]
We present DeSiRe-GS, a self-supervised gaussian splatting representation.
It enables effective static-dynamic decomposition and high-fidelity surface reconstruction in complex driving scenarios.
arXiv Detail & Related papers (2024-11-18T05:49:16Z) - Adaptive and Temporally Consistent Gaussian Surfels for Multi-view Dynamic Reconstruction [3.9363268745580426]
AT-GS is a novel method for reconstructing high-quality dynamic surfaces from multi-view videos through per-frame incremental optimization.
We reduce temporal jittering in dynamic surfaces by ensuring consistency in curvature maps across consecutive frames.
Our method achieves superior accuracy and temporal coherence in dynamic surface reconstruction, delivering high-fidelity space-time novel view synthesis.
arXiv Detail & Related papers (2024-11-10T21:30:16Z) - DENSER: 3D Gaussians Splatting for Scene Reconstruction of Dynamic Urban Environments [0.0]
We propose DENSER, a framework that significantly enhances the representation of dynamic objects.
The proposed approach significantly outperforms state-of-the-art methods by a wide margin.
arXiv Detail & Related papers (2024-09-16T07:11:58Z) - Gaussian Splatting LK [0.11249583407496218]
This paper investigates the potential of regularizing the native warp field within the dynamic Gaussian Splatting framework.
We show that we can exploit knowledge innate to the forward warp field network to derive an analytical velocity field.
This derived Lucas-Kanade style analytical regularization enables our method to achieve superior performance in reconstructing highly dynamic scenes.
arXiv Detail & Related papers (2024-07-16T01:50:43Z) - Dynamic 3D Gaussian Fields for Urban Areas [60.64840836584623]
We present an efficient neural 3D scene representation for novel-view synthesis (NVS) in large-scale, dynamic urban areas.
We propose 4DGF, a neural scene representation that scales to large-scale dynamic urban areas.
arXiv Detail & Related papers (2024-06-05T12:07:39Z) - Motion-aware 3D Gaussian Splatting for Efficient Dynamic Scene Reconstruction [89.53963284958037]
We propose a novel motion-aware enhancement framework for dynamic scene reconstruction.
Specifically, we first establish a correspondence between 3D Gaussian movements and pixel-level flow.
For the prevalent deformation-based paradigm that presents a harder optimization problem, a transient-aware deformation auxiliary module is proposed.
arXiv Detail & Related papers (2024-03-18T03:46:26Z) - RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenes [3.1224202646855903]
We present RoDUS, a pipeline for decomposing static and dynamic elements in urban scenes.
Our approach utilizes a robust kernel-based initialization coupled with 4D semantic information to selectively guide the learning process.
Notably, experimental evaluations on KITTI-360 and Pandaset datasets demonstrate the effectiveness of our method in decomposing challenging urban scenes into precise static and dynamic components.
arXiv Detail & Related papers (2024-03-14T14:08:59Z) - EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via
Self-Supervision [85.17951804790515]
EmerNeRF is a simple yet powerful approach for learning spatial-temporal representations of dynamic driving scenes.
It simultaneously captures scene geometry, appearance, motion, and semantics via self-bootstrapping.
Our method achieves state-of-the-art performance in sensor simulation.
arXiv Detail & Related papers (2023-11-03T17:59:55Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.