Space-time 2D Gaussian Splatting for Accurate Surface Reconstruction under Complex Dynamic Scenes
- URL: http://arxiv.org/abs/2409.18852v1
- Date: Fri, 27 Sep 2024 15:50:36 GMT
- Title: Space-time 2D Gaussian Splatting for Accurate Surface Reconstruction under Complex Dynamic Scenes
- Authors: Shuo Wang, Binbin Huang, Ruoyu Wang, Shenghua Gao,
- Abstract summary: We present a space-time 2D Gaussian Splatting approach to tackle the dynamic contents and the occlusions in complex scenes.
Specifically, to improve geometric quality in dynamic scenes, we learn canonical 2D Gaussian splats and deform these 2D Gaussian splats.
We also introduce a compositional opacity strategy, which further reduces the surface recovery of those occluded areas.
Experiments on real-world sparse-view video datasets and monocular dynamic datasets demonstrate that our reconstructions outperform state-of-the-art methods.
- Score: 30.32214593068206
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Previous surface reconstruction methods either suffer from low geometric accuracy or lengthy training times when dealing with real-world complex dynamic scenes involving multi-person activities, and human-object interactions. To tackle the dynamic contents and the occlusions in complex scenes, we present a space-time 2D Gaussian Splatting approach. Specifically, to improve geometric quality in dynamic scenes, we learn canonical 2D Gaussian splats and deform these 2D Gaussian splats while enforcing the disks of the Gaussian located on the surface of the objects by introducing depth and normal regularizers. Further, to tackle the occlusion issues in complex scenes, we introduce a compositional opacity deformation strategy, which further reduces the surface recovery of those occluded areas. Experiments on real-world sparse-view video datasets and monocular dynamic datasets demonstrate that our reconstructions outperform state-of-the-art methods, especially for the surface of the details. The project page and more visualizations can be found at: https://tb2-sy.github.io/st-2dgs/.
Related papers
- GSTAR: Gaussian Surface Tracking and Reconstruction [9.017056233547084]
GSTAR is a novel method that achieves photo-realistic rendering, accurate surface reconstruction, and reliable 3D tracking for general dynamic scenes with changing topology.
In regions where topology changes, GSTAR adaptively unbinds Gaussians from the mesh, enabling accurate registration and the generation of new surfaces.
Our method effectively tracks and reconstructs dynamic surfaces, enabling a range of applications.
arXiv Detail & Related papers (2025-01-17T16:26:24Z) - CoSurfGS:Collaborative 3D Surface Gaussian Splatting with Distributed Learning for Large Scene Reconstruction [68.81212850946318]
We propose a multi-agent collaborative fast 3DGS surface reconstruction framework based on distributed learning for large-scale surface reconstruction.
Specifically, we develop local model compression (LMC) and model aggregation schemes (MAS) to achieve high-quality surface representation of large scenes.
Our proposed method can achieve fast and scalable high-fidelity surface reconstruction and photorealistic rendering.
arXiv Detail & Related papers (2024-12-23T14:31:15Z) - DGNS: Deformable Gaussian Splatting and Dynamic Neural Surface for Monocular Dynamic 3D Reconstruction [17.2650972298677]
This paper tackles the dual challenges of dynamic novel-view synthesis and 3D reconstruction.
We introduce a hybrid framework: Deformable Gaussian splatting and Dynamic Neural Surfaces.
arXiv Detail & Related papers (2024-12-05T06:28:08Z) - 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) - 2DGS-Room: Seed-Guided 2D Gaussian Splatting with Geometric Constrains for High-Fidelity Indoor Scene Reconstruction [3.8879997968084137]
We introduce 2DGS-Room, a novel method leveraging 2D Gaussian Splatting for high-fidelity indoor scene reconstruction.
We employ a seed-guided mechanism to control the distribution of 2D Gaussians, with the density of seed points dynamically optimized through adaptive growth and pruning mechanisms.
To further improve geometric accuracy, we incorporate monocular depth and normal priors to provide constraints for details and textureless regions respectively.
arXiv Detail & Related papers (2024-12-04T16:17:47Z) - 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) - DynaSurfGS: Dynamic Surface Reconstruction with Planar-based Gaussian Splatting [13.762831851385227]
We propose DynaSurfGS to achieve both photorealistic rendering and high-fidelity surface reconstruction of dynamic scenarios.
The framework first incorporates Gaussian features from 4D neural voxels with the planar-based Gaussian Splatting to facilitate precise surface reconstruction.
It also incorporates the as-rigid-as-possible (ARAP) constraint to maintain the approximate rigidity of local neighborhoods of 3D Gaussians between timesteps.
arXiv Detail & Related papers (2024-08-26T01:36:46Z) - SMORE: Simulataneous Map and Object REconstruction [66.66729715211642]
We present a method for dynamic surface reconstruction of large-scale urban scenes from LiDAR.
We take a holistic perspective and optimize a compositional model of a dynamic scene that decomposes the world into rigidly-moving objects and the background.
arXiv Detail & Related papers (2024-06-19T23:53:31Z) - 2D Gaussian Splatting for Geometrically Accurate Radiance Fields [50.056790168812114]
3D Gaussian Splatting (3DGS) has recently revolutionized radiance field reconstruction, achieving high quality novel view synthesis and fast rendering speed without baking.
We present 2D Gaussian Splatting (2DGS), a novel approach to model and reconstruct geometrically accurate radiance fields from multi-view images.
We demonstrate that our differentiable terms allows for noise-free and detailed geometry reconstruction while maintaining competitive appearance quality, fast training speed, and real-time rendering.
arXiv Detail & Related papers (2024-03-26T17:21:24Z) - Deep Active Surface Models [60.027353171412216]
Active Surface Models have a long history of being useful to model complex 3D surfaces but only Active Contours have been used in conjunction with deep networks.
We introduce layers that implement them that can be integrated seamlessly into Graph Convolutional Networks to enforce sophisticated smoothness priors.
arXiv Detail & Related papers (2020-11-17T18:48:28Z)
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.