BROWSE
Detail
Conference Paper
Per-Gaussian Embedding-Based Deformation for Deformable 3D Gaussian Splatting
Cited 32 time in 
Share 
Share
- Authors
- Jeongmin Bae, Seoha Kim, Youngsik Yun, Hahyun Lee, Gun Bang, Youngjung Uh
- Issue Date
- 2024-10
- Citation
- European Conference on Computer Vision (ECCV) 2024, pp.1-16
- Language
- English
- Type
- Conference Paper
- Abstract
- As 3D Gaussian Splatting (3DGS) provides fast and high-quality novel view synthesis, it is a natural extension to deform a canonical 3DGS to multiple frames for representing a dynamic scene. However, previous works fail to accurately reconstruct complex dynamic scenes. We attribute the failure to the design of the deformation field, which is built as a coordinate-based function. This approach is problematic because 3DGS is a mixture of multiple fields centered at the Gaussians, not just a single coordinate-based framework. To resolve this problem, we define the deformation as a function of per-Gaussian embeddings and temporal embeddings. Moreover, we decompose deformations as coarse and fine deformations to model slow and fast movements, respectively. Also, we introduce a local smoothness regularization for per-Gaussian embedding to improve the details in dynamic regions. Project page: https://jeongminb.github.io/e-d3dgs/.
- KSP Keywords
- Deformation field, High-quality, Multiple fields, Natural extension, Novel view synthesis, complex dynamics, dynamic scenes, local smoothness