Per-Gaussian Embedding-Based Deformation for Deformable 3D Gaussian Splatting
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/
Code (0)
등록된 구현이 없습니다.
Tasks
3DGSAttributeNovel View SynthesisSimilar Papers 제목 키워드 기반
3D Geometry-aware Deformable Gaussian Splatting for Dynamic View Synthesis
In this paper, we propose a 3D geometry-aware deformable Gaussian Splatting method for dynamic view synthesis. Existing neural radiance fields (NeRF) based solutions learn the deformation in an implicit manner, which can…
3D geometryDynamic ReconstructionNeRFADC-GS: Anchor-Driven Deformable and Compressed Gaussian Splatting for Dynamic Scene Reconstruction
Existing 4D Gaussian Splatting methods rely on per-Gaussian deformation from a canonical space to target frames, which overlooks redundancy among adjacent Gaussian primitives and results in suboptimal performance. To add…
Monocular Endoscopic Tissue 3D Reconstruction with Multi-Level Geometry Regularization
Reconstructing deformable endoscopic tissues is crucial for achieving robot-assisted surgery. However, 3D Gaussian Splatting-based approaches encounter challenges in achieving consistent tissue surface reconstruction, wh…
3D ReconstructionBridgeSplat: Bidirectionally Coupled CT and Non-Rigid Gaussian Splatting for Deformable Intraoperative Surgical Navigation
We introduce BridgeSplat, a novel approach for deformable surgical navigation that couples intraoperative 3D reconstruction with preoperative CT data to bridge the gap between surgical video and volumetric patient data. …
3D ReconstructionSpeedy Deformable 3D Gaussian Splatting: Fast Rendering and Compression of Dynamic Scenes
Recent extensions of 3D Gaussian Splatting (3DGS) to dynamic scenes achieve high-quality novel view synthesis by using neural networks to predict the time-varying deformation of each Gaussian. However, performing per-Gau…
3DGSNeRFNovel View Synthesis