MrNeRF (@janusch_patas)
2026-01-27 | โค๏ธ 39 | ๐ 7 | ๐ฌ 1
LoD-Structured 3D Gaussian Splatting for Streaming Video Reconstruction
Contributions: โข We propose an Anchor- and Octree-based LoD-structured 3DGS representation, integrated with a hierarchical Gaussian dropout technique to stabilize training and ensure high-fidelity synthesis in Sparse-View SFVV.
โข We introduce a GMM-driven mechanism to decouple dynamic and static content, enabling targeted refinement of moving regions while maintaining the structural stability of the background.
โข We develop a quantized residual refinement framework that compresses dynamic updates, facilitating efficient data transmission and storage for low-bandwidth environments.
โข Extensive experiments demonstrate that StreamLoD-GS achieves competitive or state-of-the-art performance in terms of quality, efficiency, and storage footprints compared to contemporary SFVV approaches.
๋ฏธ๋์ด
๐ Related
- eag-pt-emission-aware-gaussians-and-path-tracing-for-indoorโ281012 โ ๊ฐ์ ์ ์ @janusch_patas
- gr3en-generative-relighting-for-3d-environments-057299 โ ๊ฐ์ ์ ์ @janusch_patas
- websplatter-enabling-cross-device-efficient-gaussian-splatti-262640 โ ๊ฐ์ ์ ์ @janusch_patas
- if-youve-ever-tried-to-create-3dgs-scenes-from-photos-taken-with-different-camer โ ์ฃผ์ : Gaussian Splatting, Nerf, Reconstruction
- ppisp-physically-plausible-compensation-and-control-of-photo โ ๋๋ฉ์ธ: Rendering