#gaussian splatting
17 papers · 1 filter
MonoVoc: Decoupling Geometry and Semantics for Lightweight Monocular Open-Vocabulary 3D Gaussians
Pouya Ardekhani, Zahra Dehghanian, Morteza Abolghasemi +1
The paper introduces a training‑free pipeline that separates 3D geometry reconstruction from semantic labeling to create compact, object‑level semantic maps from a single monocular…
S-Avatar: Diffusion-Guided Gaussian Head Avatars from a Single Image
Hail Song, Seokhwan Yang, Jiwon Yang +2
S-Avatar is a method that creates photorealistic 3D head avatars from a single image by using diffusion-guided Gaussian splatting and aligning the result with the FLAME parametric…
Split and Drive: Dual-Axis Disentanglement for Real-Time Gaussian Head Avatars
MD Wahiduzzaman Khan, Mingshan Jia, Xiaolin Zhang +2
The paper introduces SpiD, a framework that creates photorealistic, animatable head avatars from a single image using a dual-axis disentanglement of Gaussian representations, enabl…
3DGBGS: 3D Granular Ball Gaussian Splatting for Compact Novel View Synthesis
Meng Yang, Shuyin Xia, Dawei Dai +1
The paper presents 3DGBGS, a compact anchor-based framework for novel-view synthesis that adaptively partitions SfM point clouds into granular balls to reduce the number of anchors…
SplatStream: Fine Granular Scalable Gaussian Splatting for Adaptive 3D Scene Streaming
Muhammad Talha, William Gordon, Sajid Umair +3
The paper introduces SplatStream, a framework that breaks down dynamic 3D Gaussian splatting scenes into quality and resolution layers and uses predictive coding and transformer-ba…
GSR: Geometric Methods for Fast and Memory-Efficient Gaussian-based Surface Reconstruction
Dasong Gao, Vivienne Sze, Sertac Karaman
The paper introduces G²SR, a method that detects 2D Gaussian splats in a few RGB images, then analytically triangulates them into metric‑scale 3D splats for fast, memory‑efficient…