paper-with-me

Papers

SolidGS: Consolidating Gaussian Surfel Splatting for Sparse-View Surface Reconstruction

2024-12-19 · Zhuowen Shen, YuAn Liu, Zhang Chen, Zhong Li, Jiepeng Wang, Yongqing Liang, Zhengming Yu, Jingdong Zhang, Yi Xu, Scott Schaefer, Xin Li, Wenping Wang

Gaussian splatting has achieved impressive improvements for both novel-view synthesis and surface reconstruction from multi-view images. However, current methods still struggle to reconstruct high-quality surfaces from only sparse view input images using Gaussian splatting. In this paper, we propose a novel method called SolidGS to address this problem. We observed that the reconstructed geometry can be severely inconsistent across multi-views, due to the property of Gaussian function in geometry rendering. This motivates us to consolidate all Gaussians by adopting a more solid kernel function, which effectively improves the surface reconstruction quality. With the additional help of geometrical regularization and monocular normal estimation, our method achieves superior performance on the sparse view surface reconstruction than all the Gaussian splatting methods and neural field methods on the widely used DTU, Tanks-and-Temples, and LLFF datasets.

📄 PDF Abstract BibTeX arXiv:2412.15400

Code (0)

등록된 구현이 없습니다.

Tasks

Novel View SynthesisSurface Reconstruction

Similar Papers 제목 키워드 기반

SmileSplat: Generalizable Gaussian Splats for Unconstrained Sparse Images

2024-11-27 · Yanyan Li, Yixin Fang, Federico Tombari, Gim Hee Lee

Sparse Multi-view Images can be Learned to predict explicit radiance fields via Generalizable Gaussian Splatting approaches, which can achieve wider application prospects in real-life when ground-truth camera parameters …

DecoderNovel View Synthesis

SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction

2026-04-09 · Chensheng Dai, Shengjun Zhang, Min Chen, Yueqi Duan arxiv

3D Gaussian Splatting (3DGS) has demonstrated impressive performance in 3D scene reconstruction. Beyond novel view synthesis, it shows great potential for multi-view surface reconstruction. Existing methods employ optimi…

Novel View Synthesis

Point-Based 3D Reconstruction from Sparse Views under Known Illumination

2026-08-20 · Magnus Kaufmann Gjerde, Joakim Bruslund Haurum, Jeppe Revall Frisvad, Markus Worchel 외 arxiv

Sparse view 3D reconstruction is commonly addressed with neural implicit surfaces or dense point-based representations such as Gaussian splatting. Surface-aware splatting methods improve extracted geometry through orient…

3D Reconstruction

Nexels: Neurally-Textured Surfels for Real-Time Novel View Synthesis with Sparse Geometries

2025-12-15 · Victor Rong, Jan Held, Victor Chu, Daniel Rebain 외 arxiv

Though Gaussian splatting has achieved impressive results in novel view synthesis, it requires millions of primitives to model highly textured scenes, even when the geometry of the scene is simple. We propose a represent…

Novel View Synthesis

$S^3$LAM: Surfel Splatting SLAM for Geometrically Accurate Tracking and Mapping

2025-07-28 · Ruoyu Fan, Yuhui Wen, Jiajia Dai, Tao Zhang 외 arxiv

We propose $S^3$LAM, a novel RGB-D SLAM system that leverages 2D surfel splatting to achieve highly accurate geometric representations for simultaneous tracking and mapping. Unlike existing 3DGS-based SLAM approaches tha…

Computational Efficiency