4 papers
Underwater360: Reconstructing Underwater Scenes from Panoramic Images with Omnidirectional Gaussian Splatting
Jiangbei Hu, Weichao Song, Shibo Yu +8
Underwater scene reconstruction is essential for immersive exploration of aquatic environments, yet remains challenging due to complex participating-media effects such as absorptio…
GSurf: Learning Signed Distance Fields from Splatting Opaque Gaussians for High-quality 3D Reconstruction
Baixin Xu, Jiangbei Hu, Jiaze Li +1
High-fidelity surface reconstruction from multi-view images is a core problem in 3D computer vision. While neural implicit surfaces like SDFs offer smooth geometry, they are often…
A Lightweight UDF Learning Framework for 3D Reconstruction Based on Local Shape Functions
Jiangbei Hu, Yanggeng Li, Fei Hou +5
Unsigned distance fields (UDFs) provide a versatile framework for representing a diverse array of 3D shapes, encompassing both watertight and non-watertight geometries. Traditional…
GS-Octree: Octree-based 3D Gaussian Splatting for Robust Object-level 3D Reconstruction Under Strong Lighting
Jiaze Li, Zhengyu Wen, Luo Zhang +4
The 3D Gaussian Splatting technique has significantly advanced the construction of radiance fields from multi-view images, enabling real-time rendering. While point-based rasteriza…