Work

Evaluating the effect of image quantity on Gaussian Splatting: A statistical perspective

Year: 2025

Type: article

Abstract: 3D reconstruction techniques have gained a lot of popularity. With the advancements in NeRFs and Gaussian Splatting, there is an increasing need on properly capturing data to feed these algorithms and use them in real world scenarios.Most publicly available datasets that can be used for Gaussian Splatting are not suitable to do proper statistical analysis on reducing the number of cameras or the effect of uniformly placed cameras versus randomly placed cameras.The amount of cameras in the scene significantly affects the accuracy and resolution of the final 3D reconstruction.

Source: Computer Vision and Image Understanding

DOI: 10.1016/j.cviu.2025.104575

Authors: Anurag Dalal, Daniel Hagen, Kjell Gunnar Robbersmyr, Kristian Muri Knausgård

Institution: University of Agder

Language: English

Topic: 3D Shape Modeling and Analysis

Subfield: Computational Mechanics

Field: Engineering

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $2,090

Funder: Aust-Agder Utviklings- og Kompetansefond