Coverage Optimization for Camera View Selection

TL;DR

This paper introduces COVER, a coverage-based view selection metric that improves 3D scene reconstruction by selecting informative camera viewpoints, integrated into Nerfstudio, and validated on real datasets.

Contribution

The paper proposes a simple, interpretable criterion for active view selection based on Fisher Information Gain approximation, enhancing 3D reconstruction quality.

Findings

COVER outperforms existing view selection methods across multiple datasets.

The method is robust to noise and training dynamics.

Integration into Nerfstudio enables practical application and evaluation.

Abstract

What makes a good viewpoint? The quality of the data used to learn 3D reconstructions is crucial for enabling efficient and accurate scene modeling. We study the active view selection problem and develop a principled analysis that yields a simple and interpretable criterion for selecting informative camera poses. Our key insight is that informative views can be obtained by minimizing a tractable approximation of the Fisher Information Gain, which reduces to favoring viewpoints that cover geometry that has been insufficiently observed by past cameras. This leads to a lightweight coverage-based view selection metric that avoids expensive transmittance estimation and is robust to noise and training dynamics. We call this metric COVER (Camera Optimization for View Exploration and Reconstruction). We integrate our method into the Nerfstudio framework and evaluate it on real datasets within fixed and embodied data acquisition scenarios. Across multiple datasets and radiance-field baselines, our method consistently improves reconstruction quality compared to state-of-the-art active view selection methods. Additional visualizations and our Nerfstudio package can be found at https://chengine.github.io/nbv_gym/.