Coverage Optimization for Camera View Selection

arXiv cs.CV / 4/8/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper addresses active camera view selection for improving 3D reconstruction and introduces a principled criterion for choosing informative camera poses.
It proposes COVER (Camera Optimization for View Exploration and Reconstruction), which approximates Fisher Information Gain by prioritizing viewpoints that cover geometry insufficiently observed by earlier cameras.
COVER uses a lightweight, coverage-based metric that avoids expensive transmittance estimation and is designed to be robust to noise and training dynamics.
The authors integrate the method into Nerfstudio and report consistent reconstruction-quality gains over state-of-the-art active view selection baselines across multiple datasets and radiance-field setups.
Code and visualizations are provided via the Nerfstudio package and nbv_gym resources linked in the paper page.

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/.