Search papers, labs, and topics across Lattice.
The paper addresses the active view selection problem for 3D reconstruction by developing a novel coverage-based metric, COVER, that approximates Fisher Information Gain. COVER selects viewpoints that prioritize observing insufficiently covered geometry, avoiding expensive transmittance estimation. Experiments within Nerfstudio on real datasets demonstrate that COVER consistently improves reconstruction quality compared to existing active view selection methods in both fixed and embodied data acquisition scenarios.
Stop guessing where to point your cameras: a simple coverage-based metric, COVER, outperforms state-of-the-art active view selection methods for 3D reconstruction.
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/.
