ActiveNeRF: Learning Accurate 3D Geometry by Active Pattern Projection

TL;DR

ActiveNeRF enhances 3D geometry reconstruction in NeRFs by actively projecting high-frequency patterns onto scenes, enabling more accurate geometry learning through a learnable pattern rendering pipeline, outperforming existing methods.

Contribution

The paper introduces a novel active pattern projection framework for NeRFs, improving geometry accuracy by jointly learning scene geometry and active patterns with a learnable rendering pipeline.

Findings

Outperforms state-of-the-art geometry reconstruction methods.

Effective in both simulation and real-world experiments.

Improves geometry quality by actively projecting high-frequency patterns.

Abstract

NeRFs have achieved incredible success in novel view synthesis. However, the accuracy of the implicit geometry is unsatisfactory because the passive static environmental illumination has low spatial frequency and cannot provide enough information for accurate geometry reconstruction. In this work, we propose ActiveNeRF, a 3D geometry reconstruction framework, which improves the geometry quality of NeRF by actively projecting patterns of high spatial frequency onto the scene using a projector which has a constant relative pose to the camera. We design a learnable active pattern rendering pipeline which jointly learns the scene geometry and the active pattern. We find that, by adding the active pattern and imposing its consistency across different views, our proposed method outperforms state of the art geometry reconstruction methods qualitatively and quantitatively in both simulation and real experiments. Code is avaliable at https://github.com/hcp16/active_nerf