EdgeNeRF: Edge-Guided Regularization for Neural Radiance Fields from Sparse Views

TL;DR

EdgeNeRF introduces an edge-guided regularization technique for neural radiance fields that improves 3D reconstruction quality from sparse views by preserving boundary details and reducing artifacts.

Contribution

The paper proposes a novel edge-guided regularization method for NeRF that enhances boundary detail preservation in sparse-view 3D reconstruction.

Findings

Outperforms existing methods on LLFF and DTU datasets

Better preservation of sharp geometric boundaries

Plug-and-play module improves other methods' performance

Abstract

Neural Radiance Fields (NeRF) achieve remarkable performance in dense multi-view scenarios, but their reconstruction quality degrades significantly under sparse inputs due to geometric artifacts. Existing methods utilize global depth regularization to mitigate artifacts, leading to the loss of geometric boundary details. To address this problem, we propose EdgeNeRF, an edge-guided sparse-view 3D reconstruction algorithm. Our method leverages the prior that abrupt changes in depth and normals generate edges. Specifically, we first extract edges from input images, then apply depth and normal regularization constraints to non-edge regions, enhancing geometric consistency while preserving high-frequency details at boundaries. Experiments on LLFF and DTU datasets demonstrate EdgeNeRF's superior performance, particularly in retaining sharp geometric boundaries and suppressing artifacts. Additionally, the proposed edge-guided depth regularization module can be seamlessly integrated into other methods in a plug-and-play manner, significantly improving their performance without substantially increasing training time. Code is available at https://github.com/skyhigh404/edgenerf.