MonoPatchNeRF: Improving Neural Radiance Fields with Patch-based Monocular Guidance

arXiv:2404.08252v1 Announce Type: new
Abstract: The latest regularized Neural Radiance Field (NeRF) approaches produce poor geometry and view extrapolation for multiview stereo (MVS) benchmarks such as ETH3D. In this paper, we aim to create 3D models that provide accurate geometry and view synthesis, partially closing the large geometric performance gap between NeRF and traditional MVS methods. We propose a patch-based approach that effectively leverages monocular surface normal and relative depth predictions. The patch-based ray sampling also enables the appearance regularization …

3d models abstract aim arxiv benchmarks create cs.cv fields gap geometry guidance improving nerf neural radiance field neural radiance fields paper performance synthesis type view