CoMapGS: Covisibility Map-based Gaussian Splatting for Sparse Novel View Synthesis

CVPR 2025

Huawei Noah's Ark Lab
teaser

Main idea. Conventional sparse view synthesis methods using 3DGS prioritize frequently captured regions, shown as the brightest areas in the covisibility map, resulting in better reconstruction for these regions but missing details in sparsely captured areas. By using a covisibility map, we guide a sparse 3DGS to focus on these underrepresented regions, enhancing sparse novel view synthesis.

Abstract

We propose Covisibility Map-based Gaussian Splatting (CoMapGS), designed to recover underrepresented sparse regions in sparse novel view synthesis. CoMapGS addresses both high- and low-uncertainty regions by constructing covisibility maps, enhancing initial point clouds, and applying uncertainty-aware weighted supervision with a proximity classifier. Our contributions are threefold: (1) CoMapGS reframes novel view synthesis by leveraging covisibility maps as a core component to address region-specific uncertainty levels; (2) Enhanced initial point clouds for both low- and high-uncertainty regions compensate for sparse COLMAP-derived point clouds, improving reconstruction quality and benefiting few-shot 3DGS methods; (3) Adaptive supervision with covisibility-score-based weighting and proximity classification achieves consistent performance gains across scenes with various sparsity scores derived from covisibility maps. Experimental results demonstrate that CoMapGS outperforms state-of-the-art methods on datasets including Mip-NeRF 360 and LLFF.

Video

Results: rendering quality

LLFF Dataset teaser

Mip-NeRF 360 Dataset teaser

CoMapGS improves rendering quality in sparse view settings.



Results: geometric consistency

LLFF Dataset teaser teaser

Mip-NeRF 360 Dataset teaser teaser

CoMapGS improves geometric consistency in sparse view settings.

BibTeX

@inproceedings{jang2025comapgs,
  author    = {Youngkyoon Jang and Eduardo Pérez-Pellitero},
  title     = {CoMapGS: Covisibility Map-based Gaussian Splatting for Sparse Novel View Synthesis},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year      = {2025}
}