CoMapGS: Covisibility Map-based Gaussian Splatting for Sparse Novel View Synthesis
This work improves 3D reconstruction quality for sparse view synthesis, benefiting applications in computer vision and graphics, though it appears incremental as it builds on existing Gaussian splatting methods.
The paper tackles the problem of sparse novel view synthesis by proposing CoMapGS, which addresses underrepresented sparse regions using covisibility maps, enhanced point clouds, and uncertainty-aware supervision. The method outperforms state-of-the-art approaches on datasets like Mip-NeRF 360 and LLFF.
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 using 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; (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 varying 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.