AI RESEARCH

SparseSplat: Towards Applicable Feed-Forward 3D Gaussian Splatting with Pixel-Unaligned Prediction

arXiv CS.CV

ArXi:2604.03069v1 Announce Type: new Recent progress in feed-forward 3D Gaussian Splatting (3DGS) has notably improved rendering quality. However, the spatially uniform and highly redundant 3DGS map generated by previous feed-forward 3DGS methods limits their integration into downstream reconstruction tasks. We propose SparseSplat, the first feed-forward 3DGS model that adaptively adjusts Gaussian density according to scene structure and information richness of local regions, yielding highly compact 3DGS maps.