AI RESEARCH
KC-3DGS: Kurtosis-Constrained Gaussian Splatting for High-Fidelity View Synthesis
arXiv CS.CV
•
ArXi:2606.03120v1 Announce Type: new 3D Gaussian Splatting (3DGS) enables real-time novel view synthesis by representing scenes as collections of anisotropic Gaussians optimized via differentiable rasterization. However, standard pixel-space losses (L1, SSIM) constrain only aggregate reconstruction error, permitting the optimization to redistribute error across frequency scales. This leads to oversmoothing and structural artifacts, particularly in sparse-view settings where supervision is limited. We propose KC-3DGS, which augments 3