KC-3DGS: Kurtosis-Constrained Gaussian Splatting for High-Fidelity View Synthesis
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 3DGS training with wavelet-domain supervision based on natural image statistics. Our method combines three components: (1) a multi-scale wavelet coefficient alignment loss that explicitly penalizes missing high-frequency detail, (2) a supervised kurtosis concentration loss that encourages rendered images to match the heavy-tailed frequency statistics of ground-truth images, and (3) a cross-band covariance penalty that promotes frequency specialization. We provide theoretical analysis showing that pixel-space losses admit a family of indistinguishable perturbations under wavelet redistribution, and that our joint objective excludes degenerate solutions. Experiments across MipNeRF360, Tanks&Temples, MVImgNet, DeepBlending, and WRIVA-ULTRRA demonstrate consistent improvements in perceptual quality. On the challenging WRIVA-ULTRRA outdoor dataset, KC-3DGS achieves a 9.48% improvement in DreamSim while also improving PSNR, SSIM, and LPIPS. In sparse-view settings with only 12 training images, our method improves PSNR by up to 0.5 dB on MipNeRF360 while maintaining perceptual quality. The approach integrates seamlessly into existing 3DGS pipelines as a plug-and-play regularization strategy.
Code (0)
등록된 구현이 없습니다.
Tasks
Novel View SynthesisSimilar Papers 제목 키워드 기반
PAGaS: Pixel-Aligned 1DoF Gaussian Splatting for Depth Refinement
Gaussian Splatting (GS) has emerged as an efficient approach for high-quality novel view synthesis. While early GS variants struggled to accurately model the scene's geometry, recent advancements constraining the Gaussia…
Novel View Synthesis3D ReconstructionSort-free Gaussian Splatting via Weighted Sum Rendering
Recently, 3D Gaussian Splatting (3DGS) has emerged as a significant advancement in 3D scene reconstruction, attracting considerable attention due to its ability to recover high-fidelity details while maintaining low comp…
3DGS3D Scene ReconstructionGPUConstrained Dynamic Gaussian Splatting
While Dynamic Gaussian Splatting enables high-fidelity 4D reconstruction, its deployment is severely hindered by a fundamental dilemma: unconstrained densification leads to excessive memory consumption incompatible with …
Fidelity-Constrained Anchoring for Black-Box Denoisers
We propose a fidelity-constrained framework that anchors the output of a black-box denoiser to its input without retraining and with little additional computation. The method linearly blends the denoised image with the i…
Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene Representation
Recent advancements in dynamic 3D scene reconstruction have shown promising results, enabling high-fidelity 3D novel view synthesis with improved temporal consistency. Among these, 4D Gaussian Splatting (4DGS) has emerge…
3D Scene ReconstructionComputational EfficiencyNovel View Synthesis