KC-3DGS: Kurtosis-Constrained Gaussian Splatting for High-Fidelity View Synthesis

Vivekjyoti Banerjee, Abhay Yadav, Rama Chellappa, Aniket RoyarXiv 2026 · arXiv

TL;DR

KC-3DGS introduces a plug-and-play, wavelet-domain regularization strategy for 3D Gaussian Splatting (3DGS) to tackle the problem of oversmoothing and structural artifacts in sparse-view settings. By constraining higher-order natural image statistics—specifically kurtosis concentration and cross-band covariance—it forces the optimization to preserve fine textures and sharp details that standard pixel-space losses miss.

What Problem Does This Paper Address?

3D Gaussian Splatting (3DGS) has revolutionized real-time novel view synthesis, but it hits a wall when training data is sparse (e.g., only a dozen views of a scene). Under limited supervision, 3DGS optimization becomes highly underconstrained, frequently producing "floaters" (spurious floating artifacts), blurry blobs, and severe oversmoothing.

The root cause lies in standard photometric loss functions like $L_1$ and SSIM. These metrics operate in pixel space and only constrain aggregate reconstruction error. This creates a mathematical blind spot: the optimization algorithm can freely redistribute error across different frequency scales. As long as the average pixel difference is low, the model can smooth out high-frequency details (like textures and sharp edges) without being penalized.

Methods

To close this loophole, the authors propose KC-3DGS, which adds a lightweight, fully differentiable wavelet-domain regularization framework to standard 3DGS pipelines.

The method applies a 3-level discrete wavelet transform (DWT) using Daubechies-3 wavelets to both the rendered and ground-truth images, breaking them down into multi-scale frequency subbands.

KC-3DGS Training Pipeline

It then applies three distinct losses:

  1. Scale-Weighted Wavelet Alignment Loss ($L_{wav}$): Directly aligns wavelet coefficients between rendered and ground-truth images. Crucially, it exponentially upweights finer scales (by a factor of $2^j$) to counteract the natural $1/f^\alpha$ energy decay of natural images, ensuring high-frequency details get a strong gradient signal.
  2. Supervised Kurtosis Concentration Loss ($L_{KC}^{sup}$): Natural images exhibit heavy-tailed (high-kurtosis) distributions in the wavelet domain that are remarkably consistent across subbands. This loss forces the rendered image's subband kurtosis values and overall spread to match the ground truth, preventing any single frequency band from dominating.
  3. Supervised Cross-Band Covariance Penalty ($L_{CBC}^{sup}$): This penalty minimizes the statistical dependency (off-diagonal covariance) between different subbands, encouraging frequency specialization while ensuring the spatial correlation matches the ground truth (e.g., preserving sharp corners where multiple orientations intersect).

Datasets

The authors evaluated their method across five diverse benchmarks:

  • MipNeRF360: Indoor and outdoor scenes, tested in both full-view and highly constrained 12-view sparse settings.
  • Tanks&Temples: Large-scale outdoor geometry with wide-baseline views.
  • MVImgNet: Object-centric multi-view dataset.
  • DeepBlending: Bounded indoor scenes with challenging lighting and reflections.
  • WRIVA-ULTRRA: A highly challenging, real-world outdoor dataset characterized by irregular camera distributions, noisy coverage, varying resolutions, and transient objects (used as a stress test for sparse-view robustness).

Key Insights and Ideas

  • The Pixel-Space Blind Spot is Real: The authors mathematically prove (via Parseval's identity) that pixel-space $L_2$ losses admit a $(3J-1)$-dimensional family of indistinguishable perturbations. Optimization can completely scramble how error is distributed across scales without changing the pixel loss value. Subband supervision closes this loophole.
  • Unsupervised Kurtosis is Degenerate: Simply minimizing the spread of kurtosis across subbands without an anchor is a trap—the model can satisfy it perfectly by rendering a completely blurry, uniformly Gaussian image. Grounding the kurtosis directly to the ground-truth image's statistics is essential for proper regularization.
  • Decorrelation as a Likelihood: The cross-band covariance penalty is proven to be equivalent to minimizing the KL divergence between the joint distribution of subbands and a factorized Gaussian distribution, providing a solid probabilistic foundation for subband independence.

Key Results

  • Perceptual Leap: On the rugged WRIVA-ULTRRA dataset, KC-3DGS achieved a 9.48% relative improvement in DreamSim (a metric for human visual similarity) while simultaneously improving PSNR, SSIM, and LPIPS.
  • Sparse-View Robustness: In extreme 12-view sparse settings, the method boosted PSNR by up to 0.5 dB on MipNeRF360 while significantly reducing floaters and color bleeding around fine structures like foliage.
  • Plug-and-Play Integration: The regularizer requires zero architectural changes and integrates seamlessly into existing 3DGS frameworks like Nerfstudio's Splatfacto (yielding an 8.51% DreamSim boost) and FasterGS (yielding a 12.24% boost).
Figure 1: Overview of KC-3DGS. Top: Our method extracts wavelet features via a 3-level discrete wavelet transform (DWT) [20, 7], computes wavelet statistics (kurtosis κ and cross-band covariance Σ), and applies frequency-domain losses as a plug-and-play regularization for 3D Gaussian Splatting [15]. Bottom: Visual comparisons demonstrating consistent perceptual improvements across different 3DGS implementations. Adding KC-3DGS regularization to Splatfacto [32] improves DreamSim by 8.51%, while integration with FasterGS [11] yields a 12.24% improvement from some view- points, highlighting the method’s effectiveness as a general-purpose enhancement for existing 3DGS pipelines.

Limitations and Future Work

  • Over-Regularization in Dense Views: KC-3DGS is highly optimized for sparse-view regimes. When abundant training views are available (dense multi-view coverage), the frequency constraints can occasionally over-regularize the optimization, leading to minor drops in standard metrics like PSNR on datasets like MipNeRF360.
  • Computational Overhead: Incorporating the 2D discrete wavelet transform adds noticeable computational overhead during training. For speed-optimized frameworks like FasterGS, it resulted in a 2.7× increase in training time because the unoptimized DWT becomes a bottleneck relative to the highly optimized CUDA rasterizer. The authors note mitigating this overhead as a key direction for future work.

Summary updated

Abstract

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.
BibTeX
@misc{banerjee2026kc,
  author = {Vivekjyoti Banerjee and Abhay Yadav and Rama Chellappa and Aniket Roy},
  title = {{KC-3DGS: Kurtosis-Constrained Gaussian Splatting for High-Fidelity View Synthesis}},
  year = {2026},
  eprint = {2606.03120},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.03120},
}
Figure