Gaussian Entropy Fields: Driving Adaptive Sparsity in 3D Gaussian Optimization

TL;DR

This paper introduces Gaussian Entropy Fields (GEF), a novel approach that uses entropy minimization and adaptive regularization to improve surface reconstruction and rendering quality in 3D Gaussian optimization, achieving state-of-the-art results.

Contribution

The paper proposes a new entropy-driven surface modeling framework with adaptive spatial regularization and multi-scale geometric preservation for 3D Gaussian optimization.

Findings

Achieves competitive geometric precision on DTU and T extbackslash T benchmarks.

Delivers superior rendering quality on Mip-NeRF 360.

Obtains the best SSIM and LPIPS scores among baselines.

Abstract

3D Gaussian Splatting (3DGS) has emerged as a leading technique for novel view synthesis, demonstrating exceptional rendering efficiency. \replaced[]{Well-reconstructed surfaces can be characterized by low configurational entropy, where dominant primitives clearly define surface geometry while redundant components are suppressed.}{The key insight is that well-reconstructed surfaces naturally exhibit low configurational entropy, where dominant primitives clearly define surface geometry while suppressing redundant components.} Three complementary technical contributions are introduced: (1) entropy-driven surface modeling via entropy minimization for low configurational entropy in primitive distributions; (2) adaptive spatial regularization using the Surface Neighborhood Redundancy Index (SNRI) and image entropy-guided weighting; (3) multi-scale geometric preservation through competitive cross-scale entropy alignment. Extensive experiments demonstrate that GEF achieves competitive geometric precision on DTU and T\&T benchmarks, while delivering superior rendering quality compared to existing methods on Mip-NeRF 360. Notably, superior Chamfer Distance (0.64) on DTU and F1 score (0.44) on T\&T are obtained, alongside the best SSIM (0.855) and LPIPS (0.136) among baselines on Mip-NeRF 360, validating the framework's ability to enhance surface reconstruction accuracy without compromising photometric fidelity.