{"ID":2832871,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.04542","arxiv_id":"2512.04542","title":"Gaussian Entropy Fields: Driving Adaptive Sparsity in 3D Gaussian Optimization","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\\\u0026T 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\\\u0026T 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.","short_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...","url_abs":"https://arxiv.org/abs/2512.04542","url_pdf":"https://arxiv.org/pdf/2512.04542v1","authors":"[\"Hong Kuang\",\"Jianchen Liu\"]","published":"2025-12-04T07:44:42Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}