{"ID":2892309,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.15690","arxiv_id":"2507.15690","title":"DWTGS: Rethinking Frequency Regularization for Sparse-view 3D Gaussian Splatting","abstract":"Sparse-view 3D Gaussian Splatting (3DGS) presents significant challenges in reconstructing high-quality novel views, as it often overfits to the widely-varying high-frequency (HF) details of the sparse training views. While frequency regularization can be a promising approach, its typical reliance on Fourier transforms causes difficult parameter tuning and biases towards detrimental HF learning. We propose DWTGS, a framework that rethinks frequency regularization by leveraging wavelet-space losses that provide additional spatial supervision. Specifically, we supervise only the low-frequency (LF) LL subbands at multiple DWT levels, while enforcing sparsity on the HF HH subband in a self-supervised manner. Experiments across benchmarks show that DWTGS consistently outperforms Fourier-based counterparts, as this LF-centric strategy improves generalization and reduces HF hallucinations.","short_abstract":"Sparse-view 3D Gaussian Splatting (3DGS) presents significant challenges in reconstructing high-quality novel views, as it often overfits to the widely-varying high-frequency (HF) details of the sparse training views. While frequency regularization can be a promising approach, its typical reliance on Fourier transforms...","url_abs":"https://arxiv.org/abs/2507.15690","url_pdf":"https://arxiv.org/pdf/2507.15690v3","authors":"[\"Hung Nguyen\",\"Runfa Li\",\"An Le\",\"Truong Nguyen\"]","published":"2025-07-21T14:56:46Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"eess.IV\",\"eess.SP\"]","methods":"[]","has_code":false}