DWTGS: Rethinking Frequency Regularization for Sparse-view 3D Gaussian Splatting

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Nguyen, Hung, Li, Runfa, Le, An, Nguyen, Truong
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908580179869696
author Nguyen, Hung
Li, Runfa
Le, An
Nguyen, Truong
author_facet Nguyen, Hung
Li, Runfa
Le, An
Nguyen, Truong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_15690
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DWTGS: Rethinking Frequency Regularization for Sparse-view 3D Gaussian Splatting
Nguyen, Hung
Li, Runfa
Le, An
Nguyen, Truong
Computer Vision and Pattern Recognition
Image and Video Processing
Signal Processing
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.
title DWTGS: Rethinking Frequency Regularization for Sparse-view 3D Gaussian Splatting
topic Computer Vision and Pattern Recognition
Image and Video Processing
Signal Processing
url https://arxiv.org/abs/2507.15690