Learnable Multi-level Discrete Wavelet Transforms for 3D Gaussian Splatting Frequency Modulation

• URL: http://arxiv.org/abs/2602.14199v1
• Date: Sun, 15 Feb 2026 15:49:03 GMT
• Title: Learnable Multi-level Discrete Wavelet Transforms for 3D Gaussian Splatting Frequency Modulation
• Authors: Hung Nguyen, An Le, Truong Nguyen,
• Abstract summary: 3D Gaussian Splatting (3DGS) has emerged as a powerful approach for novel view synthesis.<n>We propose a multi-level DWT-based frequency modulation framework for 3DGS.
• Score: 4.380983033049863
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful approach for novel view synthesis. However, the number of Gaussian primitives often grows substantially during training as finer scene details are reconstructed, leading to increased memory and storage costs. Recent coarse-to-fine strategies regulate Gaussian growth by modulating the frequency content of the ground-truth images. In particular, AutoOpti3DGS employs the learnable Discrete Wavelet Transform (DWT) to enable data-adaptive frequency modulation. Nevertheless, its modulation depth is limited by the 1-level DWT, and jointly optimizing wavelet regularization with 3D reconstruction introduces gradient competition that promotes excessive Gaussian densification. In this paper, we propose a multi-level DWT-based frequency modulation framework for 3DGS. By recursively decomposing the low-frequency subband, we construct a deeper curriculum that provides progressively coarser supervision during early training, consistently reducing Gaussian counts. Furthermore, we show that the modulation can be performed using only a single scaling parameter, rather than learning the full 2-tap high-pass filter. Experimental results on standard benchmarks demonstrate that our method further reduces Gaussian counts while maintaining competitive rendering quality.

Related papers

• Tail-Aware Post-Training Quantization for 3D Geometry Models [58.79500829118265]
  Post-Training Quantization (PTQ) enables efficient inference without retraining.<n>PTQ fails to transfer effectively to 3D models due to intricate feature distributions and prohibitive calibration overhead.<n>We propose TAPTQ, a Tail-Aware Post-Training Quantization pipeline for 3D geometric learning.
  arXiv  Detail & Related papers  (2026-02-02T07:21:15Z)
• Quantized Visual Geometry Grounded Transformer [67.15451442018258]
  This paper proposes the first Quantization framework for VGGTs, namely QuantVGGT.<n>We introduce Dual-Smoothed Fine-Grained Quantization, which integrates pre-global Hadamard rotation and post-local channel smoothing.<n>We also design Noise-Filtered Diverse Sampling, which filters outliers via deep-layer statistics.
  arXiv  Detail & Related papers  (2025-09-25T15:17:11Z)
• Scale-GS: Efficient Scalable Gaussian Splatting via Redundancy-filtering Training on Streaming Content [28.476493987089466]
  This paper presents M, a scalable Gaussian Splatting framework for efficient training in streaming tasks.<n>M achieves superior visual quality while significantly reducing training time compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-08-29T09:13:04Z)
• DWTGS: Rethinking Frequency Regularization for Sparse-view 3D Gaussian Splatting [5.93524554224854]
  Sparse-view 3D Gaussian Splatting (3DGS) presents significant challenges in reconstructing high-quality novel views.<n>We propose DWTGS, a framework that rethinks frequency regularization by leveraging wavelet-space losses that provide additional spatial supervision.
  arXiv  Detail & Related papers  (2025-07-21T14:56:46Z)
• From Coarse to Fine: Learnable Discrete Wavelet Transforms for Efficient 3D Gaussian Splatting [5.026688852582894]
  AutoOpti3DGS is a training-time framework that automatically restrains Gaussian proliferation without sacrificing visual fidelity.<n>Wavelet-driven, coarse-to-fine process delays the formation of redundant fine Gaussians.
  arXiv  Detail & Related papers  (2025-06-29T00:27:17Z)
• Frequency-Aware Gaussian Splatting Decomposition [10.951186766576173]
  3D Gaussian Splatting (3D-GS) has revolutionized novel view synthesis with its efficient, explicit representation.<n>We introduce a frequency-decomposed 3D-GS framework that groups 3D Gaussians that correspond to subbands in the Laplacian Pyrmaids of the input images.
  arXiv  Detail & Related papers  (2025-03-27T07:35:40Z)
• Frequency-Aware Density Control via Reparameterization for High-Quality Rendering of 3D Gaussian Splatting [11.892334330536974]
  3D Gaussian Splatting (3DGS) can better represent scene details in high-frequency regions.<n>3DGS currently lacks an explicit constraint linking the density and scale of 3D Gaussians across the domain.<n>We develop a frequency-aware density control strategy, consisting of densification and deletion, to improve representation quality.
  arXiv  Detail & Related papers  (2025-03-10T07:30:45Z)
• LP-3DGS: Learning to Prune 3D Gaussian Splatting [71.97762528812187]
  We propose learning-to-prune 3DGS, where a trainable binary mask is applied to the importance score that can find optimal pruning ratio automatically. Experiments have shown that LP-3DGS consistently produces a good balance that is both efficient and high quality.
  arXiv  Detail & Related papers  (2024-05-29T05:58:34Z)
• FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization [67.47895278233717]
  We develop a progressive frequency regularization technique to tackle the over-reconstruction issue within the frequency space. FreGS achieves superior novel view synthesis and outperforms the state-of-the-art consistently.
  arXiv  Detail & Related papers  (2024-03-11T17:00:27Z)
• GaussianPro: 3D Gaussian Splatting with Progressive Propagation [49.918797726059545]
  3DGS relies heavily on the point cloud produced by Structure-from-Motion (SfM) techniques. We propose a novel method that applies a progressive propagation strategy to guide the densification of the 3D Gaussians. Our method significantly surpasses 3DGS on the dataset, exhibiting an improvement of 1.15dB in terms of PSNR.
  arXiv  Detail & Related papers  (2024-02-22T16:00:20Z)
• GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering [112.16239342037714]
  GES (Generalized Exponential Splatting) is a novel representation that employs Generalized Exponential Function (GEF) to model 3D scenes. With the aid of a frequency-modulated loss, GES achieves competitive performance in novel-view synthesis benchmarks.
  arXiv  Detail & Related papers  (2024-02-15T17:32:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.