paper-with-me

홈 › Papers

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

2025-07-21 · Hung Nguyen, Runfa Li, An Le, Truong Nguyen arxiv

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.

📄 PDF Abstract BibTeX arXiv:2507.15690

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization

2023-03-13 · CVPR 2023 1 · Jiawei Yang, Marco Pavone, Yue Wang

Novel view synthesis with sparse inputs is a challenging problem for neural radiance fields (NeRF). Recent efforts alleviate this challenge by introducing external supervision, such as pre-trained models and extra depth …

NeRFNeural RenderingNovel View Synthesis

PairDropGS: Paired Dropout-Induced Consistency Regularization for Sparse-View Gaussian Splatting

2026-05-12 · Hantang Li, Qiang Zhu, Xiandong Meng, Xingtao Wang 외 arxiv

Dropout-based sparse-view 3D Gaussian Splatting (3DGS) methods alleviate overfitting by randomly suppressing Gaussian primitives during training. Existing methods mainly focus on designing increasingly sophisticated drop…

Representation Learning

Frequency-regularized Neural Representation Method for Sparse-view Tomographic Reconstruction

2024-09-22 · Jingmou Xian, Jian Zhu, Haolin Liao, Si Li

Sparse-view tomographic reconstruction is a pivotal direction for reducing radiation dose and augmenting clinical applicability. While many research works have proposed the reconstruction of tomographic images from spars…

Initialize to Generalize: A Stronger Initialization Pipeline for Sparse-View 3DGS

2025-10-20 · Feng Zhou, Wenkai Guo, Pu Cao, Zhicheng Zhang 외 arxiv

Sparse-view 3D Gaussian Splatting (3DGS) often overfits to the training views, leading to artifacts like blurring in novel view rendering. Prior work addresses it either by enhancing the initialization (\emph{i.e.}, the …

SGCNeRF: Few-Shot Neural Rendering via Sparse Geometric Consistency Guidance

2024-04-01 · Yuru Xiao, Xianming Liu, Deming Zhai, Kui Jiang 외

Neural Radiance Field (NeRF) technology has made significant strides in creating novel viewpoints. However, its effectiveness is hampered when working with sparsely available views, often leading to performance dips due …

NeRFNeural RenderingNovel View Synthesis