WIPES: Wavelet-based Visual Primitives

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Wenhao, Zhu, Hao, Wu, Delong, Kang, Di, Bao, Linchao, Cao, Xun, Ma, Zhan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915451121958912
author Zhang, Wenhao
Zhu, Hao
Wu, Delong
Kang, Di
Bao, Linchao
Cao, Xun
Ma, Zhan
author_facet Zhang, Wenhao
Zhu, Hao
Wu, Delong
Kang, Di
Bao, Linchao
Cao, Xun
Ma, Zhan
contents Pursuing a continuous visual representation that offers flexible frequency modulation and fast rendering speed has recently garnered increasing attention in the fields of 3D vision and graphics. However, existing representations often rely on frequency guidance or complex neural network decoding, leading to spectrum loss or slow rendering. To address these limitations, we propose WIPES, a universal Wavelet-based vIsual PrimitivES for representing multi-dimensional visual signals. Building on the spatial-frequency localization advantages of wavelets, WIPES effectively captures both the low-frequency "forest" and the high-frequency "trees." Additionally, we develop a wavelet-based differentiable rasterizer to achieve fast visual rendering. Experimental results on various visual tasks, including 2D image representation, 5D static and 6D dynamic novel view synthesis, demonstrate that WIPES, as a visual primitive, offers higher rendering quality and faster inference than INR-based methods, and outperforms Gaussian-based representations in rendering quality.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12615
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WIPES: Wavelet-based Visual Primitives
Zhang, Wenhao
Zhu, Hao
Wu, Delong
Kang, Di
Bao, Linchao
Cao, Xun
Ma, Zhan
Computer Vision and Pattern Recognition
Pursuing a continuous visual representation that offers flexible frequency modulation and fast rendering speed has recently garnered increasing attention in the fields of 3D vision and graphics. However, existing representations often rely on frequency guidance or complex neural network decoding, leading to spectrum loss or slow rendering. To address these limitations, we propose WIPES, a universal Wavelet-based vIsual PrimitivES for representing multi-dimensional visual signals. Building on the spatial-frequency localization advantages of wavelets, WIPES effectively captures both the low-frequency "forest" and the high-frequency "trees." Additionally, we develop a wavelet-based differentiable rasterizer to achieve fast visual rendering. Experimental results on various visual tasks, including 2D image representation, 5D static and 6D dynamic novel view synthesis, demonstrate that WIPES, as a visual primitive, offers higher rendering quality and faster inference than INR-based methods, and outperforms Gaussian-based representations in rendering quality.
title WIPES: Wavelet-based Visual Primitives
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.12615