WIPES: Wavelet-based Visual Primitives

TL;DR

WIPES introduces a wavelet-based visual primitive that captures multi-frequency signals efficiently, enabling faster rendering and higher quality in 3D vision and graphics tasks compared to existing methods.

Contribution

The paper presents WIPES, a novel wavelet-based representation for visual signals that improves rendering speed and quality over prior frequency-guided and neural network-based approaches.

Findings

WIPES achieves higher rendering quality than INR-based methods.

WIPES provides faster inference in various visual tasks.

WIPES outperforms Gaussian-based representations in rendering quality.

Abstract

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.