WIPES: Wavelet-based Visual Primitives
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Novel View SynthesisSimilar Papers 제목 키워드 기반
Samplet limits and multiwavelets
Samplets are data adapted multiresolution analyses of localized discrete signed measures. They can be constructed on scattered data sites in arbitrary dimension such that they exhibit vanishing moments with respect to an…
Shape Primitive Histogram: A Novel Low-Level Face Representation for Face Recognition
We further exploit the representational power of Haar wavelet and present a novel low-level face representation named Shape Primitives Histogram (SPH) for face recognition. Since human faces exist abundant shape features…
Face RecognitionEndoWave: Rational-Wavelet 4D Gaussian Splatting for Endoscopic Reconstruction
In robot-assisted minimally invasive surgery, accurate 3D reconstruction from endoscopic video is vital for downstream tasks and improved outcomes. However, endoscopic scenarios present unique challenges, including photo…
3D ReconstructionTR-GS: High-Fidelity Sparse-View CT Volumetric Rendering via t-Distribution Gaussian Splatting and Ray-Confidence Modeling
High-fidelity 3D medical visualization supports applications such as clinical assessment and surgical planning. Sparse-view computed tomography (CT) can reduce projection requirements and associated radiation exposure, b…
Exploring Compositionality in Vision Transformers using Wavelet Representations
While insights into the workings of the transformer model have largely emerged by analysing their behaviour on language tasks, this work investigates the representations learnt by the Vision Transformer (ViT) encoder thr…
Representation Learning