Subtractive Modulative Network with Learnable Periodic Activations
This work addresses the need for efficient neural representations in computer vision tasks, offering a novel architecture with competitive performance.
The paper tackles the problem of parameter-efficient implicit neural representations by proposing the Subtractive Modulative Network (SMN), which achieves a PSNR of 40+ dB on image datasets and shows advantages in 3D NeRF novel view synthesis.
We propose the Subtractive Modulative Network (SMN), a novel, parameter-efficient Implicit Neural Representation (INR) architecture inspired by classical subtractive synthesis. The SMN is designed as a principled signal processing pipeline, featuring a learnable periodic activation layer (Oscillator) that generates a multi-frequency basis, and a series of modulative mask modules (Filters) that actively generate high-order harmonics. We provide both theoretical analysis and empirical validation for our design. Our SMN achieves a PSNR of $40+$ dB on two image datasets, comparing favorably against state-of-the-art methods in terms of both reconstruction accuracy and parameter efficiency. Furthermore, consistent advantage is observed on the challenging 3D NeRF novel view synthesis task. Supplementary materials are available at https://inrainbws.github.io/smn/.