Edge-Aligned Initialization of Kernels for Steered Mixture-of-Experts

TL;DR

This paper introduces an edge-based initialization method for Steered Mixture-of-Experts that improves reconstruction quality and reduces computational costs by leveraging image contours for deterministic kernel parameter estimation.

Contribution

The paper proposes a novel edge-aligned initialization scheme for SMoE that minimizes reliance on gradient-based optimization, enhancing scalability and efficiency.

Findings

Reduces memory and computational costs significantly.

Achieves high-quality image reconstruction with deterministic initialization.

Enables more scalable and efficient SMoE applications.

Abstract

Steered Mixture-of-Experts (SMoE) has recently emerged as a powerful framework for spatial-domain image modeling, enabling high-fidelity image representation using a remarkably small number of parameters. Its ability to steer kernel-based experts toward structural image features has led to successful applications in image compression, denoising, super-resolution, and light field processing. However, practical adoption is hindered by the reliance on gradient-based optimization to estimate model parameters on a per-image basis - a process that is computationally intensive and difficult to scale. Initialization strategies for SMoE are an essential component that directly affects convergence and reconstruction quality. In this paper, we propose a novel, edge-based initialization scheme that achieves good reconstruction qualities while reducing the need for stochastic optimization significantly. Through a method that leverages Canny edge detection to extract a sparse set of image contours, kernel positions and orientations are deterministically inferred. A separate approach enables the direct estimation of initial expert coefficients. This initialization reduces both memory consumption and computational cost.