Joint Implicit Image Function for Guided Depth Super-Resolution

TL;DR

This paper introduces a novel neural implicit image function (JIIF) for guided depth super-resolution, effectively combining interpolation and learning to outperform existing methods on benchmark datasets.

Contribution

The paper proposes the Joint Implicit Image Function (JIIF), a new implicit neural representation that learns interpolation weights and values simultaneously for guided depth super-resolution.

Findings

Significantly outperforms state-of-the-art methods on three benchmarks.

Uses a graph attention mechanism for learning interpolation weights.

Effectively models depth super-resolution as an implicit neural interpolation problem.

Abstract

Guided depth super-resolution is a practical task where a low-resolution and noisy input depth map is restored to a high-resolution version, with the help of a high-resolution RGB guide image. Existing methods usually view this task as a generalized guided filtering problem that relies on designing explicit filters and objective functions, or a dense regression problem that directly predicts the target image via deep neural networks. These methods suffer from either model capability or interpretability. Inspired by the recent progress in implicit neural representation, we propose to formulate the guided super-resolution as a neural implicit image interpolation problem, where we take the form of a general image interpolation but use a novel Joint Implicit Image Function (JIIF) representation to learn both the interpolation weights and values. JIIF represents the target image domain with spatially distributed local latent codes extracted from the input image and the guide image, and uses a graph attention mechanism to learn the interpolation weights at the same time in one unified deep implicit function. We demonstrate the effectiveness of our JIIF representation on guided depth super-resolution task, significantly outperforming state-of-the-art methods on three public benchmarks. Code can be found at \url{https://git.io/JC2sU}.