CVJul 19, 2021

Joint Implicit Image Function for Guided Depth Super-Resolution

arXiv:2107.08717v283 citations
Originality Incremental advance
AI Analysis

This addresses the problem of enhancing low-resolution depth maps using RGB guidance for applications like robotics or AR, representing an incremental improvement over existing methods.

The paper tackles guided depth super-resolution by proposing a Joint Implicit Image Function (JIIF) that formulates the task as neural implicit image interpolation, outperforming state-of-the-art methods on three public benchmarks.

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}.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes