← Search

Zhongyu Huang

2 accepted papers

2025

G-Depth: An Efficient Graph Method for Robust Depth Completion

ICASSP 2025accepted

Depth completion has played a vital role in enhancing depth perception in various applications such as autonomous driving, robotics, and 3D reconstruction. It is a critical task that involves generating a dense depth map from an RGB image and an aligned sparse depth map. However, many existing studi…

Cited by 0SourceScholar
2022

Going Deeper into Permutation-Sensitive Graph Neural Networks

ICML 2022spotlight

The invariance to permutations of the adjacency matrix, i.e., graph isomorphism, is an overarching requirement for Graph Neural Networks (GNNs). Conventionally, this prerequisite can be satisfied by the invariant operations over node permutations when aggregating messages. However, such an invariant…