Shiyu Ning — accepted AI-conference papers

2021

PENet: Towards Precise and Efficient Image Guided Depth Completion

Mu Hu, Shuling Wang, Bin Li, Shiyu Ning, Li Fan, Xiaojin Gong

ICRA 2021poster

Image guided depth completion is the task of generating a dense depth map from a sparse depth map and a high quality image. In this task, how to fuse the color and depth modalities plays an important role in achieving good performance. This paper proposes a two-branch backbone that consists of a col…

Cited by 369 Source ↗code ↗Scholar ↗

2018

Learning an Inverse Tone Mapping Network with a Generative Adversarial Regularizer

Shiyu Ning, Hongteng Xu, Li Song, Rong Xie, Wenjun Zhang

ICASSP 2018accepted

Transferring a low-dynamic-range (LDR) image to a high-dynamic-range (HDR) image, which is the so-called inverse tone mapping (iTM), is an important imaging technique to improve visual effects of imaging devices. In this paper, we propose a novel deep learning-based iTM method, which learns an inver…

Cited by 0 Source ↗Scholar ↗