18 Papers
11 Citations
Ru Li is an academic researcher from University of Electronic Science and Technology of China. The author has contributed to research in topics: Computer science & Image fusion. The author has an hindex of 3, co-authored 14 publications. Previous affiliations of Ru Li include China University of Petroleum.
Chat about Author
Papers
SDP-GAN: Saliency Detail Preservation Generative Adversarial Networks for High Perceptual Quality Style Transfer
TL;DR: The paper introduces a saliency network, which is trained with the generator simultaneously, providing constraints for content loss to increase punishment for salient regions, and supplying saliency features to generator to produce coherent results.
36
Quadratic Terms based Point-to-Surface 3D Representation for Deep Learning of Point Cloud
TL;DR: The point-to-surface representation is introduced, a new representation for 3D point cloud learning that has not been attempted before, which can assemble local and global geometric information effectively by building connections between the point cloud and the learned reference surfaces.
23
•Posted Content
UPHDR-GAN: Generative Adversarial Network for High Dynamic Range Imaging with Unpaired Data.
TL;DR: UPHDR-GAN as mentioned in this paper proposes a GAN-based network for solving the ghosting artifacts caused by moving objects or misalignments with the help of modified GAN loss, improved discriminator network and useful initialization phase.
20
SIRA-PCR: Sim-to-Real Adaptation for 3D Point Cloud Registration
Suyi Chen,Hao Xu,Ru Li,Guanghui Liu,Chi-Wing Fu,Shuaicheng Liu +5 more
- 01 Oct 2023
TL;DR: This work designs SIRA-PCR, a new approach to 3D point cloud registration that explores sim-to-real adaptation for point cloud registration, and builds a synthetic scene-level 3D registration dataset specifically designed with physically-based and random strategies to arrange diverse objects.
8
Photomontage for Robust HDR Imaging with Hand-Held Cameras
Ru Li,Xiaowu He,Shuaicheng Liu,Guanghui Liu,Bing Zeng +4 more
- 01 Oct 2018
TL;DR: This paper proposes to use a Markov Random Filed function for the labelling of all pixels, which assigns different labels to different aligned input images, and combines a Laplace image according to the labels and construct the fusion result by solving the Poisson equation.
6