Yanfei Su
Nanchang University
6 Papers
Yanfei Su is an academic researcher from Nanchang University. The author has contributed to research in topics: Computer science & Image registration. The author has an hindex of 1, co-authored 1 publications.
Chat about Author
Papers
Remote Sensing Image Registration Using Convolutional Neural Network Features
TL;DR: This letter investigates how to calculate the CNN feature, and study the way to fuse SIFT and CNN features for remote sensing image registration, demonstrating that the proposed method yields a better registration performance in terms of both the aligning accuracy and the number of correct correspondences.
141
Category-Level Adversaries for Outdoor LiDAR Point Clouds Cross-Domain Semantic Segmentation
TL;DR: In this article , a multi-scale domain conditioned block is proposed to extract the critical low-level domain-dependent knowledge and reduce the domain gap caused by distinct LiDAR sampling patterns.
7
Multi-stage Scene-level Constraints for Large-scale Point Cloud Weakly Supervised Semantic Segmentation
Yanfei Su,Ming Cheng,Zhimin Yuan,Weiquan Liu,Wankang Zeng,Cheng Wang +5 more
TL;DR: An effective and generalized weakly supervised semantic segmentation framework, called multistage scene-level constraints (MSCs), is proposed to solve the issue regarding inadequate labeled data and an uncertainty-guided adaptive reweighting strategy to reduce the negative impact of erroneous pseudo-labeled data on the model learning process.
5
Spatial Adaptive Fusion Consistency Contrastive Constraint: Weakly Supervised Building Facade Point Cloud Semantic Segmentation
Yanfei Su,Ming Cheng,Zhimin Yuan,Weiquan Liu,Wankang Zeng,Zhihong Zhang,Cheng Wang +6 more
TL;DR: This article designs a multirandom point cloud augmentor as an auxiliary supervision branch to enhance the learning ability of the original network branch, and presents a spatial adaptive fusion (SAF) module to extract discriminative features for building facade point clouds.
4
Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Clouds
Zhimin Yuan,Wankang Zeng,Yanfei Su,Weiquan Liu,Ming Cheng,Yulan Guo,Cheng Wang +6 more
TL;DR: Density-guided translator boosts synthetic-to-real unsupervised domain adaptive segmentation by bridging the domain gap at the input level and improving self-training strategies.