Incorporating sparse model machine learning in designing cultural heritage landscapes
Managing, protecting, and the evolutionary development of historical landscapes require
robust frameworks and processes for forming datasets and advanced decision support tools …
robust frameworks and processes for forming datasets and advanced decision support tools …
MS2Net: Multi-scale and multi-stage feature fusion for blurred image super-resolution
At present, most mainstream algorithms for single image super-resolution (SISR) assume
the image degradation process as an ideal degradation process (eg bicubic downscaling) …
the image degradation process as an ideal degradation process (eg bicubic downscaling) …
Self-supervised monocular depth estimation with frequency-based recurrent refinement
Self-supervised monocular depth estimation has succeeded in learning scene geometry
from only image pairs or sequences. However, it is still highly ill-posed for self-supervised …
from only image pairs or sequences. However, it is still highly ill-posed for self-supervised …
GRAN: ghost residual attention network for single image super resolution
Recently, many works have designed wider and deeper networks to achieve higher image
super-resolution performance. Despite their outstanding performance, they still suffer from …
super-resolution performance. Despite their outstanding performance, they still suffer from …
Triplet relationship guided sampling consensus for robust model estimation
RANSAC (RANdom SAmple Consensus) is a widely used robust estimator for estimating a
geometric model from feature matches in an image pair. Unfortunately, it becomes less …
geometric model from feature matches in an image pair. Unfortunately, it becomes less …
SCSA-Net: Presentation of two-view reliable correspondence learning via spatial-channel self-attention
Seeking reliable correspondences between pairwise images is non-trivial in feature
matching. In this paper, we propose a novel network, called the Spatial-Channel Self …
matching. In this paper, we propose a novel network, called the Spatial-Channel Self …
Trinocular camera self-calibration based on spatio-temporal multi-layer optimization
X Tian, Q Gao, Q Luo, J Feng - Measurement, 2023 - Elsevier
In stereo vision systems with dynamically rotating cameras, the accuracy of camera self-
calibration method is reduced due to the interference of space noise and mismatched …
calibration method is reduced due to the interference of space noise and mismatched …
RANet: A relation-aware network for two-view correspondence learning
Finding true correspondences from a set of putative correspondences is a basic task in
computer vision. Recent advances have demonstrated that Multi Layer Perceptrons (MLPs) …
computer vision. Recent advances have demonstrated that Multi Layer Perceptrons (MLPs) …
Robust multi-model fitting via neighborhood graph structure consistency
H Guo, J Zhao, W Liu, D Yang, C Zhou, G Lin… - Digital Signal …, 2024 - Elsevier
Recently, some graph-based methods have been proposed for multi-model fitting. These
methods usually construct full-connected graphs between any pairs of data for model fitting …
methods usually construct full-connected graphs between any pairs of data for model fitting …
一种结合局部与半全局几何保持的影像匹配算法
郑美艳， 陈俊， 葛小青， 张红 - 中国科学院大学学报, 2022 - journal.ucas.ac.cn
遥感影像匹配是众多遥感应用中数据处理的关键前置步骤, 但高程差导致的影像局部畸变和影像
匹配的复杂性严重限制了高分辨率影像的匹配精度. 本文提出一种适用于局部畸变和高外点比例 …
匹配的复杂性严重限制了高分辨率影像的匹配精度. 本文提出一种适用于局部畸变和高外点比例 …