From the 1 of 13 linked papers with an AI index.
1 citations · 1 across the 6 of their papers we have counts for
13 papers
Panoramic Scene Understanding: A Survey from Distortion-Aware Engineering to Sphere-Native Modeling
Qinfeng Zhu, Lei Fan
The paper surveys methods for understanding panoramic images, covering techniques that handle projection distortions, sphere-native models, and adaptations of pretrained vision fou…
SO3UFormer: Learning Intrinsic Spherical Features for Rotation-Robust Panoramic Dense Prediction
Qinfeng Zhu, Yunxi Jiang, Lei Fan
Panoramic dense-prediction models, spanning semantic segmentation and depth estimation, are typically trained under a strict gravity-aligned assumption. Real-world captures, howeve…
A generalised pre-training strategy for deep learning networks in semantic segmentation of remotely sensed images
Yuan Fang, Yuanzhi Cai, Jagannath Aryal +4
In the segmentation of remotely sensed images, deep learning models are typically pre-trained using large image databases like ImageNet before fine-tuned on domain-specific dataset…
WFST Astrometric Calibration -- I. Modeling Global Geometric Distortion with Zernike Polynomials
Chao Yang, Min Fang, Xian Zhong Zheng +21
Accurate modeling of geometric distortion is essential for precise astrometric calibration in wide-field imaging surveys. We present a self-calibration method based on Zernike poly…
From Landslide Conditioning Factors to Satellite Embeddings: Evaluating the Utilisation of Google AlphaEarth for Landslide Susceptibility Mapping using Deep Learning
Yusen Cheng, Qinfeng Zhu, Lei Fan
Data-driven landslide susceptibility mapping (LSM) typically relies on landslide conditioning factors (LCFs), whose availability, heterogeneity, and preprocessing-related uncertain…
ClassWise-CRF: Category-Specific Fusion for Enhanced Semantic Segmentation of Remote Sensing Imagery
Qinfeng Zhu, Yunxi Jiang, Lei Fan
We propose a result-level category-specific fusion architecture called ClassWise-CRF. This architecture employs a two-stage process: first, it selects expert networks that perform…