1 citations · 1 across the 9 of their papers we have counts for
8 papers · 1 filter
Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction
Weijian Chen, Weibo Yao, Yuhang Zhang +7
Scaling 3D Gaussian Splatting (3DGS) to large outdoor scenes is costly in both data acquisition and computation. Adopting panoramic images with equirectangular projection (ERP) can…
VReID-XFD: Video-based Person Re-identification at Extreme Far Distance Challenge Results
Kailash A. Hambarde, Hugo Proença, Md Rashidunnabi +18
Person re-identification (ReID) across aerial and ground views at extreme far distances introduces a distinct operating regime where severe resolution degradation, extreme viewpoin…
Multi-level distortion-aware deformable network for omnidirectional image super-resolution
Cuixin Yang, Rongkang Dong, Kin-Man Lam +2
As augmented reality and virtual reality applications gain popularity, image processing for OmniDirectional Images (ODIs) has attracted increasing attention. OmniDirectional Image…
AirSim360: A Panoramic Simulation Platform within Drone View
Xian Ge, Yuling Pan, Yuhang Zhang +12
The field of 360-degree omnidirectional understanding has been receiving increasing attention for advancing spatial intelligence. However, the lack of large-scale and diverse data…
Curriculum Prompting Foundation Models for Medical Image Segmentation
Xiuqi Zheng, Yuhang Zhang, Haoran Zhang +4
Adapting large pre-trained foundation models, e.g., SAM, for medical image segmentation remains a significant challenge. A crucial step involves the formulation of a series of spec…
UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding
Bowen Shi, Peisen Zhao, Zichen Wang +8
Vision-language foundation models, represented by Contrastive Language-Image Pre-training (CLIP), have gained increasing attention for jointly understanding both vision and textual…
DeLR: Active Learning for Detection with Decoupled Localization and Recognition Query
Yuhang Zhang, Yuang Deng, Xiaopeng Zhang +3
Active learning has been demonstrated effective to reduce labeling cost, while most progress has been designed for image recognition, there still lacks instance-level active learni…
Investigating the Robustness and Properties of Detection Transformers (DETR) Toward Difficult Images
Zhao Ning Zou, Yuhang Zhang, Robert Wijaya
Transformer-based object detectors (DETR) have shown significant performance across machine vision tasks, ultimately in object detection. This detector is based on a self-attention…