activity
20202026
most citedNuSegDG: Integration of Heterogeneous Space and Gaussian Kernel for Domain-Generalized Nuclei Segmentation

9 citations · 27 across the 20 of their papers we have counts for

collaborators
Showing 2025 · cs.CVShow all

10 papers · 2 filters

cs.CV2025

MetaScope: Optics-Driven Neural Network for Ultra-Micro Metalens Endoscopy

Wuyang Li, Wentao Pan, Xiaoyuan Liu +6

Miniaturized endoscopy has advanced accurate visual perception within the human body. Prevailing research remains limited to conventional cameras employing convex lenses, where the…

cs.CV2025

WonderFree: Enhancing Novel View Quality and Cross-View Consistency for 3D Scene Exploration

Chaojun Ni, Jie Li, Haoyun Li +8

Interactive 3D scene generation from a single image has gained significant attention due to its potential to create immersive virtual worlds. However, a key challenge in current 3D…

cs.CV2025

Track Any Anomalous Object: A Granular Video Anomaly Detection Pipeline

Yuzhi Huang, Chenxin Li, Haitao Zhang +9

Video anomaly detection (VAD) is crucial in scenarios such as surveillance and autonomous driving, where timely detection of unexpected activities is essential. Although existing m…

cs.CV2025

FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting

Hengyu Liu, Yuehao Wang, Chenxin Li +6

3D Gaussian splatting (3DGS) has enabled various applications in 3D scene representation and novel view synthesis due to its efficient rendering capabilities. However, 3DGS demands…

cs.CV2025★ 2 cited

Towards a general-purpose foundation model for fMRI analysis

Cheng Wang, Yu Jiang, Zhihao Peng +18

Functional MRI (fMRI) is crucial for studying brain function and diagnosing neurological disorders. However, existing analysis methods suffer from reproducibility and transferabili…

cs.CV2025

MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models

Yifan Liu, Keyu Fan, Weihao Yu +3

Recent advances in generalizable 3D Gaussian Splatting have demonstrated promising results in real-time high-fidelity rendering without per-scene optimization, yet existing approac…