3 papers
cs.CV2026
:Scene-agnostic Visual Localization in the Wild
Yu Zhang, Muhua Zhu, Yifei Xue +2
Standard visual localization methods typically require offline pre-processing of scenes to obtain 3D structural information for better performance. This inevitably introduces addit…
cs.CV2026
VS3R: Robust Full-frame Video Stabilization via Deep 3D Reconstruction
Muhua Zhu, Xinhao Jin, Xinping Wang +4
Video stabilization aims to mitigate camera shake but faces a fundamental trade-off between geometric robustness and full-frame consistency. While 2D methods suffer from aggressive…
cs.CV2025
PIS3R: Very Large Parallax Image Stitching via Deep 3D Reconstruction
Muhua Zhu, Xinhao Jin, Chengbo Wang +4
Image stitching aim to align two images taken from different viewpoints into one seamless, wider image. However, when the 3D scene contains depth variations and the camera baseline…