4 papers
: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…
DisorientLiDAR: Physical Attacks on LiDAR-based Localization
Yizhen Lao, Yu Zhang, Ziting Wang +3
Deep learning models have been shown to be susceptible to adversarial attacks with visually imperceptible perturbations. Even this poses a serious security challenge for the locali…
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…
Faster and Better 3D Splatting via Group Training
Chengbo Wang, Guozheng Ma, Yifei Xue +1
3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, demonstrating remarkable capability in high-fidelity scene reconstruction through its Gau…