Recent progress in 3D Gaussian Splatting (3DGS) has enabled dense visual SLAM with pinhole cameras, yet most pipelines are not designed for panoramic imagery. We present Cube-Splat, the first panoramic GS-SLAM framework that factorizes each 360{\deg} frame into a cubemap of four fixed-orientation virtual pinhole views...
Xiang-Fei Guo, Hao-Wen Shi, Yufan Zhang et al.· 0 citations
Real-time dense SLAM is a core capability for robotics applications that require robust localization and high- quality mapping in dynamic or fast-changing environments. Recent 3D Gaussian Splatting (3DGS)-based SLAM methods have shown promising performance, but most are designed for narrow-FoV pinhole cameras, where li...
Yong-Qi Mao, Hao-Wen Shi, Yu-Fan Zhang et al.· 0 citations
Manifold4D is proposed, which injects the render directly into the initial noise of flow matching, so that generation no longer departs from standard Gaussian noise but from a geometry-bearing noise distribution that is term the point cloud rendered manifold, leaving the source video as the only visual condition.
Yongbo Mao, Zijia Dai, Zhi-Shu Liu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.