AI RESEARCH

Towards Accurate Single Panoramic 3D Detection: A Semantic Gaussian Centric Approach

arXiv CS.CV

ArXi:2605.14601v1 Announce Type: new Three-dimensional object detection in panoramic imagery is crucial for comprehensive scene understanding, yet accurately mapping 2D features to 3D remains a significant challenge. Prevailing methods often project 2D features onto discrete 3D grids, which break geometric continuity and limit representation efficiency. To overcome this limitation, this paper proposes PanoGSDet, a monocular panoramic 3D detection framework built upon continuous semantic 3D Gaussian representations.