 This paper presents a novel two-stage approach called Fusion RCNN which combines LiDAR and camera data to improve the performance of 3D object detection. The proposed method uses a unified attention mechanism to integrate the sparse geometry information from LiDAR and dense texture information from cameras. Experiments show that Fusion RCNN significantly boosts the performance of existing detectors and now performs other two-stage approaches. This article was authored by Sheenli Su, Xiaotsong Dong, Tingfa Su, and others.