赞
踩
paper:CVPR 2021 Open Access Repositoryhttps://openaccess.thecvf.com/content/CVPR2021/html/Wang_Depth-Conditioned_Dynamic_Message_Propagation_for_Monocular_3D_Object_Detection_CVPR_2021_paper.html
code:GitHub - fudan-zvg/DDMP: [CVPR 2021] Depth-conditioned Dynamic Message Propagation forMonocular 3D Object Detectionhttps://github.com/fudan-zvg/DDMP
精度对比:KITTI Cars Moderate Benchmark (Monocular 3D Object Detection) | Papers With Codehttps://paperswithcode.com/sota/monocular-3d-object-detection-on-kitti-cars
实现:
思想和双目视差估计的AAnet比较像,基本上就是deformable conv那一套