This repo contains the source code and prediction saliency maps of our RD3D and RD3D+. The latter is an extension of the former, which is lighter and more computationally efficient and accurate. 🔥 ...
Abstract: In recent years, much achievement have been made in the field of 3D clothed human reconstruction. However, most of researches performed not well for reconstruction from in-the-wild images ...
Abstract: Achieving robust 3D object detection by fusing images and point clouds remains challenging. In this paper, we propose a novel 3D object detector (SimpleFusion) that enables simple and ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results