Inferring Point Clouds from Single Monocular Images by Depth Intermediation
This addresses the problem of 3D object reconstruction from limited data for applications like robotics or AR, but it is incremental as it builds on existing depth and completion techniques.
The paper tackles 3D point cloud generation from single-view RGB images by decomposing it into depth estimation and point cloud completion, outperforming state-of-the-art methods in reconstruction tasks.
In this paper, we propose a pipeline to generate 3D point cloud of an object from a single-view RGB image. Most previous work predict the 3D point coordinates from single RGB images directly. We decompose this problem into depth estimation from single images and point cloud completion from partial point clouds. Our method sequentially predicts the depth maps from images and then infers the complete 3D object point clouds based on the predicted partial point clouds. We explicitly impose the camera model geometrical constraint in our pipeline and enforce the alignment of the generated point clouds and estimated depth maps. Experimental results for the single image 3D object reconstruction task show that the proposed method outperforms existing state-of-the-art methods. Both the qualitative and quantitative results demonstrate the generality and suitability of our method.