Visual Enhanced 3D Point Cloud Reconstruction from A Single Image
This work addresses the challenge of generating visually satisfactory 3D reconstructions from monocular images, which is incremental as it builds on existing deep learning methods by refining the loss function.
The paper tackles the problem of 3D point cloud reconstruction from a single image by addressing the limitations of Chamfer loss, which sacrifices fine-grained structures, and proposes a framework that focuses on boundaries to recover detailed point clouds, resulting in significant qualitative and quantitative improvements with fewer training parameters.
Solving the challenging problem of 3D object reconstruction from a single image appropriately gives existing technologies the ability to perform with a single monocular camera rather than requiring depth sensors. In recent years, thanks to the development of deep learning, 3D reconstruction of a single image has demonstrated impressive progress. Existing researches use Chamfer distance as a loss function to guide the training of the neural network. However, the Chamfer loss will give equal weights to all points inside the 3D point clouds. It tends to sacrifice fine-grained and thin structures to avoid incurring a high loss, which will lead to visually unsatisfactory results. This paper proposes a framework that can recover a detailed three-dimensional point cloud from a single image by focusing more on boundaries (edge and corner points). Experimental results demonstrate that the proposed method outperforms existing techniques significantly, both qualitatively and quantitatively, and has fewer training parameters.