Recovering Detail in 3D Shapes Using Disparity Maps
This addresses the challenge of recovering detail in 3D shapes for applications like computer vision and graphics, but it appears incremental as it builds on existing monocular depth estimation methods.
The paper tackles the problem of improving 3D geometry reconstruction from single images by fine-tuning with disparity maps, resulting in more faithful and detailed final geometries as demonstrated on synthetic and real images.
We present a fine-tuning method to improve the appearance of 3D geometries reconstructed from single images. We leverage advances in monocular depth estimation to obtain disparity maps and present a novel approach to transforming 2D normalized disparity maps into 3D point clouds by using shape priors to solve an optimization on the relevant camera parameters. After creating a 3D point cloud from disparity, we introduce a method to combine the new point cloud with existing information to form a more faithful and detailed final geometry. We demonstrate the efficacy of our approach with multiple experiments on both synthetic and real images.