Learning to Generate Dense Point Clouds with Textures on Multiple Categories
This addresses the challenge of obtaining detailed geometry and texture for objects with arbitrary topology in computer vision, representing an incremental improvement over existing methods.
The paper tackles the problem of 3D reconstruction from single RGB images by proposing a method that recovers dense point clouds with textures across multiple categories, achieving superior generalization to unseen categories compared to previous techniques.
3D reconstruction from images is a core problem in computer vision. With recent advances in deep learning, it has become possible to recover plausible 3D shapes even from single RGB images for the first time. However, obtaining detailed geometry and texture for objects with arbitrary topology remains challenging. In this paper, we propose a novel approach for reconstructing point clouds from RGB images. Unlike other methods, we can recover dense point clouds with hundreds of thousands of points, and we also include RGB textures. In addition, we train our model on multiple categories which leads to superior generalization to unseen categories compared to previous techniques. We achieve this using a two-stage approach, where we first infer an object coordinate map from the input RGB image, and then obtain the final point cloud using a reprojection and completion step. We show results on standard benchmarks that demonstrate the advantages of our technique. Code is available at https://github.com/TaoHuUMD/3D-Reconstruction.