Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling
This work addresses the problem of limited and poorly aligned datasets for 3D shape tasks, providing a resource for researchers in computer vision and graphics.
The authors tackled 3D shape modeling from single images by introducing Pix3D, a large-scale benchmark with pixel-level alignment, and a novel multi-task model that achieved state-of-the-art performance in 3D reconstruction and pose estimation.
We study 3D shape modeling from a single image and make contributions to it in three aspects. First, we present Pix3D, a large-scale benchmark of diverse image-shape pairs with pixel-level 2D-3D alignment. Pix3D has wide applications in shape-related tasks including reconstruction, retrieval, viewpoint estimation, etc. Building such a large-scale dataset, however, is highly challenging; existing datasets either contain only synthetic data, or lack precise alignment between 2D images and 3D shapes, or only have a small number of images. Second, we calibrate the evaluation criteria for 3D shape reconstruction through behavioral studies, and use them to objectively and systematically benchmark cutting-edge reconstruction algorithms on Pix3D. Third, we design a novel model that simultaneously performs 3D reconstruction and pose estimation; our multi-task learning approach achieves state-of-the-art performance on both tasks.