Discovering 3D Parts from Image Collections
This addresses the challenge of 3D shape reasoning from single-view images for computer vision applications, offering a novel self-supervised approach that is incremental in improving part discovery without relying on labeled data.
The paper tackles the problem of discovering 3D parts from 2D image collections without manual annotations, proposing a self-supervised method that learns a part shape prior to achieve consistent part discovery and favorable reconstruction accuracy on synthetic and real-world datasets.
Reasoning 3D shapes from 2D images is an essential yet challenging task, especially when only single-view images are at our disposal. While an object can have a complicated shape, individual parts are usually close to geometric primitives and thus are easier to model. Furthermore, parts provide a mid-level representation that is robust to appearance variations across objects in a particular category. In this work, we tackle the problem of 3D part discovery from only 2D image collections. Instead of relying on manually annotated parts for supervision, we propose a self-supervised approach, latent part discovery (LPD). Our key insight is to learn a novel part shape prior that allows each part to fit an object shape faithfully while constrained to have simple geometry. Extensive experiments on the synthetic ShapeNet, PartNet, and real-world Pascal 3D+ datasets show that our method discovers consistent object parts and achieves favorable reconstruction accuracy compared to the existing methods with the same level of supervision.