AutoSweep: Recovering 3D Editable Objectsfrom a Single Photograph
This addresses the challenge of creating editable 3D models from images for applications in computer graphics and design, representing an incremental advance over prior depth or mesh recovery methods.
The paper tackles the problem of automatically extracting editable 3D objects from a single photograph by recovering semantic parts represented as generalized primitives, resulting in high-quality 3D models that outperform existing methods in instance segmentation and 3D reconstruction.
This paper presents a fully automatic framework for extracting editable 3D objects directly from a single photograph. Unlike previous methods which recover either depth maps, point clouds, or mesh surfaces, we aim to recover 3D objects with semantic parts and can be directly edited. We base our work on the assumption that most human-made objects are constituted by parts and these parts can be well represented by generalized primitives. Our work makes an attempt towards recovering two types of primitive-shaped objects, namely, generalized cuboids and generalized cylinders. To this end, we build a novel instance-aware segmentation network for accurate part separation. Our GeoNet outputs a set of smooth part-level masks labeled as profiles and bodies. Then in a key stage, we simultaneously identify profile-body relations and recover 3D parts by sweeping the recognized profile along their body contour and jointly optimize the geometry to align with the recovered masks. Qualitative and quantitative experiments show that our algorithm can recover high quality 3D models and outperforms existing methods in both instance segmentation and 3D reconstruction. The dataset and code of AutoSweep are available at https://chenxin.tech/AutoSweep.html.