AutoSweep: Recovering 3D Editable Objectsfrom a Single Photograph

TL;DR

AutoSweep is an automatic method that reconstructs editable 3D objects with semantic parts from a single photograph, focusing on primitive shapes like cuboids and cylinders, enabling direct editing.

Contribution

It introduces a novel instance-aware segmentation network and a joint optimization process for recovering 3D objects with semantic parts from a single image.

Findings

Outperforms existing methods in segmentation and reconstruction quality

Successfully recovers high-quality 3D models with semantic parts

Effective for objects composed of generalized cuboids and cylinders

Abstract

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.