Learning 3D Part Assembly from a Single Image
| Autor: | Leonidas J. Guibas, Lin Shao, Kaichun Mo, Yichen Li, Minhyuk Sung |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
business.industry
Computer science 020207 software engineering Robotics 02 engineering and technology Pipeline (software) Task (project management) Human–computer interaction Obstacle avoidance 0202 electrical engineering electronic engineering information engineering Benchmark (computing) Robot Graph (abstract data type) 020201 artificial intelligence & image processing Motion planning Artificial intelligence business |
| Zdroj: | Computer Vision – ECCV 2020 ISBN: 9783030585389 ECCV (6) |
| Popis: | Autonomous assembly is a crucial capability for robots in many applications. For this task, several problems such as obstacle avoidance, motion planning, and actuator control have been extensively studied in robotics. However, when it comes to task specification, the space of possibilities remains underexplored. Towards this end, we introduce a novel problem, single-image-guided 3D part assembly, along with a learning-based solution. We study this problem in the setting of furniture assembly from a given complete set of parts and a single image depicting the entire assembled object. Multiple challenges exist in this setting, including handling ambiguity among parts (e.g., slats in a chair back and leg stretchers) and 3D pose prediction for parts and part subassemblies, whether visible or occluded. We address these issues by proposing a two-module pipeline that leverages strong 2D-3D correspondences and assembly-oriented graph message-passing to infer part relationships. In experiments with a PartNet-based synthetic benchmark, we demonstrate the effectiveness of our framework as compared with three baseline approaches (code and data available at https://github.com/AntheaLi/3DPartAssembly). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|