IKEA-Manual: Seeing Shape Assembly Step by Step

Ruocheng Wang, Yunzhi Zhang, Jiayuan Mao, Ran Zhang, Chin-Yi Cheng, Jiajun Wu

Abstract: Human-designed visual manuals are crucial components in shape assembly activities. They provide step-by-step guidance on how we should move and connect different parts in a convenient and physically-realizable way. While there has been an ongoing effort in building agents that perform assembly tasks, the information in human-design manuals has been largely overlooked. We identify that this is due to 1) a lack of realistic 3D assembly objects that have paired manuals and 2) the difficulty of extracting structured information from purely image-based manuals. Motivated by this observation, we present IKEA-Manual, a dataset consisting of 102 IKEA objects paired with assembly manuals. We provide fine-grained annotations on the IKEA objects and assembly manuals, including decomposed assembly parts, assembly plans, manual segmentation, and 2D-3D correspondence between 3D parts and visual manuals. We illustrate the broad application of our dataset on four tasks related to shape assembly: assembly plan generation, part segmentation, pose estimationand 3D part assembly.

Author Statement: Yes

License: We licensed the annotations of visual manuals under CC BY-NC-SA 4.0. Copyright of the original visual manuals and 3D models are owned by their creators respectively.

Contribution Process Agreement: Yes

In Person Attendance: Yes

URL: https://cs.stanford.edu/~rcwang/projects/ikea_manual

Dataset Url: https://download.cs.stanford.edu/viscam/ikea_manual/dataset.zip