MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices
Authors:
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4892-4901
Abstract
High-quality 3D ground-truth shapes are critical for 3D object reconstruction evaluation. However, it is difficult to create a replica of an object in reality, and even 3D reconstructions generated by 3D scanners have artefacts that cause biases in evaluation. To address this issue, we introduce a novel multi-view RGBD dataset captured using a mobile device, which includes highly precise 3D ground-truth annotations for 153 object models featuring a diverse set of 3D structures. We obtain precise 3D ground-truth shape without relying on high-end 3D scanners by utilising LEGO models with known geometry as the 3D structures for image capture. The distinct data modality offered by high-resolution RGB images and low-resolution depth maps captured on a mobile device, when combined with precise 3D geometry annotations, presents a unique opportunity for future research on high-fidelity 3D reconstruction. Furthermore, we evaluate a range of 3D reconstruction algorithms on the proposed dataset.Keywords
All Related Versions
Funding Information
- UKRI (EP/W002981/1)
- EPSRC
- MURI (EP/N019474/1)
- Royal Academy of Engineering
This publication has 27 references indexed in Scilit:
- Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation2019
- Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling2018
- Matterport3D: Learning from RGB-D Data in Indoor Environments2017
- Tanks and templesACM Transactions on Graphics, 2017
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes2017
- Structure-from-Motion Revisited2016
- Large Scale Multi-view Stereopsis Evaluation2014
- Beyond PASCAL: A benchmark for 3D object detection in the wild2014
- KinectFusion: Real-time dense surface mapping and tracking2011
- MonoSLAM: Real-Time Single Camera SLAMIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007