CVLGMar 3, 2023

MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices

ByteDanceOxford
arXiv:2303.01932v216 citationsh-index: 117
Originality Synthesis-oriented
AI Analysis

This provides a new benchmark for 3D reconstruction research, particularly for mobile applications, though it is incremental as it builds on existing dataset creation methods.

The authors tackled the problem of lacking high-quality 3D ground-truth shapes for evaluating 3D object reconstruction by introducing a novel multi-view RGBD dataset captured on a mobile device, which includes precise 3D annotations for 153 LEGO models, enabling evaluation of various algorithms.

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. Project page: http://code.active.vision/MobileBrick/

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes