research area Computer Vision, research area Methods and Algorithmsconference CVPR
content type paperpublished March 2023

MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices

In collaboration with University of Oxford

AuthorsKejie Li, Jia-Wang Bian, Robert Castle, Philip H.S. Torr, Victor Adrian Prisacariu

View publication

View source code (GitHub)

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.

Video 1: A selection of captures and ground truth models from the dataset.

Video 2: An example showing the quality of ground truth shape alignment to the image sequence by projecting the 3D model to the RGB images (shown as '3D Model Projection'). 'GT depth' is the depth maps rendered from the 3D model at the same viewpoint. 'RGB Image' and 'ARKit Depth' are the high-res RGB images and low-res depth maps provided by ARKit.

Related readings and updates.

DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models

January 18, 2025research area Computer Vision

Generating high-quality 3D content requires models capable of learning robust distributions of complex scenes and the real-world objects within them. Recent Gaussian-based 3D reconstruction techniques have achieved impressive results in recovering high-fidelity 3D assets from sparse input images by predicting 3D Gaussians in a feed-forward manner. However, these techniques often lack the extensive priors and expressiveness offered by Diffusion…

Read more

FineRecon: Depth-aware Feed-forward Network for Detailed 3D Reconstruction

August 16, 2023research area Computer Visionconference ICCV

Recent works on 3D reconstruction from posed images have demonstrated that direct inference of scene-level 3D geometry without iterative optimization is feasible using a deep neural network, showing remarkable promise and high efficiency. However, the reconstructed geometries, typically represented as a 3D truncated signed distance function (TSDF), are often coarse without fine geometric details. To address this problem, we propose three…

Read more