3D Object Reconstruction
61 papers with code • 4 benchmarks • 7 datasets
Image: Choy et al
Benchmarks
These leaderboards are used to track progress in 3D Object Reconstruction
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find 3D Object Reconstruction models and implementationsDatasets
ShapeNet
BEHAVE
X3D
Parcel3D
A collection of 131 CT datasets of pieces of modeling clay containing stones
Corn Seeds Dataset
Latest papers
CAD-Estate: Large-scale CAD Model Annotation in RGB Videos
google-research/cad-estate
•
•
ICCV 2023
We propose a method for annotating videos of complex multi-object scenes with a globally-consistent 3D representation of the objects.
MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices
ActiveVisionLab/MobileBrick
•
•
CVPR 2023
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.
UMIFormer: Mining the Correlations between Similar Tokens for Multi-View 3D Reconstruction
garyzhu1996/umiformer
•
•
ICCV 2023
We empirically demonstrate on ShapeNet and confirm that our decoupled learning method is adaptable for unstructured multiple images.
Single-view 3D Mesh Reconstruction for Seen and Unseen Categories
Wi-sc/GenMesh
•
•
Single-view 3D object reconstruction is a fundamental and challenging computer vision task that aims at recovering 3D shapes from single-view RGB images.
Monocular 3D Object Reconstruction with GAN Inversion
junzhezhang/mesh-inversion
•
•
Reconstruction is achieved by searching for a latent space in the 3D GAN that best resembles the target mesh in accordance with the single view observation.
Self-calibrating Photometric Stereo by Neural Inverse Rendering
This paper tackles the task of uncalibrated photometric stereo for 3D object reconstruction, where both the object shape, object reflectance, and lighting directions are unknown.
Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency
monniert/unicorn
•
•
Approaches for single-view reconstruction typically rely on viewpoint annotations, silhouettes, the absence of background, multiple views of the same instance, a template shape, or symmetry.
CHORE: Contact, Human and Object REconstruction from a single RGB image
xiexh20/CHORE
•
•
However, humans are constantly interacting with the surrounding objects, thus calling for models that can reason about not only the human but also the object and their interaction.
Neural Face Identification in a 2D Wireframe Projection of a Manifold Object
manycore-research/faceformer
•
•
CVPR 2022
In computer-aided design (CAD) systems, 2D line drawings are commonly used to illustrate 3D object designs.
Phase-SLAM: Phase Based Simultaneous Localization and Mapping for Mobile Structured Light Illumination Systems
In this paper, we propose a phase based Simultaneous Localization and Mapping (Phase-SLAM) framework for fast and accurate SLI sensor pose estimation and 3D object reconstruction.
