SOTAVerified

3D Reconstruction

3D Reconstruction is the task of creating a 3D model or representation of an object or scene from 2D images or other data sources. The goal of 3D reconstruction is to create a virtual representation of an object or scene that can be used for a variety of purposes, such as visualization, animation, simulation, and analysis. It can be used in fields such as computer vision, robotics, and virtual reality.

Image: Gwak et al

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2151–2200 of 2326 papers

TitleStatusHype
Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying LightingCode0
A Learning-based Framework for Hybrid Depth-from-Defocus and Stereo Matching—0
InfiniTAM v3: A Framework for Large-Scale 3D Reconstruction with Loop ClosureCode0
3D Sketching using Multi-View Deep Volumetric Prediction—0
Compact Model Representation for 3D Reconstruction—0
3D Shape Reconstruction from Sketches via Multi-view Convolutional NetworksCode0
"Maximizing rigidity" revisited: a convex programming approach for generic 3D shape reconstruction from multiple perspective views—0
LabelFusion: A Pipeline for Generating Ground Truth Labels for Real RGBD Data of Cluttered ScenesCode0
Pixel-variant Local Homography for Fisheye Stereo Rectification Minimizing Resampling Distortion—0
Fast 3D Reconstruction of Faces With Glasses—0
Semantic Multi-View Stereo: Jointly Estimating Objects and Voxels—0
Semantically Coherent Co-Segmentation and Reconstruction of Dynamic Scenes—0
KillingFusion: Non-Rigid 3D Reconstruction Without Correspondences—0
Stereo-Based 3D Reconstruction of Dynamic Fluid Surfaces by Global Optimization—0
An Efficient Background Term for 3D Reconstruction and Tracking With Smooth Surface Models—0
DUST: Dual Union of Spatio-Temporal Subspaces for Monocular Multiple Object 3D Reconstruction—0
Semi-Calibrated Near Field Photometric Stereo—0
Predicting Behaviors of Basketball Players From First Person Videos—0
Polarimetric Multi-View Stereo—0
A Practical Method for Fully Automatic Intrinsic Camera Calibration Using Directionally Encoded Light—0
Face Normals "In-The-Wild" Using Fully Convolutional Networks—0
Semantically Informed Multiview Surface Refinement—0
A comparative study of breast surface reconstruction for aesthetic outcome assessment—0
Superhuman Accuracy on the SNEMI3D Connectomics ChallengeCode0
Weakly supervised 3D Reconstruction with Adversarial ConstraintCode0
A fully dense and globally consistent 3D map reconstruction approach for GI tract to enhance therapeutic relevance of the endoscopic capsule robot—0
Learning a Hierarchical Latent-Variable Model of 3D ShapesCode0
Intel RealSense Stereoscopic Depth CamerasCode0
Back to RGB: 3D tracking of hands and hand-object interactions based on short-baseline stereo—0
Spatial-Temporal Union of Subspaces for Multi-body Non-rigid Structure-from-Motion—0
A Correspondence Relaxation Approach for 3D Shape Reconstruction—0
CAD Priors for Accurate and Flexible Instance Reconstruction—0
Machine Vision System for 3D Plant Phenotyping—0
Joint Layout Estimation and Global Multi-View Registration for Indoor Reconstruction—0
Towards Large-Pose Face Frontalization in the Wild—0
OctNetFusion: Learning Depth Fusion from DataCode0
Dense Multi-view 3D-reconstruction Without Dense Correspondences—0
View Selection with Geometric Uncertainty Modeling—0
Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D OutputsCode0
A fully end-to-end deep learning approach for real-time simultaneous 3D reconstruction and material recognition—0
3D Scanning System for Automatic High-Resolution Plant Phenotyping—0
3D Reconstruction of Temples in the Special Region of Yogyakarta By Using Close-Range Photogrammetry—0
Weighted Motion Averaging for the Registration of Multi-View Range Scans—0
Solving Uncalibrated Photometric Stereo Using Fewer Images by Jointly Optimizing Low-rank Matrix Completion and Integrability—0
Recovering 3D Planar Arrangements from Videos—0
Improved Descriptors for Patch Matching and Reconstruction—0
3D Reconstruction of Simple Objects from A Single View Silhouette Image—0
Two-view 3D Reconstruction for Food Volume Estimation—0
SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground TruthCode0
A Point Set Generation Network for 3D Object Reconstruction from a Single ImageCode0
Show:102550
← PrevPage 44 of 47Next →
All datasetsDTUShapeNetData3D−R2N2Scan2CAD3DPeopleAria Digital Twin DatasetAria Synthetic EnvironmentsScanNet

Benchmark Results

#ModelMetricClaimedVerifiedStatus
13D-R2N2Overall0.63—Unverified
2GipumaOverall0.58—Unverified
3COLMAPOverall0.53—Unverified
4MVSNetOverall0.46—Unverified
5Vis-MVSNetOverall0.37—Unverified
6AA-RMVSNetOverall0.36—Unverified
7Cas-MVSNetOverall0.36—Unverified
8EPP-MVSNetOverall0.36—Unverified
9PatchmatchNetOverall0.35—Unverified
10CVP-MVSNetOverall0.35—Unverified
#ModelMetricClaimedVerifiedStatus
1MD-GONIoU92.8—Unverified
2POCOIoU92.6—Unverified
3FS-SDFIoU91.2—Unverified
4DP-ConvONetIoU89.5—Unverified
5ConvONetIoU88.4—Unverified
6ONetIoU76.1—Unverified
7EVolTIoU73.8—Unverified
8ZubicLioIoU65.43—Unverified
#ModelMetricClaimedVerifiedStatus
1AttSets3DIoU0.64—Unverified
2PSGN3DIoU0.64—Unverified
3OGN3DIoU0.6—Unverified
43D-R2N23DIoU0.56—Unverified
#ModelMetricClaimedVerifiedStatus
1Scan2CADAverage Accuracy31.68—Unverified
23DMatchAverage Accuracy10.29—Unverified
#ModelMetricClaimedVerifiedStatus
1SVCPChamfer10—Unverified
#ModelMetricClaimedVerifiedStatus
1EVLAccuracy18.2—Unverified
#ModelMetricClaimedVerifiedStatus
1EVLAccuracy5.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Atlas (finetuned)3DIoU89.4—Unverified