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 2001–2050 of 2326 papers

TitleStatusHype
RayNet: Learning Volumetric 3D Reconstruction with Ray PotentialsCode0
Diffeomorphic registration with intensity transformation and missing data: Application to 3D digital pathology of Alzheimer’s disease—0
Rendu basé image avec contraintes sur les gradients—0
Learning to Reconstruct Shapes from Unseen Classes—0
FML: Face Model Learning from Videos—0
3D-SIS: 3D Semantic Instance Segmentation of RGB-D ScansCode0
DeepCalib: a deep learning approach for automatic intrinsic calibration of wide field-of-view camerasCode0
A Self-Supervised Bootstrap Method for Single-Image 3D Face Reconstruction—0
SeFM: A Sequential Feature Point Matching Algorithm for Object 3D Reconstruction—0
Real-time Indoor Scene Reconstruction with RGBD and Inertia Input—0
Learning to Infer the Depth Map of a Hand from its Color Image—0
Learning Implicit Fields for Generative Shape ModelingCode0
Domain-Adaptive Single-View 3D ReconstructionCode0
Multiview Cross-supervision for Semantic Segmentation—0
DeepVoxels: Learning Persistent 3D Feature EmbeddingsCode0
EV-SegNet: Semantic Segmentation for Event-based Cameras—0
3D Shape Reconstruction from a Single 2D Image via 2D-3D Self-Consistency—0
Single-view Object Shape Reconstruction Using Deep Shape Prior and Silhouette—0
Traffic Danger Recognition With Surveillance Cameras Without Training Data—0
Scan2CAD: Learning CAD Model Alignment in RGB-D ScansCode0
Multiview Supervision By RegistrationCode0
Object Tracking by Reconstruction with View-Specific Discriminative Correlation Filters—0
Learning View Priors for Single-view 3D Reconstruction—0
Matchable Image Retrieval by Learning from Surface ReconstructionCode0
Multi-View Inpainting for RGB-D Sequence—0
Semantic Stereo for Incidental Satellite ImagesCode0
Deep Shape-from-Template: Wide-Baseline, Dense and Fast Registration and Deformable Reconstruction from a Single Image—0
Object 3D Reconstruction based on Photometric Stereo and Inverted Rendering—0
Geometry-Aware Recurrent Neural Networks for Active Visual Recognition—0
Equivalent Constraints for Two-View Geometry: Pose Solution/Pure Rotation Identification and 3D Reconstruction—0
Skeleton Driven Non-rigid Motion Tracking and 3D Reconstruction—0
Quadtree-accelerated Real-time Monocular Dense MappingCode0
Modelling Errors in X-ray Fluoroscopic Imaging Systems Using Photogrammetric Bundle Adjustment With a Data-Driven Self-Calibration Approach—0
Deep Textured 3D Reconstruction of Human Bodies—0
Do-It-Yourself Single Camera 3D Pointer Input DeviceCode0
Hubless keypoint-based 3D deformable groupwise registrationCode0
Deep Depth from Defocus: how can defocus blur improve 3D estimation using dense neural networks?Code0
Neural Procedural Reconstruction for Residential Buildings—0
Simultaneous 3D Reconstruction for Water Surface and Underwater Scene—0
Learning Single-View 3D Reconstruction with Limited Pose SupervisionCode0
Learning Priors for Semantic 3D Reconstruction—0
Reconstruction-based Pairwise Depth Dataset for Depth Image Enhancement Using CNN—0
Semantically Aware Urban 3D Reconstruction with Plane-Based Regularization—0
On Learning 3D Face Morphable Model from In-the-wild ImagesCode0
Scale Drift Correction of Camera Geo-Localization using Geo-Tagged Images—0
Deep Learned Full-3D Object Completion from Single View—0
Fast and Accurate Camera Covariance Computation for Large 3D Reconstruction—0
A Generic Multi-Projection-Center Model and Calibration Method for Light Field Cameras—0
Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D ReconstructionCode0
Geo-Supervised Visual Depth PredictionCode0
Show:102550
← PrevPage 41 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