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 201–250 of 2326 papers

TitleStatusHype
Human-Aware Object Placement for Visual Environment ReconstructionCode1
HRBF-Fusion: Accurate 3D reconstruction from RGB-D data using on-the-fly implicitsCode1
Human Mesh Recovery from Multiple ShotsCode1
3D-C2FT: Coarse-to-fine Transformer for Multi-view 3D ReconstructionCode1
HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object InteractionCode1
Hybrid Rotation Averaging: A Fast and Robust Rotation Averaging ApproachCode1
HDD-Net: Hybrid Detector Descriptor with Mutual Interactive LearningCode1
3DInvNet: A Deep Learning-Based 3D Ground-Penetrating Radar Data InversionCode1
GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware SupervisionCode1
Gradient-based Local Next-best-view Planning for Improved Perception of Targeted Plant NodesCode1
ASLFeat: Learning Local Features of Accurate Shape and LocalizationCode1
Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the WildCode1
HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet LossCode1
Large Images are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian SplattingCode1
An Effective Loss Function for Generating 3D Models from Single 2D Image without RenderingCode1
3D Reconstruction Using a Linear Laser Scanner and a CameraCode1
GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal EstimationCode1
Geodesy of irregular small bodies via neural density fields: geodesyNetsCode1
Generative Object Insertion in Gaussian Splatting with a Multi-View Diffusion ModelCode1
Generating Diverse 3D Reconstructions from a Single Occluded Face ImageCode1
Generative Proxemics: A Prior for 3D Social Interaction from ImagesCode1
GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional NetworkCode1
GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View StereoCode1
GenDR: A Generalized Differentiable RendererCode1
Amodal 3D Reconstruction for Robotic Manipulation via Stability and ConnectivityCode1
Gradient-SDF: A Semi-Implicit Surface Representation for 3D ReconstructionCode1
G3DR: Generative 3D Reconstruction in ImageNetCode1
gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object ReconstructionCode1
GSurf: 3D Reconstruction via Signed Distance Fields with Direct Gaussian SupervisionCode1
H3D-Net: Few-Shot High-Fidelity 3D Head ReconstructionCode1
Fully Understanding Generic Objects: Modeling, Segmentation, and ReconstructionCode1
Enhancing Monocular 3D Scene Completion with Diffusion ModelCode1
Fully Convolutional Slice-to-Volume Reconstruction for Single-Stack MRICode1
HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D ReconstructionCode1
3D-RETR: End-to-End Single and Multi-View 3D Reconstruction with TransformersCode1
How to Use Diffusion Priors under Sparse Views?Code1
3D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal PerspectiveCode1
Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian ParticleCode1
Generalized Binary Search Network for Highly-Efficient Multi-View StereoCode1
3DMatch: Learning Local Geometric Descriptors from RGB-D ReconstructionsCode1
Free3D: Consistent Novel View Synthesis without 3D RepresentationCode1
iMatching: Imperative Correspondence LearningCode1
FineRecon: Depth-aware Feed-forward Network for Detailed 3D ReconstructionCode1
Incremental Visual-Inertial 3D Mesh Generation with Structural RegularitiesCode1
3DGR-CAR: Coronary artery reconstruction from ultra-sparse 2D X-ray views with a 3D Gaussians representationCode1
FLSea: Underwater Visual-Inertial and Stereo-Vision Forward-Looking DatasetsCode1
InFusionSurf: Refining Neural RGB-D Surface Reconstruction Using Per-Frame Intrinsic Refinement and TSDF Fusion Prior LearningCode1
AIR-Nets: An Attention-Based Framework for Locally Conditioned Implicit RepresentationsCode1
Articulated 3D Human-Object Interactions from RGB Videos: An Empirical Analysis of Approaches and ChallengesCode1
Few-Shot Single-View 3-D Object Reconstruction with Compositional PriorsCode1
Show:102550
← PrevPage 5 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