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

Showing 251300 of 2326 papers

TitleStatusHype
PyTorchGeoNodes: Enabling Differentiable Shape Programs for 3D Shape ReconstructionCode1
EventEgo3D: 3D Human Motion Capture from Egocentric Event StreamsCode1
WorDepth: Variational Language Prior for Monocular Depth EstimationCode1
Unsupervised Occupancy Learning from Sparse Point CloudCode1
CoherentGS: Sparse Novel View Synthesis with Coherent 3D GaussiansCode1
SAT-NGP : Unleashing Neural Graphics Primitives for Fast Relightable Transient-Free 3D reconstruction from Satellite ImageryCode1
SUP-NeRF: A Streamlined Unification of Pose Estimation and NeRF for Monocular 3D Object ReconstructionCode1
Leveraging Thermal Modality to Enhance Reconstruction in Low-Light ConditionsCode1
Bayesian Diffusion Models for 3D Shape ReconstructionCode1
DITTO: Dual and Integrated Latent Topologies for Implicit 3D ReconstructionCode1
CN-RMA: Combined Network with Ray Marching Aggregation for 3D Indoors Object Detection from Multi-view ImagesCode1
G3DR: Generative 3D Reconstruction in ImageNetCode1
DISORF: A Distributed Online 3D Reconstruction Framework for Mobile RobotsCode1
WHU-Synthetic: A Synthetic Perception Dataset for 3-D Multitask Model ResearchCode1
DUDF: Differentiable Unsigned Distance Fields with Hyperbolic ScalingCode1
Camera Calibration through Geometric Constraints from Rotation and Projection MatricesCode1
OmniSCV: An Omnidirectional Synthetic Image Generator for Computer VisionCode1
3D Reconstruction and New View Synthesis of Indoor Environments based on a Dual Neural Radiance FieldCode1
Range-Agnostic Multi-View Depth Estimation With Keyframe SelectionCode1
Multi-View Neural 3D Reconstruction of Micro-/Nanostructures with Atomic Force MicroscopyCode1
Learning Implicit Representation for Reconstructing Articulated ObjectsCode1
S3Net: Innovating Stereo Matching and Semantic Segmentation with a Single-Branch Semantic Stereo Network in Satellite Epipolar ImageryCode1
CN-RMA: Combined Network with Ray Marching Aggregation for 3D Indoor Object Detection from Multi-view ImagesCode1
Pola4All: survey of polarimetric applications and an open-source toolkit to analyze polarizationCode1
3D Pose Estimation of Two Interacting Hands from a Monocular Event CameraCode1
Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D EnvironmentsCode1
CT-MVSNet: Efficient Multi-View Stereo with Cross-scale TransformerCode1
SuperNormal: Neural Surface Reconstruction via Multi-View Normal IntegrationCode1
Free3D: Consistent Novel View Synthesis without 3D RepresentationCode1
Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian ParticleCode1
Fully Convolutional Slice-to-Volume Reconstruction for Single-Stack MRICode1
iMatching: Imperative Correspondence LearningCode1
Steerers: A framework for rotation equivariant keypoint descriptorsCode1
RNb-NeuS: Reflectance and Normal-based Multi-View 3D ReconstructionCode1
Self-Evolving Neural Radiance FieldsCode1
Gradient-based Local Next-best-view Planning for Improved Perception of Targeted Plant NodesCode1
Physics-guided Shape-from-Template: Monocular Video Perception through Neural Surrogate ModelsCode1
DEFN: Dual-Encoder Fourier Group Harmonics Network for Three-Dimensional Indistinct-Boundary Object SegmentationCode1
GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View StereoCode1
Long-term Dependency for 3D Reconstruction of Freehand Ultrasound Without External TrackerCode1
Implicit Shape and Appearance Priors for Few-Shot Full Head ReconstructionCode1
PC-NeRF: Parent-Child Neural Radiance Fields under Partial Sensor Data Loss in Autonomous Driving EnvironmentsCode1
When Epipolar Constraint Meets Non-local Operators in Multi-View StereoCode1
MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View StereoCode1
NeRRF: 3D Reconstruction and View Synthesis for Transparent and Specular Objects with Neural Refractive-Reflective FieldsCode1
NTO3D: Neural Target Object 3D Reconstruction with Segment AnythingCode1
Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset UpdatesCode1
Uncertainty-aware 3D Object-Level Mapping with Deep Shape PriorsCode1
TiAVox: Time-aware Attenuation Voxels for Sparse-view 4D DSA ReconstructionCode1
Doppelgangers: Learning to Disambiguate Images of Similar StructuresCode1
Show:102550
← PrevPage 6 of 47Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
13D-R2N2Overall0.63Unverified
2GipumaOverall0.58Unverified
3COLMAPOverall0.53Unverified
4MVSNetOverall0.46Unverified
5Vis-MVSNetOverall0.37Unverified
6AA-RMVSNetOverall0.36Unverified
7Cas-MVSNetOverall0.36Unverified
8EPP-MVSNetOverall0.36Unverified
9PatchmatchNetOverall0.35Unverified
10CVP-MVSNetOverall0.35Unverified
#ModelMetricClaimedVerifiedStatus
1MD-GONIoU92.8Unverified
2POCOIoU92.6Unverified
3FS-SDFIoU91.2Unverified
4DP-ConvONetIoU89.5Unverified
5ConvONetIoU88.4Unverified
6ONetIoU76.1Unverified
7EVolTIoU73.8Unverified
8ZubicLioIoU65.43Unverified
#ModelMetricClaimedVerifiedStatus
1AttSets3DIoU0.64Unverified
2PSGN3DIoU0.64Unverified
3OGN3DIoU0.6Unverified
43D-R2N23DIoU0.56Unverified
#ModelMetricClaimedVerifiedStatus
1Scan2CADAverage Accuracy31.68Unverified
23DMatchAverage Accuracy10.29Unverified
#ModelMetricClaimedVerifiedStatus
1SVCPChamfer10Unverified
#ModelMetricClaimedVerifiedStatus
1EVLAccuracy18.2Unverified
#ModelMetricClaimedVerifiedStatus
1EVLAccuracy5.7Unverified
#ModelMetricClaimedVerifiedStatus
1Atlas (finetuned)3DIoU89.4Unverified