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 251–300 of 2326 papers

TitleStatusHype
3D Shape Reconstruction from Free-Hand SketchesCode1
Evaluate Geometry of Radiance Fields with Low-frequency Color PriorCode1
LineGS : 3D Line Segment Representation on 3D Gaussian SplattingCode1
Leveraging Photogrammetric Mesh Models for Aerial-Ground Feature Point Matching Toward Integrated 3D ReconstructionCode1
Leveraging Thermal Modality to Enhance Reconstruction in Low-Light ConditionsCode1
Enhancing Agricultural Environment Perception via Active Vision and Zero-Shot LearningCode1
A geometry-aware deep network for depth estimation in monocular endoscopyCode1
ENRICH: Multi-purposE dataset for beNchmaRking In Computer vision and pHotogrammetryCode1
3D Gaussian Splatting against Moving Objects for High-Fidelity Street Scene ReconstructionCode1
Fully Understanding Generic Objects: Modeling, Segmentation, and ReconstructionCode1
3D Reconstruction of Novel Object Shapes from Single ImagesCode1
Enhance-NeRF: Multiple Performance Evaluation for Neural Radiance FieldsCode1
HDD-Net: Hybrid Detector Descriptor with Mutual Interactive LearningCode1
LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance FieldsCode1
LivePose: Online 3D Reconstruction from Monocular Video with Dynamic Camera PosesCode1
MonoScene: Monocular 3D Semantic Scene CompletionCode1
E-3DGS: Gaussian Splatting with Exposure and Motion EventsCode1
E3D: Event-Based 3D Shape ReconstructionCode1
Dynamic Plane Convolutional Occupancy NetworksCode1
E2GS: Event Enhanced Gaussian SplattingCode1
Efficient Implicit Neural Reconstruction Using LiDARCode1
Learning to Detect 3D Reflection Symmetry for Single-View ReconstructionCode1
DUDF: Differentiable Unsigned Distance Fields with Hyperbolic ScalingCode1
Adversarial Parametric Pose PriorCode1
Learning Online Multi-Sensor Depth FusionCode1
3D GAN Inversion with Pose OptimizationCode1
Learning to Parse Wireframes in Images of Man-Made EnvironmentsCode1
Learning Deformable Tetrahedral Meshes for 3D ReconstructionCode1
Learning How To Robustly Estimate Camera Pose in Endoscopic VideosCode1
Doppelgangers: Learning to Disambiguate Images of Similar StructuresCode1
Efficient Pix2Vox++ for 3D Cardiac Reconstruction from 2D echo viewsCode1
Learning Implicit Representation for Reconstructing Articulated ObjectsCode1
ADJUST: A Dictionary-Based Joint Reconstruction and Unmixing Method for Spectral TomographyCode1
DITTO: Dual and Integrated Latent Topologies for Implicit 3D ReconstructionCode1
DMCVR: Morphology-Guided Diffusion Model for 3D Cardiac Volume ReconstructionCode1
3D^2-Actor: Learning Pose-Conditioned 3D-Aware Denoiser for Realistic Gaussian Avatar ModelingCode1
A Dataset-Dispersion Perspective on Reconstruction Versus Recognition in Single-View 3D Reconstruction NetworksCode1
DISORF: A Distributed Online 3D Reconstruction Framework for Mobile RobotsCode1
Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB ImageCode1
DI-Fusion: Online Implicit 3D Reconstruction with Deep PriorsCode1
DiffInDScene: Diffusion-based High-Quality 3D Indoor Scene GenerationCode1
Large Images are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian SplattingCode1
DifferSketching: How Differently Do People Sketch 3D Objects?Code1
Detecting Line Segments in Motion-blurred Images with EventsCode1
DeOcc-1-to-3: 3D De-Occlusion from a Single Image via Self-Supervised Multi-View DiffusionCode1
Active 3D Shape Reconstruction from Vision and TouchCode1
Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset UpdatesCode1
Learning Accurate Dense Correspondences and When to Trust ThemCode1
DEFN: Dual-Encoder Fourier Group Harmonics Network for Three-Dimensional Indistinct-Boundary Object SegmentationCode1
Deformable Model-Driven Neural Rendering for High-Fidelity 3D Reconstruction of Human Heads Under Low-View SettingsCode1
Show:102550
← PrevPage 6 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