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 501550 of 2326 papers

TitleStatusHype
SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static ImagesCode1
Amodal 3D Reconstruction for Robotic Manipulation via Stability and ConnectivityCode1
Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstructionCode1
Next-Best View Policy for 3D ReconstructionCode1
Multi-Dimension Fusion Network for Light Field Spatial Super-Resolution using Dynamic FiltersCode1
Visibility-aware Multi-view Stereo NetworkCode1
BraggNN: Fast X-ray Bragg Peak Analysis Using Deep LearningCode1
Stochastic Bundle Adjustment for Efficient and Scalable 3D ReconstructionCode1
Continuous Object Representation Networks: Novel View Synthesis without Target View SupervisionCode1
Event-based Stereo Visual OdometryCode1
GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware SupervisionCode1
Single View Metrology in the WildCode1
Fast and Robust Iterative Closest PointCode1
Learning to Parse Wireframes in Images of Man-Made EnvironmentsCode1
Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric LearningCode1
SPSG: Self-Supervised Photometric Scene Generation from RGB-D ScansCode1
3D Shape Reconstruction from Free-Hand SketchesCode1
Learning to Detect 3D Reflection Symmetry for Single-View ReconstructionCode1
HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet LossCode1
Coherent Reconstruction of Multiple Humans from a Single ImageCode1
3D Reconstruction of Novel Object Shapes from Single ImagesCode1
Robust Learning Through Cross-Task ConsistencyCode1
DeepDeform: Learning Non-Rigid RGB-D Reconstruction With Semi-Supervised DataCode1
Robust Learning Through Cross-Task ConsistencyCode1
AutoSweep: Recovering 3D Editable Objectsfrom a Single PhotographCode1
DeepFaceFlow: In-the-wild Dense 3D Facial Motion EstimationCode1
HDD-Net: Hybrid Detector Descriptor with Mutual Interactive LearningCode1
Through the Looking Glass: Neural 3D Reconstruction of Transparent ShapesCode1
Few-Shot Single-View 3-D Object Reconstruction with Compositional PriorsCode1
Occlusion-Aware Depth Estimation with Adaptive Normal ConstraintsCode1
Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB ImageCode1
Deep Local Shapes: Learning Local SDF Priors for Detailed 3D ReconstructionCode1
ASLFeat: Learning Local Features of Accurate Shape and LocalizationCode1
Multiview Neural Surface Reconstruction by Disentangling Geometry and AppearanceCode1
Reconstructing Sinus Anatomy from Endoscopic Video -- Towards a Radiation-free Approach for Quantitative Longitudinal AssessmentCode1
Self-supervised Single-view 3D Reconstruction via Semantic ConsistencyCode1
Convolutional Occupancy NetworksCode1
Implicit Functions in Feature Space for 3D Shape Reconstruction and CompletionCode1
Extremely Dense Point Correspondences using a Learned Feature DescriptorCode1
Leveraging Photogrammetric Mesh Models for Aerial-Ground Feature Point Matching Toward Integrated 3D ReconstructionCode1
PeeledHuman: Robust Shape Representation for Textured 3D Human Body ReconstructionCode1
RoutedFusion: Learning Real-time Depth Map FusionCode1
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo MatchingCode1
DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised DataCode1
BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo NetworksCode1
BSP-Net: Generating Compact Meshes via Binary Space PartitioningCode1
Surface Reconstruction from 3D Line SegmentsCode1
Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and MappingCode1
PCRNet: Point Cloud Registration Network using PointNet EncodingCode1
D2-Net: A Trainable CNN for Joint Detection and Description of Local FeaturesCode1
Show:102550
← PrevPage 11 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