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 1451–1500 of 2326 papers

TitleStatusHype
Multi-view Monocular Depth and Uncertainty Prediction with Deep SfM in Dynamic Environments—0
FaceOcc: A Diverse, High-quality Face Occlusion Dataset for Human Face ExtractionCode1
Instant Neural Graphics Primitives with a Multiresolution Hash EncodingCode6
Automated Aircraft Dent Inspection via a Modified Fourier Transform Profilometry AlgorithmCode1
POCO: Point Convolution for Surface ReconstructionCode2
Rethinking Depth Estimation for Multi-View Stereo: A Unified RepresentationCode2
Blind Face Restoration via Integrating Face Shape and Generative Priors—0
Using 3D Topological Connectivity for Ghost Particle Reduction in Flow Reconstruction—0
KeyTr: Keypoint Transporter for 3D Reconstruction of Deformable Objects in Videos—0
Learning Soft Estimator of Keypoint Scale and Orientation With Probabilistic Covariant LossCode0
f-SfT: Shape-From-Template With a Physics-Based Deformation ModelCode1
Enhancing Face Recognition With Self-Supervised 3D Reconstruction—0
Automated 3D reconstruction of LoD2 and LoD1 models for all 10 million buildings of the Netherlands—0
Visual and Object Geo-localization: A Comprehensive Survey—0
ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth EstimationCode1
Multimodal perception for dexterous manipulation—0
Multi-initialization Optimization Network for Accurate 3D Human Pose and Shape Estimation—0
Pose Adaptive Dual Mixup for Few-Shot Single-View 3D Reconstruction—0
Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and ResultsCode1
ADJUST: A Dictionary-Based Joint Reconstruction and Unmixing Method for Spectral TomographyCode1
MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networks—0
Improving neural implicit surfaces geometry with patch warpingCode1
GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional NetworkCode1
MVLayoutNet:3D layout reconstruction with multi-view panoramas—0
Curvature-guided dynamic scale networks for Multi-view StereoCode1
Roominoes: Generating Novel 3D Floor Plans From Existing 3D Rooms—0
Representing 3D Shapes with Probabilistic Directed Distance Fields—0
PERF: Performant, Explicit Radiance Fields—0
Sparse Depth Completion with Semantic Mesh Deformation Optimization—0
ScaleNet: A Shallow Architecture for Scale EstimationCode1
Adversarial Parametric Pose PriorCode1
What's Behind the Couch? Directed Ray Distance Functions (DRDF) for 3D Scene Reconstruction—0
Input-level Inductive Biases for 3D Reconstruction—0
Fast Organization of Objects' Spatial Positions in Manipulator Space from Single RGB-D CameraCode0
Generalized Binary Search Network for Highly-Efficient Multi-View StereoCode1
Geometry-aware Two-scale PIFu Representation for Human Reconstruction—0
CoNeRF: Controllable Neural Radiance FieldsCode1
MonoScene: Monocular 3D Semantic Scene CompletionCode1
3DVNet: Multi-View Depth Prediction and Volumetric RefinementCode1
Generating Diverse 3D Reconstructions from a Single Occluded Face ImageCode1
VoRTX: Volumetric 3D Reconstruction With Transformers for Voxelwise View Selection and FusionCode1
3D Reconstruction Using a Linear Laser Scanner and a CameraCode1
REMIPS: Physically Consistent 3D Reconstruction of Multiple Interacting People under Weak Supervision—0
Dense Keypoints via Multiview Supervision—0
LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies—0
A Dataset-Dispersion Perspective on Reconstruction Versus Recognition in Single-View 3D Reconstruction NetworksCode1
ESL: Event-based Structured Light—0
IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions—0
Urban Radiance Fields—0
TransMVSNet: Global Context-aware Multi-view Stereo Network with TransformersCode1
Show:102550
← PrevPage 30 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