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 151–200 of 2326 papers

TitleStatusHype
MAC-Ego3D: Multi-Agent Gaussian Consensus for Real-Time Collaborative Ego-Motion and Photorealistic 3D ReconstructionCode2
CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size EstimationCode2
MegaLoc: One Retrieval to Place Them AllCode2
Memorize What Matters: Emergent Scene Decomposition from MultitraverseCode2
Boost 3D Reconstruction using Diffusion-based Monocular Camera CalibrationCode2
3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and HumansCode2
MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian SplattingCode2
Multiview Compressive Coding for 3D ReconstructionCode2
PartGS:Learning Part-aware 3D Representations by Fusing 2D Gaussians and SuperquadricsCode2
6Img-to-3D: Few-Image Large-Scale Outdoor Driving Scene ReconstructionCode2
LandMarkSystem Technical ReportCode2
Neural 3D Scene Reconstruction with the Manhattan-world AssumptionCode2
DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single ImageCode2
NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360° ViewsCode2
Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene GraphsCode2
ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand ReconstructionCode2
InteractVLM: 3D Interaction Reasoning from 2D Foundational ModelsCode2
OmniColor: A Global Camera Pose Optimization Approach of LiDAR-360Camera Fusion for Colorizing Point CloudsCode2
iHuman: Instant Animatable Digital Humans From Monocular VideosCode2
DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature MatchingCode2
HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from VideoCode2
Joint Reconstruction of 3D Human and Object via Contact-Based Refinement TransformerCode2
Learning Continuous Image Representation with Local Implicit Image FunctionCode2
PC^2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D ReconstructionCode2
A Survey on 3D Gaussian SplattingCode2
A Simple Framework for 3D Occupancy Estimation in Autonomous DrivingCode2
EndoGS: Deformable Endoscopic Tissues Reconstruction with Gaussian SplattingCode2
GO-SLAM: Global Optimization for Consistent 3D Instant ReconstructionCode2
Delicate Textured Mesh Recovery from NeRF via Adaptive Surface RefinementCode2
PLVS: A SLAM System with Points, Lines, Volumetric Mapping, and 3D Incremental SegmentationCode2
DiffCalib: Reformulating Monocular Camera Calibration as Diffusion-Based Dense Incident Map GenerationCode2
ARCTIC: A Dataset for Dexterous Bimanual Hand-Object ManipulationCode2
Animal Avatars: Reconstructing Animatable 3D Animals from Casual VideosCode2
Atlas: End-to-End 3D Scene Reconstruction from Posed ImagesCode2
GigaPose: Fast and Robust Novel Object Pose Estimation via One CorrespondenceCode2
GoMVS: Geometrically Consistent Cost Aggregation for Multi-View StereoCode2
Learning Implicit Surface Light FieldsCode2
Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and DenoisingCode2
3D Shape Reconstruction from Free-Hand SketchesCode1
Geodesy of irregular small bodies via neural density fields: geodesyNetsCode1
Generative Proxemics: A Prior for 3D Social Interaction from ImagesCode1
3D Shape Reconstruction from 2D Images with Disentangled Attribute FlowCode1
Generalized Binary Search Network for Highly-Efficient Multi-View StereoCode1
Generating Diverse 3D Reconstructions from a Single Occluded Face ImageCode1
GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional NetworkCode1
3DMatch: Learning Local Geometric Descriptors from RGB-D ReconstructionsCode1
GenDR: A Generalized Differentiable RendererCode1
Generative Object Insertion in Gaussian Splatting with a Multi-View Diffusion ModelCode1
GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal EstimationCode1
3D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal PerspectiveCode1
Show:102550
← PrevPage 4 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