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 101–150 of 2326 papers

TitleStatusHype
Neural Rendering for Stereo 3D Reconstruction of Deformable Tissues in Robotic SurgeryCode2
3D Reconstruction of Spherical Images based on Incremental Structure from MotionCode2
Neural 3D Reconstruction in the WildCode2
Occupancy-Based Dual ContouringCode2
NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360° ViewsCode2
OcclusionFusion: Occlusion-aware Motion Estimation for Real-time Dynamic 3D ReconstructionCode2
PeRFception: Perception using Radiance FieldsCode2
EndoGS: Deformable Endoscopic Tissues Reconstruction with Gaussian SplattingCode2
Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy VideoCode2
Delicate Textured Mesh Recovery from NeRF via Adaptive Surface RefinementCode2
MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based DepthCode2
Multiview Compressive Coding for 3D ReconstructionCode2
MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian SplattingCode2
Multi-View Mesh Reconstruction with Neural Deferred ShadingCode2
MicroDreamer: Efficient 3D Generation in 20 Seconds by Score-based Iterative ReconstructionCode2
MicroDiffusion: Implicit Representation-Guided Diffusion for 3D Reconstruction from Limited 2D Microscopy ProjectionsCode2
Momentum-GS: Momentum Gaussian Self-Distillation for High-Quality Large Scene ReconstructionCode2
PLVS: A SLAM System with Points, Lines, Volumetric Mapping, and 3D Incremental SegmentationCode2
MegaLoc: One Retrieval to Place Them AllCode2
PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training ParadigmCode2
Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category ReconstructionCode2
Memorize What Matters: Emergent Scene Decomposition from MultitraverseCode2
EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the WildCode2
MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface ReconstructionCode2
LumiGauss: Relightable Gaussian Splatting in the WildCode2
LRM-Zero: Training Large Reconstruction Models with Synthesized DataCode2
LuSNAR:A Lunar Segmentation, Navigation and Reconstruction Dataset based on Muti-sensor for Autonomous ExplorationCode2
CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size EstimationCode2
MAC-Ego3D: Multi-Agent Gaussian Consensus for Real-Time Collaborative Ego-Motion and Photorealistic 3D ReconstructionCode2
PartGS:Learning Part-aware 3D Representations by Fusing 2D Gaussians and SuperquadricsCode2
Local Feature Matching Using Deep Learning: A SurveyCode2
LandMarkSystem Technical ReportCode2
Boost 3D Reconstruction using Diffusion-based Monocular Camera CalibrationCode2
Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene GraphsCode2
InteractVLM: 3D Interaction Reasoning from 2D Foundational ModelsCode2
iHuman: Instant Animatable Digital Humans From Monocular VideosCode2
Joint Reconstruction of 3D Human and Object via Contact-Based Refinement TransformerCode2
GO-SLAM: Global Optimization for Consistent 3D Instant ReconstructionCode2
3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and HumansCode2
HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from VideoCode2
Learning Continuous Image Representation with Local Implicit Image FunctionCode2
6Img-to-3D: Few-Image Large-Scale Outdoor Driving Scene ReconstructionCode2
Atlas: End-to-End 3D Scene Reconstruction from Posed ImagesCode2
GeoMVSNet: Learning Multi-View Stereo With Geometry PerceptionCode2
A Survey on 3D Gaussian SplattingCode2
GigaPose: Fast and Robust Novel Object Pose Estimation via One CorrespondenceCode2
Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single ViewCode2
ARCTIC: A Dataset for Dexterous Bimanual Hand-Object ManipulationCode2
GenNBV: Generalizable Next-Best-View Policy for Active 3D ReconstructionCode2
A Simple Framework for 3D Occupancy Estimation in Autonomous DrivingCode2
Show:102550
← PrevPage 3 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