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 701–750 of 2326 papers

TitleStatusHype
EventEgo3D: 3D Human Motion Capture from Egocentric Event StreamsCode1
GoMVS: Geometrically Consistent Cost Aggregation for Multi-View StereoCode2
MonoSelfRecon: Purely Self-Supervised Explicit Generalizable 3D Reconstruction of Indoor Scenes from Monocular RGB Views—0
Binomial Self-compensation for Motion Error in Dynamic 3D ScanningCode0
3D-COCO: extension of MS-COCO dataset for image detection and 3D reconstruction modules—0
Learning Topology Uniformed Face Mesh by Volume Rendering for Multi-view Reconstruction—0
3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level SupervisionsCode2
Joint Reconstruction of 3D Human and Object via Contact-Based Refinement TransformerCode2
OmniColor: A Global Camera Pose Optimization Approach of LiDAR-360Camera Fusion for Colorizing Point CloudsCode2
The More You See in 2D, the More You Perceive in 3DCode2
RaFE: Generative Radiance Fields Restoration—0
WorDepth: Variational Language Prior for Monocular Depth EstimationCode1
Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single ViewCode2
APC2Mesh: Bridging the gap from occluded building façades to full 3D models—0
LiDAR4D: Dynamic Neural Fields for Novel Space-time View LiDAR SynthesisCode3
Neural Radiance Fields with Torch Units—0
Behind the Veil: Enhanced Indoor 3D Scene Reconstruction with Occluded Surfaces Completion—0
TCLC-GS: Tightly Coupled LiDAR-Camera Gaussian Splatting for Autonomous Driving—0
Unsupervised Occupancy Learning from Sparse Point CloudCode1
Few-shot point cloud reconstruction and denoising via learned Guassian splats renderings and fine-tuned diffusion featuresCode0
3DGSR: Implicit Surface Reconstruction with 3D Gaussian SplattingCode0
InstantSplat: Sparse-view SfM-free Gaussian Splatting in SecondsCode5
NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and DenoisingCode0
CoherentGS: Sparse Novel View Synthesis with Coherent 3D GaussiansCode1
Neural Fields for 3D Tracking of Anatomy and Surgical Instruments in Monocular Laparoscopic Video Clips—0
Total-Decom: Decomposed 3D Scene Reconstruction with Minimal InteractionCode2
WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects under Occlusion—0
SAT-NGP : Unleashing Neural Graphics Primitives for Fast Relightable Transient-Free 3D reconstruction from Satellite ImageryCode1
SplatFace: Gaussian Splat Face Reconstruction Leveraging an Optimizable Surface—0
Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstructionCode2
EgoLifter: Open-world 3D Segmentation for Egocentric PerceptionCode2
DN-Splatter: Depth and Normal Priors for Gaussian Splatting and MeshingCode4
Animal Avatars: Reconstructing Animatable 3D Animals from Casual VideosCode2
Spike-NeRF: Neural Radiance Field Based On Spike Camera—0
Creating a Digital Twin of Spinal Surgery: A Proof of Concept—0
Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusion—0
Interactive Manipulation and Visualization of 3D Brain MRI for Surgical Training—0
latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction—0
SUP-NeRF: A Streamlined Unification of Pose Estimation and NeRF for Monocular 3D Object ReconstructionCode1
Make VLM Recognize Visual Hallucination on Cartoon Character Image with Pose Information—0
Recent Trends in 3D Reconstruction of General Non-Rigid Scenes—0
FastCAD: Real-Time CAD Retrieval and Alignment from Scans and Videos—0
Hyperspectral Neural Radiance Fields—0
MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View ImagesCode5
GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and GenerationCode4
Isotropic Gaussian Splatting for Real-Time Radiance Field Rendering—0
Leveraging Thermal Modality to Enhance Reconstruction in Low-Light ConditionsCode1
T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Image—0
GVGEN: Text-to-3D Generation with Volumetric Representation—0
PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust 3D Human Mesh Recovery—0
Show:102550
← PrevPage 15 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