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 201250 of 2326 papers

TitleStatusHype
Deep Learning-based Bathymetry Retrieval without In-situ Depths using Remote Sensing Imagery and SfM-MVS DSMs with Data GapsCode1
Wheat3DGS: In-field 3D Reconstruction, Instance Segmentation and Phenotyping of Wheat Heads with Gaussian SplattingCode1
BlenderGym: Benchmarking Foundational Model Systems for Graphics EditingCode1
3D Gaussian Splatting against Moving Objects for High-Fidelity Street Scene ReconstructionCode1
X-Field: A Physically Grounded Representation for 3D X-ray ReconstructionCode1
Enhancing Monocular 3D Scene Completion with Diffusion ModelCode1
MESC-3D:Mining Effective Semantic Cues for 3D Reconstruction from a Single ImageCode1
CDGS: Confidence-Aware Depth Regularization for 3D Gaussian SplattingCode1
Large Images are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian SplattingCode1
GP-GS: Gaussian Processes for Enhanced Gaussian SplattingCode1
OpticFusion: Multi-Modal Neural Implicit 3D Reconstruction of Microstructures by Fusing White Light Interferometry and Optical MicroscopyCode1
ConcealGS: Concealing Invisible Copyright Information in 3D Gaussian SplattingCode1
3D^2-Actor: Learning Pose-Conditioned 3D-Aware Denoiser for Realistic Gaussian Avatar ModelingCode1
Volumetric Mapping with Panoptic Refinement via Kernel Density Estimation for Mobile RobotsCode1
DCSEG: Decoupled 3D Open-Set Segmentation using Gaussian SplattingCode1
PBR-NeRF: Inverse Rendering with Physics-Based Neural FieldsCode1
How to Use Diffusion Priors under Sparse Views?Code1
LineGS : 3D Line Segment Representation on 3D Gaussian SplattingCode1
GSurf: 3D Reconstruction via Signed Distance Fields with Direct Gaussian SupervisionCode1
TimeFormer: Capturing Temporal Relationships of Deformable 3D Gaussians for Robust ReconstructionCode1
E-3DGS: Gaussian Splatting with Exposure and Motion EventsCode1
UniGS: Modeling Unitary 3D Gaussians for Novel View Synthesis from Sparse-view ImagesCode1
Multimodal 3D Fusion and In-Situ Learning for Spatially Aware AICode1
IceCloudNet: 3D reconstruction of cloud ice from Meteosat SEVIRICode1
3DGR-CAR: Coronary artery reconstruction from ultra-sparse 2D X-ray views with a 3D Gaussians representationCode1
Generative Object Insertion in Gaussian Splatting with a Multi-View Diffusion ModelCode1
Matérn Kernels for Tunable Implicit Surface ReconstructionCode1
Enhancing Agricultural Environment Perception via Active Vision and Zero-Shot LearningCode1
Sources of Uncertainty in 3D Scene ReconstructionCode1
Online 3D reconstruction and dense tracking in endoscopic videosCode1
DARES: Depth Anything in Robotic Endoscopic Surgery with Self-supervised Vector-LoRA of the Foundation ModelCode1
Mismatched: Evaluating the Limits of Image Matching Approaches and BenchmarksCode1
S4D: Streaming 4D Real-World Reconstruction with Gaussians and 3D Control PointsCode1
Comparative Evaluation of 3D Reconstruction Methods for Object Pose EstimationCode1
CryoBench: Diverse and challenging datasets for the heterogeneity problem in cryo-EMCode1
A Review of 3D Reconstruction Techniques for Deformable Tissues in Robotic SurgeryCode1
Opening the Black Box of 3D Reconstruction Error Analysis with VECTORCode1
BodySLAM: A Generalized Monocular Visual SLAM Framework for Surgical ApplicationsCode1
SparseCraft: Few-Shot Neural Reconstruction through Stereopsis Guided Geometric LinearizationCode1
MaRINeR: Enhancing Novel Views by Matching Rendered Images with Nearby ReferencesCode1
Repeat and Concatenate: 2D to 3D Image Translation with 3D to 3D Generative ModelingCode1
E2GS: Event Enhanced Gaussian SplattingCode1
A Two-Stage Masked Autoencoder Based Network for Indoor Depth CompletionCode1
HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object InteractionCode1
Coarse-To-Fine Tensor Trains for Compact Visual RepresentationsCode1
C^2RV: Cross-Regional and Cross-View Learning for Sparse-View CBCT ReconstructionCode1
EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian SplattingCode1
S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular VideoCode1
TD-NeRF: Novel Truncated Depth Prior for Joint Camera Pose and Neural Radiance Field OptimizationCode1
OneTo3D: One Image to Re-editable Dynamic 3D Model and Video GenerationCode1
Show:102550
← PrevPage 5 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