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 51–100 of 2326 papers

TitleStatusHype
Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion ModelsCode3
EPRecon: An Efficient Framework for Real-Time Panoptic 3D Reconstruction from Monocular VideoCode3
Chat-Edit-3D: Interactive 3D Scene Editing via Text PromptsCode3
LaRa: Efficient Large-Baseline Radiance FieldsCode3
SpotlessSplats: Ignoring Distractors in 3D Gaussian SplattingCode3
Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion TransformerCode3
DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian ConsensusCode3
Lightplane: Highly-Scalable Components for Neural 3D FieldsCode3
LiDAR4D: Dynamic Neural Fields for Novel Space-time View LiDAR SynthesisCode3
SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video DiffusionCode3
LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D GenerationCode3
Relaxing Accurate Initialization Constraint for 3D Gaussian SplattingCode3
GES: Generalized Exponential Splatting for Efficient Radiance Field RenderingCode3
EscherNet: A Generative Model for Scalable View SynthesisCode3
pix2gestalt: Amodal Segmentation by Synthesizing WholesCode3
MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View StereoCode3
Splatter Image: Ultra-Fast Single-View 3D ReconstructionCode3
pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D ReconstructionCode3
One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape OptimizationCode3
Anything-3D: Towards Single-view Anything Reconstruction in the WildCode3
BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown ObjectsCode3
SimpleRecon: 3D Reconstruction Without 3D ConvolutionsCode3
Point-NeRF: Point-based Neural Radiance FieldsCode3
SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature AlignmentCode2
Test3R: Learning to Reconstruct 3D at Test TimeCode2
StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video StreamsCode2
TetWeave: Isosurface Extraction using On-The-Fly Delaunay Tetrahedral Grids for Gradient-Based Mesh OptimizationCode2
GauSS-MI: Gaussian Splatting Shannon Mutual Information for Active 3D ReconstructionCode2
POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D ReconstructionCode2
InteractVLM: 3D Interaction Reasoning from 2D Foundational ModelsCode2
LandMarkSystem Technical ReportCode2
WideRange4D: Enabling High-Quality 4D Reconstruction with Wide-Range Movements and ScenesCode2
MegaLoc: One Retrieval to Place Them AllCode2
Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy VideoCode2
WeatherGS: 3D Scene Reconstruction in Adverse Weather Conditions via Gaussian SplattingCode2
MAC-Ego3D: Multi-Agent Gaussian Consensus for Real-Time Collaborative Ego-Motion and Photorealistic 3D ReconstructionCode2
From an Image to a Scene: Learning to Imagine the World from a Million 360 VideosCode2
Momentum-GS: Momentum Gaussian Self-Distillation for High-Quality Large Scene ReconstructionCode2
Refine3DNet: Scaling Precision in 3D Object Reconstruction from Multi-View RGB Images using AttentionCode2
SADG: Segment Any Dynamic Gaussian Without Object TrackersCode2
Boost 3D Reconstruction using Diffusion-based Monocular Camera CalibrationCode2
EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the WildCode2
SPARS3R: Semantic Prior Alignment and Regularization for Sparse 3D ReconstructionCode2
ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian SplattingsCode2
MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian SplattingCode2
Occupancy-Based Dual ContouringCode2
PartGS:Learning Part-aware 3D Representations by Fusing 2D Gaussians and SuperquadricsCode2
LumiGauss: Relightable Gaussian Splatting in the WildCode2
Deep Diffusion Image Prior for Efficient OOD Adaptation in 3D Inverse ProblemsCode2
iHuman: Instant Animatable Digital Humans From Monocular VideosCode2
Show:102550
← PrevPage 2 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