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 125 of 2326 papers

TitleStatusHype
TripoSR: Fast 3D Object Reconstruction from a Single ImageCode9
MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction PriorsCode7
Grounding Image Matching in 3D with MASt3RCode7
Instant Neural Graphics Primitives with a Multiresolution Hash EncodingCode6
Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse AttentionCode5
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow ModelsCode5
Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward PassCode5
Prompting Depth Anything for 4K Resolution Accurate Metric Depth EstimationCode5
SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB VideosCode5
Neural Fields in Robotics: A SurveyCode5
ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View SynthesisCode5
3D Reconstruction with Spatial MemoryCode5
PatchRefiner: Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth EstimationCode5
InstantSplat: Sparse-view SfM-free Gaussian Splatting in SecondsCode5
MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View ImagesCode5
Real3D-Portrait: One-shot Realistic 3D Talking Portrait SynthesisCode5
DUSt3R: Geometric 3D Vision Made EasyCode5
Structure-Aware Sparse-View X-ray 3D ReconstructionCode5
Infinite Photorealistic Worlds using Procedural GenerationCode5
RealFusion: 360° Reconstruction of Any Object from a Single ImageCode5
SpatialTrackerV2: 3D Point Tracking Made EasyCode4
UniK3D: Universal Camera Monocular 3D EstimationCode4
AGS-Mesh: Adaptive Gaussian Splatting and Meshing with Geometric Priors for Indoor Room Reconstruction Using SmartphonesCode4
No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed ImagesCode4
Lotus: Diffusion-based Visual Foundation Model for High-quality Dense PredictionCode4
Show:102550
← PrevPage 1 of 94Next →

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