HyperAI

3D Reconstruction On Dtu

Metrics

Acc
Comp
Overall

Results

Performance results of various models on this benchmark

Model Name
Acc
Comp
Overall
Paper TitleRepository
TransMVSNet0.3210.2890.305TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers
UCSNet0.3380.3490.344Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness-
EPP-MVSNet0.4130.2960.355EPP-MVSNet: Epipolar-Assembling Based Depth Prediction for Multi-View Stereo
COLMAP0.4000.6640.532Structure-From-Motion Revisited
ET-MVSNet0.3290.2530.291When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo
MVSNet0.3960.5270.462MVSNet: Depth Inference for Unstructured Multi-view Stereo
3D-R2N20.3970.8840.6303D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
CDS-MVSNet0.3510.2780.315Curvature-guided dynamic scale networks for Multi-view Stereo
Gipuma0.2830.8730.578Massively Parallel Multiview Stereopsis by Surface Normal Diffusion-
GeoMVSNet0.3310.2590.295GeoMVSNet: Learning Multi-View Stereo With Geometry Perception
GoMVS0.3470.2270.287GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo
Cas-MVSNet0.3250.3850.355Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
CVP-MVSNet0.2960.4060.351Cost Volume Pyramid Based Depth Inference for Multi-View Stereo
AA-RMVSNet0.3760.3390.357AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network
Vis-MVSNet0.3690.3610.365Visibility-aware Multi-view Stereo Network
GC-MVSNet0.3300.2600.295GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View Stereo
IB-MVS0.3340.3090.321IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions-
RA-MVSNet0.3260.2680.297Multi-View Stereo Representation Revisit: Region-Aware MVSNet-
GBi-Net0.3120.2930.303Generalized Binary Search Network for Highly-Efficient Multi-View Stereo
MVSFormer++0.30900.25210.2805MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo
0 of 24 row(s) selected.