HyperAI
HyperAI超神経
ホーム
ニュース
最新論文
チュートリアル
データセット
百科事典
SOTA
LLMモデル
GPU ランキング
学会
検索
サイトについて
日本語
HyperAI
HyperAI超神経
Toggle sidebar
サイトを検索…
⌘
K
ホーム
SOTA
3D再構成
3D Reconstruction On Dtu
3D Reconstruction On Dtu
評価指標
Acc
Comp
Overall
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
Columns
モデル名
Acc
Comp
Overall
Paper Title
Repository
TransMVSNet
0.321
0.289
0.305
TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers
UCSNet
0.338
0.349
0.344
Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness
-
EPP-MVSNet
0.413
0.296
0.355
EPP-MVSNet: Epipolar-Assembling Based Depth Prediction for Multi-View Stereo
COLMAP
0.400
0.664
0.532
Structure-From-Motion Revisited
ET-MVSNet
0.329
0.253
0.291
When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo
MVSNet
0.396
0.527
0.462
MVSNet: Depth Inference for Unstructured Multi-view Stereo
3D-R2N2
0.397
0.884
0.630
3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
CDS-MVSNet
0.351
0.278
0.315
Curvature-guided dynamic scale networks for Multi-view Stereo
Gipuma
0.283
0.873
0.578
Massively Parallel Multiview Stereopsis by Surface Normal Diffusion
-
GeoMVSNet
0.331
0.259
0.295
GeoMVSNet: Learning Multi-View Stereo With Geometry Perception
GoMVS
0.347
0.227
0.287
GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo
Cas-MVSNet
0.325
0.385
0.355
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
CVP-MVSNet
0.296
0.406
0.351
Cost Volume Pyramid Based Depth Inference for Multi-View Stereo
AA-RMVSNet
0.376
0.339
0.357
AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network
Vis-MVSNet
0.369
0.361
0.365
Visibility-aware Multi-view Stereo Network
GC-MVSNet
0.330
0.260
0.295
GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View Stereo
IB-MVS
0.334
0.309
0.321
IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions
-
RA-MVSNet
0.326
0.268
0.297
Multi-View Stereo Representation Revisit: Region-Aware MVSNet
-
GBi-Net
0.312
0.293
0.303
Generalized Binary Search Network for Highly-Efficient Multi-View Stereo
MVSFormer++
0.3090
0.2521
0.2805
MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo
0 of 24 row(s) selected.
Previous
Next
3D Reconstruction On Dtu | SOTA | HyperAI超神経