High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

GG-mvs-BLEND				99.59 157	99.54 230	99.49 146	99.17 394	99.52 72		99.96 138	99.68 295	100.00 1	99.33 289	99.71 157	99.99 103	99.96 130

gg-mvs-nofinetune		96.95 280	96.10 302	99.50 169	99.41 270	99.36 163	99.07 408	99.52 72	83.69 418	99.96 138	83.60 434	100.00 1	99.20 295	99.68 168	99.99 103	99.96 130

reproduce_monomvs		98.61 193	98.54 189	98.82 234	99.97 90	99.28 169	100.00 1	99.33 243	98.51 87	97.87 332	99.24 345	99.98 3	99.45 278	99.02 228	92.93 329	97.74 322

CHOSEN 280x420		99.85 3	99.87 1	99.80 114	99.99 49	99.97 21	99.97 264	99.98 16	98.96 34	100.00 1	100.00 1	99.96 4	99.42 282	100.00 1	100.00 1	100.00 1

GDP-MVS		99.39 88	99.26 97	99.77 126	99.53 233	99.55 130	100.00 1	99.11 348	97.14 207	99.96 138	100.00 1	99.83 5	99.89 191	98.47 258	99.26 178	99.87 198

test_yl		99.51 71	99.37 81	99.95 54	99.82 126	99.90 63	100.00 1	99.47 79	97.48 180	100.00 1	100.00 1	99.80 6	100.00 1	99.98 84	97.75 255	99.94 141

DCV-MVSNet		99.51 71	99.37 81	99.95 54	99.82 126	99.90 63	100.00 1	99.47 79	97.48 180	100.00 1	100.00 1	99.80 6	100.00 1	99.98 84	97.75 255	99.94 141

UWE-MVS		99.18 126	99.06 126	99.51 166	99.67 182	98.80 211	100.00 1	99.43 125	96.80 236	99.93 174	99.86 258	99.79 8	99.94 179	97.78 287	98.33 215	99.80 240

patch_mono-2		99.04 140	99.79 6	96.81 349	99.92 108	90.47 400	100.00 1	99.41 193	98.95 37	100.00 1	100.00 1	99.78 9	100.00 1	100.00 1	100.00 1	99.95 136

MVSTER		98.58 196	98.52 192	98.77 239	99.65 192	99.68 114	100.00 1	99.29 266	95.63 301	98.65 282	99.80 276	99.78 9	98.88 320	98.59 254	95.31 292	97.73 329

CDS-MVSNet		98.96 161	98.95 143	99.01 223	99.48 256	98.36 241	99.93 284	99.37 217	96.79 237	99.31 241	99.83 266	99.77 11	98.91 314	98.07 276	97.98 236	99.77 249
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PAPM		99.78 16	99.76 12	99.85 96	99.01 308	99.95 32	100.00 1	99.75 52	99.37 3	99.99 118	100.00 1	99.76 12	99.60 240	100.00 1	100.00 1	100.00 1

BP-MVS1		99.56 67	99.48 72	99.79 118	99.48 256	99.61 121	100.00 1	99.32 246	97.34 193	99.94 168	100.00 1	99.74 13	99.89 191	99.75 147	99.72 159	99.87 198

DP-MVS Recon		99.76 18	99.69 22	99.98 23	100.00 1	99.95 32	100.00 1	99.52 72	97.99 123	99.99 118	100.00 1	99.72 14	100.00 1	99.96 97	100.00 1	100.00 1

TESTMET0.1,1		99.08 135	98.96 139	99.44 177	99.63 200	99.38 159	100.00 1	99.45 103	95.53 305	99.48 225	100.00 1	99.71 15	99.02 302	96.84 317	99.99 103	99.91 157

test-mter		98.96 161	98.82 156	99.40 187	99.40 275	99.28 169	100.00 1	99.45 103	95.44 316	99.42 230	99.12 351	99.70 16	99.01 303	96.82 318	99.99 103	99.91 157

WBMVS		98.19 227	98.10 224	98.47 253	99.63 200	99.03 194	100.00 1	99.32 246	95.46 312	98.39 300	99.40 336	99.69 17	98.61 339	98.64 248	92.39 337	97.76 289

UBG		99.36 95	99.27 93	99.63 150	99.63 200	99.01 198	100.00 1	99.43 125	96.99 220	100.00 1	99.92 247	99.69 17	99.99 100	99.74 148	98.06 233	99.88 187

MSP-MVS		99.81 11	99.77 9	99.94 66	100.00 1	99.86 82	100.00 1	99.42 144	98.87 55	100.00 1	100.00 1	99.65 19	99.96 154	100.00 1	100.00 1	100.00 1
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
test_0728_THIRD									98.79 71	100.00 1	100.00 1	99.61 20	100.00 1	100.00 1	100.00 1	100.00 1

test_one_0601					100.00 1	99.99 5		99.42 144	98.72 76	100.00 1	100.00 1	99.60 21

MSLP-MVS++		99.89 1	99.85 2	99.99 12	100.00 1	99.96 24	100.00 1	99.95 19	99.11 8	100.00 1	100.00 1	99.60 21	100.00 1	100.00 1	100.00 1	100.00 1

PAPM_NR		99.74 25	99.66 33	99.99 12	100.00 1	99.96 24	100.00 1	99.47 79	97.87 136	100.00 1	100.00 1	99.60 21	100.00 1	100.00 1	100.00 1	100.00 1

NCCC		99.86 2	99.82 3	100.00 1	100.00 1	99.99 5	100.00 1	99.71 61	99.07 11	100.00 1	100.00 1	99.59 24	100.00 1	100.00 1	100.00 1	100.00 1

PLC	98.56 2	99.70 36	99.74 16	99.58 161	100.00 1	98.79 212	100.00 1	99.54 71	98.58 84	99.96 138	100.00 1	99.59 24	100.00 1	100.00 1	100.00 1	99.94 141
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
DPM-MVS		99.63 54	99.51 66	100.00 1	99.90 112	100.00 1	100.00 1	99.43 125	99.00 27	100.00 1	100.00 1	99.58 26	100.00 1	97.64 291	100.00 1	100.00 1

test_241102_TWO								99.42 144	99.03 21	100.00 1	100.00 1	99.56 27	100.00 1	100.00 1	100.00 1	100.00 1

APDe-MVS		99.84 6	99.78 7	99.99 12	100.00 1	99.98 17	100.00 1	99.44 117	99.06 13	100.00 1	100.00 1	99.56 27	99.99 100	100.00 1	100.00 1	100.00 1
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
segment_acmp												99.55 29

DVP-MVS++		99.81 11	99.75 14	100.00 1	100.00 1	99.99 5	100.00 1	99.42 144	98.79 71	100.00 1	100.00 1	99.54 30	100.00 1	100.00 1	100.00 1	100.00 1

PC_three_1452									98.80 68	100.00 1	100.00 1	99.54 30	100.00 1	100.00 1	100.00 1	100.00 1

OPU-MVS				100.00 1	100.00 1	100.00 1	100.00 1				100.00 1	99.54 30	100.00 1	100.00 1	100.00 1	100.00 1

DVP-MVS		99.83 7	99.78 7	100.00 1	100.00 1	99.99 5	100.00 1	99.42 144	99.04 16	100.00 1	100.00 1	99.53 33	100.00 1	100.00 1	100.00 1	100.00 1
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test0726					100.00 1	99.99 5	100.00 1	99.42 144	99.04 16	100.00 1	100.00 1	99.53 33

TEST9					100.00 1	99.95 32	100.00 1	99.42 144	97.65 154	100.00 1	100.00 1	99.53 33	99.97 137

SteuartSystems-ACMMP		99.78 16	99.71 20	99.98 23	99.76 157	99.95 32	100.00 1	99.42 144	98.69 77	100.00 1	100.00 1	99.52 36	99.99 100	100.00 1	100.00 1	100.00 1
Skip Steuart: Steuart Systems R&D Blog.
train_agg		99.71 33	99.63 41	99.97 34	100.00 1	99.95 32	100.00 1	99.42 144	97.70 149	100.00 1	100.00 1	99.51 37	99.97 137	100.00 1	100.00 1	100.00 1

test_8					100.00 1	99.91 56	100.00 1	99.42 144	97.70 149	100.00 1	100.00 1	99.51 37	99.98 130

PAPR		99.76 18	99.68 28	99.99 12	100.00 1	99.96 24	100.00 1	99.47 79	98.16 109	100.00 1	100.00 1	99.51 37	100.00 1	100.00 1	100.00 1	100.00 1

EPP-MVSNet		99.10 134	99.00 133	99.40 187	99.51 246	98.68 220	99.92 286	99.43 125	95.47 311	99.65 217	100.00 1	99.51 37	99.76 227	99.53 197	98.00 234	99.75 252

SED-MVS		99.83 7	99.77 9	100.00 1	100.00 1	99.99 5	100.00 1	99.42 144	99.03 21	100.00 1	100.00 1	99.50 41	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_ONE					100.00 1	99.99 5		99.42 144	99.03 21	100.00 1	100.00 1	99.50 41	100.00 1

miper_enhance_ethall		98.33 218	98.27 210	98.51 251	99.66 190	99.04 193	100.00 1	99.22 307	97.53 173	98.51 294	99.38 337	99.49 43	98.75 330	98.02 278	92.61 332	97.76 289

test_post											89.05 427	99.49 43	99.59 242

HyFIR lowres test		99.32 104	99.24 102	99.58 161	99.95 100	99.26 172	100.00 1	99.99 13	96.72 246	99.29 242	99.91 250	99.49 43	99.47 273	99.74 148	98.08 231	100.00 1

PatchmatchNet		99.03 142	98.96 139	99.26 209	99.49 254	98.33 244	99.38 368	99.45 103	96.64 255	99.96 138	99.58 318	99.49 43	99.50 269	97.63 292	99.00 186	99.93 152
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
testing3-2		99.45 81	99.31 89	99.86 92	99.70 166	99.73 104	100.00 1	99.47 79	97.46 182	99.97 131	99.97 212	99.48 47	100.00 1	99.78 139	97.99 235	99.85 203

Patchmatch-test		97.83 238	97.42 250	99.06 217	99.08 299	97.66 289	98.66 416	99.21 313	93.65 357	98.25 313	99.58 318	99.47 48	99.57 247	90.25 394	98.59 195	99.95 136

test_prior2							100.00 1		98.82 63	100.00 1	100.00 1	99.47 48		100.00 1	100.00 1

TSAR-MVS + MP.		99.82 9	99.77 9	99.99 12	100.00 1	99.96 24	100.00 1	99.43 125	99.05 15	100.00 1	100.00 1	99.45 50	99.99 100	100.00 1	100.00 1	100.00 1
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
thisisatest0530		99.37 94	99.27 93	99.69 140	99.59 216	99.41 157	100.00 1	99.46 95	96.46 265	99.90 180	100.00 1	99.44 51	99.85 206	98.97 229	99.58 171	99.80 240

tttt0517		99.34 99	99.23 105	99.67 144	99.57 225	99.38 159	100.00 1	99.46 95	96.33 277	99.89 183	100.00 1	99.44 51	99.84 209	98.93 231	99.46 175	99.78 248

thisisatest0515		99.42 85	99.31 89	99.74 130	99.59 216	99.55 130	100.00 1	99.46 95	96.65 254	99.92 175	100.00 1	99.44 51	99.85 206	99.09 225	99.63 169	99.81 223

PGM-MVS		99.69 39	99.61 45	99.95 54	99.99 49	99.85 85	100.00 1	99.58 67	97.69 151	100.00 1	100.00 1	99.44 51	100.00 1	99.79 133	100.00 1	100.00 1

UWE-MVS-28		99.29 110	99.23 105	99.48 172	99.73 162	98.86 208	100.00 1	99.43 125	96.97 222	99.99 118	99.83 266	99.43 55	99.77 224	99.35 206	98.31 217	99.80 240

testing11		99.26 115	99.19 112	99.46 174	99.64 198	98.61 224	100.00 1	99.43 125	96.94 224	99.92 175	99.94 242	99.43 55	99.97 137	99.67 171	97.79 253	99.82 214

SMA-MVS		99.69 39	99.59 47	99.98 23	99.99 49	99.93 47	100.00 1	99.43 125	97.50 178	100.00 1	100.00 1	99.43 55	100.00 1	100.00 1	100.00 1	100.00 1
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
原ACMM1				99.93 70	100.00 1	99.80 92		99.66 63	98.18 108	100.00 1	100.00 1	99.43 55	100.00 1	99.50 199	100.00 1	100.00 1

testdata				99.66 147	99.99 49	98.97 205		99.73 56	97.96 130	100.00 1	100.00 1	99.42 59	100.00 1	99.28 213	100.00 1	100.00 1

baseline2		98.99 154	98.93 146	99.18 214	99.26 288	99.15 186	100.00 1	99.46 95	96.71 247	96.79 365	100.00 1	99.42 59	99.25 293	98.75 242	99.94 126	99.15 276

myMVS_eth3d28		99.41 86	99.28 91	99.80 114	99.69 169	99.53 135	100.00 1	99.43 125	97.12 211	99.98 125	99.97 212	99.41 61	100.00 1	99.81 132	98.07 232	99.88 187

patchmatchnet-post											97.79 402	99.41 61	99.54 259

Patchmatch-RL test		93.49 359	93.63 356	93.05 390	91.78 421	83.41 416	98.21 420	96.95 426	91.58 387	91.05 405	97.64 405	99.40 63	95.83 415	94.11 361	81.95 411	99.91 157

CNVR-MVS		99.85 3	99.80 4	100.00 1	100.00 1	99.99 5	100.00 1	99.77 48	99.07 11	100.00 1	100.00 1	99.39 64	100.00 1	100.00 1	100.00 1	100.00 1

FE-MVS		99.16 129	98.99 135	99.66 147	99.65 192	99.18 183	99.58 347	99.43 125	95.24 317	99.91 178	99.59 316	99.37 65	99.97 137	98.31 265	99.81 153	99.83 209

sam_mvs												99.33 66

test_post1							99.32 373				88.24 429	99.33 66	99.59 242	98.31 265

SD-MVS		99.81 11	99.75 14	99.99 12	99.99 49	99.96 24	100.00 1	99.42 144	99.01 26	100.00 1	100.00 1	99.33 66	100.00 1	100.00 1	100.00 1	100.00 1
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
ZD-MVS					100.00 1	99.98 17		99.80 43	97.31 198	100.00 1	100.00 1	99.32 69	99.99 100	100.00 1	100.00 1

CDPH-MVS		99.73 28	99.64 37	99.99 12	100.00 1	99.97 21	100.00 1	99.42 144	98.02 121	100.00 1	100.00 1	99.32 69	99.99 100	100.00 1	100.00 1	100.00 1

HFP-MVS		99.74 25	99.67 30	99.96 45	100.00 1	99.89 70	100.00 1	99.76 49	97.95 131	100.00 1	100.00 1	99.31 71	100.00 1	99.99 69	100.00 1	100.00 1

test-LLR		99.03 142	98.91 148	99.40 187	99.40 275	99.28 169	100.00 1	99.45 103	96.70 248	99.42 230	99.12 351	99.31 71	99.01 303	96.82 318	99.99 103	99.91 157

test0.0.03 1		98.12 229	98.03 230	98.39 260	99.11 295	98.07 263	100.00 1	99.93 30	96.70 248	96.91 361	99.95 236	99.31 71	98.19 368	91.93 379	98.44 202	98.91 280

MCST-MVS		99.85 3	99.80 4	100.00 1	100.00 1	99.99 5	100.00 1	99.73 56	99.19 5	100.00 1	100.00 1	99.31 71	100.00 1	100.00 1	100.00 1	100.00 1

TAPA-MVS	96.40 10	97.64 245	97.37 254	98.45 256	99.94 103	95.70 337	100.00 1	99.40 197	97.65 154	99.53 221	100.00 1	99.31 71	99.66 237	80.48 421	100.00 1	100.00 1
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					99.99 49	99.90 63	100.00 1	99.69 62	97.66 153	100.00 1	100.00 1	99.30 76			100.00 1	100.00 1

sam_mvs1												99.29 77				99.91 157

ACMMPR		99.74 25	99.67 30	99.96 45	100.00 1	99.89 70	100.00 1	99.76 49	97.95 131	100.00 1	100.00 1	99.29 77	100.00 1	99.99 69	100.00 1	100.00 1

CostFormer		98.84 174	98.77 161	99.04 221	99.41 270	97.58 291	99.67 337	99.35 234	94.66 330	99.96 138	99.36 339	99.28 79	99.74 230	99.41 203	97.81 250	99.81 223

旧先验1					99.99 49	99.88 77		99.82 40			100.00 1	99.27 80			100.00 1	100.00 1

APD-MVS		99.68 43	99.58 49	99.97 34	99.99 49	99.96 24	100.00 1	99.42 144	97.53 173	100.00 1	100.00 1	99.27 80	99.97 137	100.00 1	100.00 1	100.00 1
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test12				99.95 54	99.99 49	99.89 70		99.42 144		100.00 1		99.24 82	99.97 137		100.00 1	100.00 1

DPE-MVS		99.79 14	99.73 17	99.99 12	99.99 49	99.98 17	100.00 1	99.42 144	98.91 47	100.00 1	100.00 1	99.22 83	100.00 1	100.00 1	100.00 1	100.00 1
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
HPM-MVS++		99.82 9	99.76 12	99.99 12	99.99 49	99.98 17	100.00 1	99.83 39	98.88 52	99.96 138	100.00 1	99.21 84	100.00 1	100.00 1	100.00 1	99.99 114

新几何1				99.99 12	100.00 1	99.96 24		99.81 42	97.89 134	100.00 1	100.00 1	99.20 85	100.00 1	97.91 283	100.00 1	100.00 1

region2R		99.72 29	99.64 37	99.97 34	100.00 1	99.90 63	100.00 1	99.74 55	97.86 137	100.00 1	100.00 1	99.19 86	100.00 1	99.99 69	100.00 1	100.00 1

F-COLMAP		99.64 51	99.64 37	99.67 144	99.99 49	99.07 189	100.00 1	99.44 117	98.30 102	99.90 180	100.00 1	99.18 87	99.99 100	99.91 110	100.00 1	99.94 141

XVS		99.79 14	99.73 17	99.98 23	100.00 1	99.94 41	100.00 1	99.75 52	98.67 79	100.00 1	100.00 1	99.16 88	100.00 1	100.00 1	100.00 1	100.00 1

X-MVStestdata		97.04 275	96.06 304	99.98 23	100.00 1	99.94 41	100.00 1	99.75 52	98.67 79	100.00 1	66.97 437	99.16 88	100.00 1	100.00 1	100.00 1	100.00 1

9.14			99.57 52		99.99 49		100.00 1	99.42 144	97.54 171	100.00 1	100.00 1	99.15 90	99.99 100	100.00 1	100.00 1

CNLPA		99.72 29	99.65 34	99.91 75	99.97 90	99.72 106	100.00 1	99.47 79	98.43 91	99.88 185	100.00 1	99.14 91	100.00 1	99.97 95	100.00 1	100.00 1

testing3		98.44 209	98.37 205	98.65 243	99.51 246	98.32 246	100.00 1	99.62 66	96.43 266	97.93 328	99.99 198	99.11 92	97.81 391	94.88 351	97.80 251	99.82 214

Test By Simon												99.10 93

myMVS_eth3d		98.52 204	98.51 194	98.53 250	99.50 250	97.98 270	100.00 1	99.57 68	96.23 280	98.07 319	100.00 1	99.09 94	97.81 391	96.17 331	97.96 238	99.82 214

CP-MVS		99.67 46	99.58 49	99.95 54	100.00 1	99.84 87	100.00 1	99.42 144	97.77 144	100.00 1	100.00 1	99.07 95	100.00 1	100.00 1	100.00 1	100.00 1

testing99		99.18 126	99.10 123	99.41 183	99.60 212	98.43 231	100.00 1	99.43 125	96.76 239	99.84 189	99.92 247	99.06 96	99.98 130	99.62 181	97.67 259	99.81 223

alignmvs		99.38 91	99.21 107	99.91 75	99.73 162	99.92 53	100.00 1	99.51 76	97.61 163	100.00 1	100.00 1	99.06 96	99.93 183	99.83 125	97.12 267	99.90 168

testing91		99.18 126	99.10 123	99.41 183	99.60 212	98.43 231	100.00 1	99.43 125	96.76 239	99.82 200	99.92 247	99.05 98	99.98 130	99.62 181	97.67 259	99.81 223

SF-MVS		99.66 48	99.57 52	99.95 54	99.99 49	99.85 85	100.00 1	99.42 144	97.67 152	100.00 1	100.00 1	99.05 98	99.99 100	100.00 1	100.00 1	100.00 1

EPMVS		99.25 119	99.13 119	99.60 155	99.60 212	99.20 180	99.60 345	100.00 1	96.93 225	99.92 175	99.36 339	99.05 98	99.71 234	98.77 240	98.94 187	99.90 168

EI-MVSNet-Vis-set		99.70 36	99.64 37	99.87 89	100.00 1	99.64 118	99.98 258	99.44 117	98.35 99	99.99 118	100.00 1	99.04 101	99.96 154	99.98 84	100.00 1	100.00 1

mPP-MVS		99.69 39	99.60 46	99.97 34	100.00 1	99.91 56	100.00 1	99.42 144	97.91 133	100.00 1	100.00 1	99.04 101	100.00 1	100.00 1	100.00 1	100.00 1

tpmrst		98.98 158	98.93 146	99.14 216	99.61 209	97.74 286	99.52 354	99.36 223	96.05 288	99.98 125	99.64 304	99.04 101	99.86 200	98.94 230	98.19 226	99.82 214

reproduce-ours		99.76 18	99.69 22	99.98 23	99.96 96	99.94 41	100.00 1	99.42 144	98.82 63	100.00 1	100.00 1	98.99 104	100.00 1	100.00 1	100.00 1	100.00 1

our_new_method		99.76 18	99.69 22	99.98 23	99.96 96	99.94 41	100.00 1	99.42 144	98.82 63	100.00 1	100.00 1	98.99 104	100.00 1	100.00 1	100.00 1	100.00 1

SR-MVS		99.68 43	99.58 49	99.98 23	100.00 1	99.95 32	100.00 1	99.64 64	97.59 167	100.00 1	100.00 1	98.99 104	99.99 100	100.00 1	100.00 1	100.00 1

reproduce_model		99.76 18	99.69 22	99.98 23	99.96 96	99.93 47	100.00 1	99.42 144	98.81 67	100.00 1	100.00 1	98.98 107	100.00 1	100.00 1	100.00 1	100.00 1

EI-MVSNet-UG-set		99.69 39	99.63 41	99.87 89	99.99 49	99.64 118	99.95 276	99.44 117	98.35 99	100.00 1	100.00 1	98.98 107	99.97 137	99.98 84	100.00 1	100.00 1

ZNCC-MVS		99.71 33	99.62 44	99.97 34	99.99 49	99.90 63	100.00 1	99.79 45	97.97 127	99.97 131	100.00 1	98.97 109	100.00 1	99.94 105	100.00 1	100.00 1

APD-MVS_3200maxsize		99.65 49	99.55 59	99.97 34	99.99 49	99.91 56	100.00 1	99.48 78	97.54 171	100.00 1	100.00 1	98.97 109	99.99 100	99.98 84	100.00 1	100.00 1

EPNet		99.62 59	99.69 22	99.42 182	99.99 49	98.37 239	100.00 1	99.89 37	98.83 61	100.00 1	100.00 1	98.97 109	100.00 1	99.90 111	99.61 170	99.89 174
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tpm2		98.64 189	98.58 186	98.81 237	99.42 268	97.12 311	99.69 334	99.37 217	93.63 358	99.94 168	99.67 296	98.96 112	99.47 273	98.62 252	97.95 240	99.83 209

TSAR-MVS + GP.		99.61 61	99.69 22	99.35 194	99.99 49	98.06 265	100.00 1	99.36 223	99.83 2	100.00 1	100.00 1	98.95 113	99.99 100	100.00 1	99.11 182	100.00 1

HPM-MVS_fast		99.60 64	99.49 69	99.91 75	99.99 49	99.78 94	100.00 1	99.42 144	97.09 212	100.00 1	100.00 1	98.95 113	99.96 154	99.98 84	100.00 1	100.00 1

RE-MVS-def			99.55 59		99.99 49	99.91 56	100.00 1	99.42 144	97.62 159	100.00 1	100.00 1	98.94 115		99.99 69	100.00 1	100.00 1

WTY-MVS		99.54 70	99.40 76	99.95 54	99.81 132	99.93 47	100.00 1	100.00 1	97.98 125	99.84 189	100.00 1	98.94 115	99.98 130	99.86 119	98.21 224	99.94 141

HY-MVS	96.53 9	99.50 74	99.35 86	99.96 45	99.81 132	99.93 47	99.64 339	100.00 1	97.97 127	99.84 189	99.85 263	98.94 115	99.99 100	99.86 119	98.23 223	99.95 136

MDTV_nov1_ep13			98.94 144		99.53 233	98.36 241	99.39 367	99.46 95	96.54 260	99.99 118	99.63 308	98.92 118	99.86 200	98.30 268	98.71 194

API-MVS		99.72 29	99.70 21	99.79 118	99.97 90	99.37 162	99.96 270	99.94 22	98.48 88	100.00 1	100.00 1	98.92 118	100.00 1	100.00 1	100.00 1	100.00 1

ACMMP		99.65 49	99.57 52	99.89 82	99.99 49	99.66 116	99.75 321	99.73 56	98.16 109	99.75 210	100.00 1	98.90 120	100.00 1	99.96 97	99.88 139	100.00 1
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
ACMMP_NAP		99.67 46	99.57 52	99.97 34	99.98 86	99.92 53	100.00 1	99.42 144	97.83 138	100.00 1	100.00 1	98.89 121	100.00 1	99.98 84	100.00 1	100.00 1

test2506		99.48 78	99.38 78	99.75 129	99.89 114	99.51 140	99.45 360	100.00 1	98.38 93	99.83 192	100.00 1	98.86 122	99.81 216	99.25 214	98.78 190	99.94 141

MDTV_nov1_ep13_2view						99.24 176	99.56 349		96.31 278	99.96 138		98.86 122		98.92 232		99.89 174

KD-MVS_2432*1600		94.15 353	93.08 362	97.35 322	99.53 233	97.83 283	99.63 341	99.19 317	92.88 377	96.29 373	97.68 403	98.84 124	96.70 403	89.73 396	63.92 427	97.53 373

miper_refine_blended		94.15 353	93.08 362	97.35 322	99.53 233	97.83 283	99.63 341	99.19 317	92.88 377	96.29 373	97.68 403	98.84 124	96.70 403	89.73 396	63.92 427	97.53 373

dp		98.72 182	98.61 182	99.03 222	99.53 233	97.39 297	99.45 360	99.39 210	95.62 302	99.94 168	99.52 327	98.83 126	99.82 213	96.77 323	98.42 204	99.89 174

TAMVS		98.76 179	98.73 166	98.86 233	99.44 266	97.69 287	99.57 348	99.34 241	96.57 258	99.12 252	99.81 273	98.83 126	99.16 296	97.97 282	97.91 242	99.73 257

IB-MVS	96.24 12	97.54 252	96.95 267	99.33 198	99.67 182	98.10 261	100.00 1	99.47 79	97.42 187	99.26 243	99.69 291	98.83 126	99.89 191	99.43 201	78.77 418	100.00 1
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
DeepC-MVS_fast	98.92 1	99.75 23	99.67 30	99.99 12	99.99 49	99.96 24	99.73 327	99.52 72	99.06 13	100.00 1	100.00 1	98.80 129	100.00 1	99.95 103	100.00 1	100.00 1
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MP-MVS-pluss		99.61 61	99.50 67	99.97 34	99.98 86	99.92 53	100.00 1	99.42 144	97.53 173	99.77 207	100.00 1	98.77 130	100.00 1	99.99 69	100.00 1	99.99 114
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
pcd_1.5k_mvsjas		8.24 407	10.99 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.14 440	98.75 131	0.00 440	0.00 439	0.00 438	0.00 436

PS-MVSNAJss		98.03 232	98.06 228	97.94 302	97.63 379	97.33 303	99.89 294	99.23 303	96.27 279	98.03 322	99.59 316	98.75 131	98.78 325	98.52 256	94.61 315	97.70 344

PS-MVSNAJ		99.64 51	99.57 52	99.85 96	99.78 154	99.81 90	99.95 276	99.42 144	98.38 93	100.00 1	100.00 1	98.75 131	100.00 1	99.88 115	99.99 103	99.74 253

dcpmvs_2		98.87 172	99.53 62	96.90 343	99.87 118	90.88 399	99.94 281	99.07 362	98.20 107	100.00 1	100.00 1	98.69 134	99.86 200	100.00 1	100.00 1	99.95 136

ETVMVS		99.16 129	98.98 136	99.69 140	99.67 182	99.56 128	100.00 1	99.45 103	96.36 274	99.98 125	99.95 236	98.65 135	99.64 238	99.11 224	97.63 262	99.88 187

SR-MVS-dyc-post		99.63 54	99.52 64	99.97 34	99.99 49	99.91 56	100.00 1	99.42 144	97.62 159	100.00 1	100.00 1	98.65 135	99.99 100	99.99 69	100.00 1	100.00 1

MTAPA		99.68 43	99.59 47	99.97 34	99.99 49	99.91 56	100.00 1	99.42 144	98.32 101	99.94 168	100.00 1	98.65 135	100.00 1	99.96 97	100.00 1	100.00 1

HPM-MVS		99.59 65	99.50 67	99.89 82	100.00 1	99.70 111	100.00 1	99.42 144	97.46 182	100.00 1	100.00 1	98.60 138	99.96 154	99.99 69	100.00 1	100.00 1
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MG-MVS		99.75 23	99.68 28	99.97 34	100.00 1	99.91 56	99.98 258	99.47 79	99.09 10	100.00 1	100.00 1	98.59 139	100.00 1	99.95 103	100.00 1	100.00 1

EPNet_dtu		98.53 203	98.23 217	99.43 180	99.92 108	99.01 198	99.96 270	99.47 79	98.80 68	99.96 138	99.96 229	98.56 140	99.30 290	87.78 406	99.68 162	100.00 1
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing222		99.14 131	98.94 144	99.73 133	99.67 182	99.51 140	100.00 1	99.43 125	96.90 230	99.99 118	99.90 252	98.55 141	99.86 200	98.85 235	97.18 266	99.81 223

JIA-IIPM		97.09 271	96.34 293	99.36 193	98.88 325	98.59 226	99.81 306	99.43 125	84.81 416	99.96 138	90.34 426	98.55 141	99.52 265	97.00 312	98.28 219	99.98 117

xiu_mvs_v2_base		99.51 71	99.41 75	99.82 104	99.70 166	99.73 104	99.92 286	99.40 197	98.15 111	100.00 1	100.00 1	98.50 143	100.00 1	99.85 121	99.13 181	99.74 253

sss		99.45 81	99.34 88	99.80 114	99.76 157	99.50 142	100.00 1	99.91 35	97.72 147	99.98 125	99.94 242	98.45 144	100.00 1	99.53 197	98.75 193	99.89 174

IS-MVSNet		99.08 135	98.91 148	99.59 157	99.65 192	99.38 159	99.78 312	99.24 299	96.70 248	99.51 223	100.00 1	98.44 145	99.52 265	98.47 258	98.39 207	99.88 187

GST-MVS		99.64 51	99.53 62	99.95 54	100.00 1	99.86 82	100.00 1	99.79 45	97.72 147	99.95 166	100.00 1	98.39 146	100.00 1	99.96 97	99.99 103	100.00 1

114514_t		99.39 88	99.25 99	99.81 109	99.97 90	99.48 150	100.00 1	99.42 144	95.53 305	100.00 1	100.00 1	98.37 147	99.95 167	99.97 95	100.00 1	100.00 1

baseline1		98.91 168	98.61 182	99.81 109	99.71 164	99.77 97	99.78 312	99.44 117	97.51 177	98.81 275	99.99 198	98.25 148	99.76 227	98.60 253	95.41 288	99.89 174

MP-MVS		99.61 61	99.49 69	99.98 23	99.99 49	99.94 41	100.00 1	99.42 144	97.82 139	99.99 118	100.00 1	98.20 149	100.00 1	99.99 69	100.00 1	100.00 1
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
miper_ehance_all_eth		97.81 239	97.66 244	98.23 272	99.49 254	98.37 239	99.99 232	99.11 348	94.78 325	98.25 313	99.21 348	98.18 150	98.57 347	97.35 305	92.61 332	97.76 289

PHI-MVS		99.50 74	99.39 77	99.82 104	100.00 1	99.45 152	100.00 1	99.94 22	96.38 272	100.00 1	100.00 1	98.18 150	100.00 1	100.00 1	100.00 1	100.00 1

Vis-MVSNet (Re-imp)		98.99 154	98.89 152	99.29 203	99.64 198	98.89 207	99.98 258	99.31 253	96.74 243	99.48 225	100.00 1	98.11 152	99.10 298	98.39 261	98.34 212	99.89 174

DeepPCF-MVS	98.03 4	98.54 202	99.72 19	94.98 375	99.99 49	84.94 414	100.00 1	99.42 144	99.98 1	100.00 1	100.00 1	98.11 152	100.00 1	100.00 1	100.00 1	100.00 1

cl22		98.23 226	98.11 222	98.58 249	99.82 126	99.01 198	100.00 1	99.28 272	96.92 227	98.33 305	99.21 348	98.09 154	98.97 309	98.72 243	92.61 332	97.76 289

mvsany_test1		99.57 66	99.48 72	99.85 96	99.86 119	99.54 133	100.00 1	99.36 223	98.94 40	100.00 1	100.00 1	97.97 155	100.00 1	99.88 115	99.28 177	100.00 1

PatchT		95.90 333	94.95 348	98.75 240	99.03 306	98.39 236	99.08 406	99.32 246	85.52 414	99.96 138	94.99 418	97.94 156	98.05 384	80.20 422	98.47 201	99.81 223

MVS_111021_LR		99.70 36	99.65 34	99.88 87	99.96 96	99.70 111	100.00 1	99.97 17	98.96 34	100.00 1	100.00 1	97.93 157	99.95 167	99.99 69	100.00 1	100.00 1

fmvsm_l_conf0.5_n		99.63 54	99.56 57	99.86 92	99.81 132	99.59 124	100.00 1	99.36 223	98.98 30	100.00 1	100.00 1	97.92 158	99.99 100	100.00 1	99.95 122	100.00 1

balanced_conf03		99.43 84	99.28 91	99.85 96	99.68 174	99.68 114	99.97 264	99.28 272	97.03 217	99.96 138	99.97 212	97.90 159	99.93 183	99.77 141	100.00 1	99.94 141

MVSMamba_PlusPlus		99.39 88	99.25 99	99.80 114	99.68 174	99.59 124	99.99 232	99.30 259	96.66 253	99.96 138	99.97 212	97.89 160	99.92 186	99.76 143	100.00 1	99.90 168

c3_l		97.58 249	97.42 250	98.06 290	99.48 256	98.16 255	99.96 270	99.10 351	94.54 334	98.13 317	99.20 350	97.87 161	98.25 366	97.28 306	91.20 359	97.75 300

fmvsm_l_conf0.5_n_a		99.63 54	99.55 59	99.86 92	99.83 124	99.58 126	100.00 1	99.36 223	98.98 30	100.00 1	100.00 1	97.85 162	99.99 100	100.00 1	99.94 126	100.00 1

MVS_111021_HR		99.71 33	99.63 41	99.93 70	99.95 100	99.83 88	100.00 1	100.00 1	98.89 51	100.00 1	100.00 1	97.85 162	99.95 167	100.00 1	100.00 1	100.00 1

FA-MVS(test-final)		99.00 150	98.75 163	99.73 133	99.63 200	99.43 155	99.83 302	99.43 125	95.84 297	99.52 222	99.37 338	97.84 164	99.96 154	97.63 292	99.68 162	99.79 245

MVS_0304		99.72 29	99.65 34	99.93 70	99.99 49	99.79 93	100.00 1	99.91 35	99.17 6	100.00 1	100.00 1	97.84 164	100.00 1	100.00 1	99.95 122	100.00 1

CSCG		99.28 112	99.35 86	99.05 219	99.99 49	97.15 310	100.00 1	99.47 79	97.44 185	99.42 230	100.00 1	97.83 166	100.00 1	99.99 69	100.00 1	100.00 1

CS-MVS		99.33 102	99.27 93	99.50 169	99.99 49	99.00 201	100.00 1	99.13 341	97.26 201	99.96 138	100.00 1	97.79 167	99.64 238	99.64 177	99.67 164	99.87 198

mamv4		98.95 164	99.11 122	98.46 254	99.68 174	95.67 338	99.14 399	99.27 282	96.43 266	99.94 168	99.97 212	97.79 167	99.88 198	99.77 141	100.00 1	99.84 205

ET-MVSNet_ETH3D		96.41 304	95.48 335	99.20 213	99.81 132	99.75 99	100.00 1	99.02 378	97.30 200	78.33 426	100.00 1	97.73 169	97.94 388	99.70 160	87.41 391	99.92 154

tpm cat1		98.05 231	97.76 239	98.92 229	99.50 250	97.10 313	99.77 317	99.30 259	90.20 399	99.72 213	98.71 380	97.71 170	99.86 200	96.75 324	98.20 225	99.81 223

test_fmvsmvis_n_1920		99.46 80	99.37 81	99.73 133	98.88 325	99.18 183	100.00 1	99.26 289	98.85 57	99.79 204	100.00 1	97.70 171	100.00 1	99.98 84	99.86 145	100.00 1

DELS-MVS		99.62 59	99.56 57	99.82 104	99.92 108	99.45 152	100.00 1	99.78 47	98.92 45	99.73 212	100.00 1	97.70 171	100.00 1	99.93 107	100.00 1	100.00 1
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
DIV-MVS_self_test		97.52 255	97.35 255	98.05 294	99.46 263	98.11 259	100.00 1	99.10 351	94.21 344	97.62 343	99.63 308	97.65 173	98.29 363	96.47 325	91.98 344	97.76 289

tpmvs		98.59 195	98.38 203	99.23 211	99.69 169	97.90 277	99.31 376	99.47 79	94.52 335	99.68 216	99.28 343	97.64 174	99.89 191	97.71 289	98.17 228	99.89 174

kuosan		98.55 199	98.53 191	98.62 245	99.66 190	96.16 329	100.00 1	99.44 117	93.93 351	99.81 203	99.98 203	97.58 175	99.81 216	98.08 274	98.28 219	99.89 174

tpm		98.24 225	98.22 218	98.32 266	99.13 294	95.79 335	99.53 353	99.12 347	95.20 318	99.96 138	99.36 339	97.58 175	99.28 292	97.41 301	96.67 276	99.88 187

ADS-MVSNet2		98.28 223	98.51 194	97.62 313	99.51 246	95.03 346	99.24 381	99.41 193	95.52 307	99.96 138	99.70 288	97.57 177	97.94 388	97.11 309	98.54 196	99.88 187

ADS-MVSNet		98.70 185	98.51 194	99.28 206	99.51 246	98.39 236	99.24 381	99.44 117	95.52 307	99.96 138	99.70 288	97.57 177	99.58 246	97.11 309	98.54 196	99.88 187

SPE-MVS-test		99.31 106	99.27 93	99.43 180	99.99 49	98.77 213	100.00 1	99.19 317	97.24 202	99.96 138	100.00 1	97.56 179	99.70 235	99.68 168	99.81 153	99.82 214

dongtai		98.29 221	98.25 211	98.42 258	99.58 221	95.86 334	100.00 1	99.44 117	93.46 364	99.69 215	99.97 212	97.53 180	99.51 267	96.28 330	98.27 221	99.89 174

cl____		97.54 252	97.32 256	98.18 276	99.47 260	98.14 258	100.00 1	99.10 351	94.16 347	97.60 345	99.63 308	97.52 181	98.65 336	96.47 325	91.97 345	97.76 289

h-mvs33		97.03 276	96.53 282	98.51 251	99.79 150	95.90 333	99.45 360	99.45 103	98.21 105	100.00 1	99.78 279	97.49 182	99.99 100	99.72 153	74.92 420	99.65 265

hse-mvs2		96.79 284	96.38 290	98.04 296	99.68 174	95.54 340	99.81 306	99.42 144	98.21 105	100.00 1	99.80 276	97.49 182	99.46 277	99.72 153	73.27 423	99.12 277

EIA-MVS		99.26 115	99.19 112	99.45 176	99.63 200	98.75 214	100.00 1	99.27 282	96.93 225	99.95 166	100.00 1	97.47 184	99.79 219	99.74 148	99.72 159	99.82 214

Test_1112_low_res		98.83 175	98.60 184	99.51 166	99.69 169	98.75 214	99.99 232	99.14 337	96.81 235	98.84 272	99.06 355	97.45 185	99.89 191	98.66 245	97.75 255	99.89 174

1112_ss		98.91 168	98.71 170	99.51 166	99.69 169	98.75 214	99.99 232	99.15 332	96.82 234	98.84 272	100.00 1	97.45 185	99.89 191	98.66 245	97.75 255	99.89 174

ETV-MVS		99.34 99	99.24 102	99.64 149	99.58 221	99.33 164	100.00 1	99.25 293	97.57 169	99.96 138	100.00 1	97.44 187	99.79 219	99.70 160	99.65 166	99.81 223

CPTT-MVS		99.49 76	99.38 78	99.85 96	100.00 1	99.54 133	100.00 1	99.42 144	97.58 168	99.98 125	100.00 1	97.43 188	100.00 1	99.99 69	100.00 1	100.00 1

miper_lstm_enhance		97.40 259	97.28 258	97.75 310	99.48 256	97.52 292	100.00 1	99.07 362	94.08 348	98.01 325	99.61 314	97.38 189	97.98 386	96.44 328	91.47 356	97.76 289

test_fmvsmconf_n		99.56 67	99.46 74	99.86 92	99.68 174	99.58 126	100.00 1	99.31 253	98.92 45	99.88 185	100.00 1	97.35 190	99.99 100	99.98 84	99.99 103	100.00 1

test_fmvsm_n_1920		99.55 69	99.49 69	99.73 133	99.85 120	99.19 181	100.00 1	99.41 193	98.87 55	100.00 1	100.00 1	97.34 191	100.00 1	99.98 84	99.90 135	100.00 1

EI-MVSNet		97.98 234	97.93 234	98.16 279	99.11 295	97.84 282	99.74 322	99.29 266	94.39 340	98.65 282	100.00 1	97.21 192	98.88 320	97.62 295	95.31 292	97.75 300

IterMVS-LS		97.56 250	97.44 249	97.92 305	99.38 279	97.90 277	99.89 294	99.10 351	94.41 339	98.32 306	99.54 326	97.21 192	98.11 375	97.50 297	91.62 351	97.75 300
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tfpn200view9		99.26 115	99.03 129	99.96 45	99.81 132	99.89 70	100.00 1	99.94 22	97.23 203	99.83 192	99.96 229	97.04 194	100.00 1	99.59 187	97.85 246	99.98 117

thres400		99.26 115	99.03 129	99.95 54	99.81 132	99.89 70	100.00 1	99.94 22	97.23 203	99.83 192	99.96 229	97.04 194	100.00 1	99.59 187	97.85 246	99.97 124

thres200		99.27 113	99.04 128	99.96 45	99.81 132	99.90 63	100.00 1	99.94 22	97.31 198	99.83 192	99.96 229	97.04 194	100.00 1	99.62 181	97.88 244	99.98 117

1314		99.38 91	99.19 112	99.96 45	98.88 325	99.89 70	99.24 381	99.93 30	98.88 52	98.79 277	100.00 1	97.02 197	100.00 1	100.00 1	100.00 1	100.00 1

thres100view900		99.25 119	99.01 131	99.95 54	99.81 132	99.87 79	100.00 1	99.94 22	97.13 209	99.83 192	99.96 229	97.01 198	100.00 1	99.59 187	97.85 246	99.98 117

thres600view7		99.24 122	99.00 133	99.95 54	99.81 132	99.87 79	100.00 1	99.94 22	97.13 209	99.83 192	99.96 229	97.01 198	100.00 1	99.54 195	97.77 254	99.97 124

OMC-MVS		99.27 113	99.38 78	98.96 227	99.95 100	97.06 314	100.00 1	99.40 197	98.83 61	99.88 185	100.00 1	97.01 198	99.86 200	99.47 200	99.84 150	99.97 124

xiu_mvs_v1_base_debu		99.35 96	99.21 107	99.79 118	99.67 182	99.71 107	99.78 312	99.36 223	98.13 113	100.00 1	100.00 1	97.00 201	100.00 1	99.83 125	99.07 183	99.66 262

xiu_mvs_v1_base		99.35 96	99.21 107	99.79 118	99.67 182	99.71 107	99.78 312	99.36 223	98.13 113	100.00 1	100.00 1	97.00 201	100.00 1	99.83 125	99.07 183	99.66 262

xiu_mvs_v1_base_debi		99.35 96	99.21 107	99.79 118	99.67 182	99.71 107	99.78 312	99.36 223	98.13 113	100.00 1	100.00 1	97.00 201	100.00 1	99.83 125	99.07 183	99.66 262

CR-MVSNet		98.02 233	97.71 243	98.93 228	99.31 282	98.86 208	99.13 400	99.00 381	96.53 261	99.96 138	98.98 365	96.94 204	98.10 378	91.18 384	98.40 205	99.84 205

Patchmtry		96.81 283	96.37 291	98.14 280	99.31 282	98.55 228	98.91 411	99.00 381	90.45 395	97.92 329	98.98 365	96.94 204	98.12 373	94.27 357	91.53 353	97.75 300

eth_miper_zixun_eth		97.47 256	97.28 258	98.06 290	99.41 270	97.94 275	99.62 343	99.08 357	94.46 338	98.19 316	99.56 323	96.91 206	98.50 352	96.78 321	91.49 354	97.74 322

EC-MVSNet		99.19 125	99.09 125	99.48 172	99.42 268	99.07 189	100.00 1	99.21 313	96.95 223	99.96 138	100.00 1	96.88 207	99.48 271	99.64 177	99.79 157	99.88 187

LS3D		99.31 106	99.13 119	99.87 89	99.99 49	99.71 107	99.55 350	99.46 95	97.32 196	99.82 200	100.00 1	96.85 208	99.97 137	99.14 220	100.00 1	99.92 154

MVSFormer		98.94 166	98.82 156	99.28 206	99.45 264	99.49 146	100.00 1	99.13 341	95.46 312	99.97 131	100.00 1	96.76 209	98.59 344	98.63 250	100.00 1	99.74 253

lupinMVS		99.29 110	99.16 116	99.69 140	99.45 264	99.49 146	100.00 1	99.15 332	97.45 184	99.97 131	100.00 1	96.76 209	99.76 227	99.67 171	100.00 1	99.81 223

MonoMVSNet		98.55 199	98.64 179	98.26 270	98.21 359	95.76 336	99.94 281	99.16 330	96.23 280	99.47 228	99.24 345	96.75 211	99.22 294	99.61 184	99.17 179	99.81 223

mvsmamba		99.05 139	98.98 136	99.27 208	99.57 225	98.10 261	100.00 1	99.28 272	95.92 291	99.96 138	99.97 212	96.73 212	99.89 191	99.72 153	99.65 166	99.81 223

MAR-MVS		99.49 76	99.36 84	99.89 82	99.97 90	99.66 116	99.74 322	99.95 19	97.89 134	100.00 1	100.00 1	96.71 213	100.00 1	100.00 1	100.00 1	100.00 1
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
MM		99.63 54	99.52 64	99.94 66	99.99 49	99.82 89	100.00 1	99.97 17	99.11 8	100.00 1	100.00 1	96.65 214	100.00 1	100.00 1	99.97 116	100.00 1

MSDG		98.90 170	98.63 180	99.70 139	99.92 108	99.25 174	100.00 1	99.37 217	95.71 299	99.40 236	100.00 1	96.58 215	99.95 167	96.80 320	99.94 126	99.91 157

PVSNet_BlendedMVS		98.71 183	98.62 181	98.98 226	99.98 86	99.60 122	100.00 1	100.00 1	97.23 203	100.00 1	99.03 361	96.57 216	99.99 100	100.00 1	94.75 312	97.35 382

PVSNet_Blended		99.48 78	99.36 84	99.83 102	99.98 86	99.60 122	100.00 1	100.00 1	97.79 142	100.00 1	100.00 1	96.57 216	99.99 100	100.00 1	99.88 139	99.90 168

MVS_Test		98.93 167	98.65 177	99.77 126	99.62 207	99.50 142	99.99 232	99.19 317	95.52 307	99.96 138	99.86 258	96.54 218	99.98 130	98.65 247	98.48 200	99.82 214

PMMVS		99.12 132	98.97 138	99.58 161	99.57 225	98.98 203	100.00 1	99.30 259	97.14 207	99.96 138	100.00 1	96.53 219	99.82 213	99.70 160	98.49 199	99.94 141

PVSNet_Blended_VisFu		99.33 102	99.18 115	99.78 123	99.82 126	99.49 146	100.00 1	99.95 19	97.36 190	99.63 218	100.00 1	96.45 220	99.95 167	99.79 133	99.65 166	99.89 174

mvs_anonymous		98.80 177	98.60 184	99.38 191	99.57 225	99.24 176	100.00 1	99.21 313	95.87 292	98.92 264	99.82 270	96.39 221	99.03 301	99.13 222	98.50 198	99.88 187

DP-MVS		98.86 173	98.54 189	99.81 109	99.97 90	99.45 152	99.52 354	99.40 197	94.35 341	98.36 301	100.00 1	96.13 222	99.97 137	99.12 223	100.00 1	100.00 1

PVSNet	94.91 18	99.30 108	99.25 99	99.44 177	100.00 1	98.32 246	100.00 1	99.86 38	98.04 120	100.00 1	100.00 1	96.10 223	100.00 1	99.55 192	99.73 158	100.00 1

Effi-MVS+-dtu		98.51 206	98.86 153	97.47 317	99.77 156	94.21 369	100.00 1	98.94 386	97.61 163	99.91 178	98.75 379	95.89 224	99.51 267	99.36 205	99.48 174	98.68 282

our_test_3		96.51 299	96.35 292	96.98 339	97.61 381	95.05 345	99.98 258	99.01 380	94.68 329	96.77 367	99.06 355	95.87 225	98.14 371	91.81 380	92.37 338	97.75 300

UA-Net		99.06 137	98.83 155	99.74 130	99.52 241	99.40 158	99.08 406	99.45 103	97.64 156	99.83 192	100.00 1	95.80 226	99.94 179	98.35 263	99.80 156	99.88 187

FMVSNet5		95.32 341	95.43 338	94.99 374	99.39 278	92.99 382	99.25 380	99.24 299	90.45 395	97.44 350	98.45 390	95.78 227	94.39 420	87.02 407	91.88 346	97.59 369

CVMVSNet		98.56 198	98.47 197	98.82 234	99.11 295	97.67 288	99.74 322	99.47 79	97.57 169	99.06 258	100.00 1	95.72 228	98.97 309	98.21 271	97.33 265	99.83 209

RPMNet		95.26 344	93.82 353	99.56 164	99.31 282	98.86 208	99.13 400	99.42 144	79.82 423	99.96 138	95.13 416	95.69 229	99.98 130	77.54 426	98.40 205	99.84 205

MVS		99.22 123	98.96 139	99.98 23	99.00 312	99.95 32	99.24 381	99.94 22	98.14 112	98.88 267	100.00 1	95.63 230	100.00 1	99.85 121	100.00 1	100.00 1

jason		99.11 133	98.96 139	99.59 157	99.17 292	99.31 167	100.00 1	99.13 341	97.38 189	99.83 192	100.00 1	95.54 231	99.72 233	99.57 191	99.97 116	99.74 253
jason: jason.
AdaColmap		99.44 83	99.26 97	99.95 54	100.00 1	99.86 82	99.70 332	99.99 13	98.53 85	99.90 180	100.00 1	95.34 232	100.00 1	99.92 108	100.00 1	100.00 1

CANet		99.40 87	99.24 102	99.89 82	99.99 49	99.76 98	100.00 1	99.73 56	98.40 92	99.78 206	100.00 1	95.28 233	99.96 154	100.00 1	99.99 103	99.96 130

FIs		97.95 235	97.73 242	98.62 245	98.53 343	99.24 176	100.00 1	99.43 125	96.74 243	97.87 332	99.82 270	95.27 234	98.89 317	98.78 239	93.07 326	97.74 322

sasdasda		99.03 142	98.73 166	99.94 66	99.75 159	99.95 32	100.00 1	99.30 259	97.64 156	100.00 1	100.00 1	95.22 235	99.97 137	99.76 143	96.90 273	99.91 157

canonicalmvs		99.03 142	98.73 166	99.94 66	99.75 159	99.95 32	100.00 1	99.30 259	97.64 156	100.00 1	100.00 1	95.22 235	99.97 137	99.76 143	96.90 273	99.91 157

fmvsm_s_conf0.5_n_a		99.32 104	99.15 117	99.81 109	99.80 145	99.47 151	100.00 1	99.35 234	98.22 104	100.00 1	100.00 1	95.21 237	99.99 100	99.96 97	99.86 145	99.98 117

FC-MVSNet-test		97.84 237	97.63 246	98.45 256	98.30 353	99.05 192	100.00 1	99.43 125	96.63 257	97.61 344	99.82 270	95.19 238	98.57 347	98.64 248	93.05 327	97.73 329

MGCFI-Net		99.01 149	98.70 172	99.93 70	99.74 161	99.94 41	100.00 1	99.29 266	97.60 166	100.00 1	100.00 1	95.10 239	99.96 154	99.74 148	96.85 275	99.91 157

UniMVSNet_NR-MVSNet		97.16 268	96.80 272	98.22 273	98.38 347	98.41 233	100.00 1	99.45 103	96.14 286	97.76 335	99.64 304	95.05 240	98.50 352	97.98 279	86.84 394	97.75 300

Fast-Effi-MVS+-dtu		98.38 216	98.56 188	97.82 308	99.58 221	94.44 366	100.00 1	99.16 330	96.75 241	99.51 223	99.63 308	95.03 241	99.60 240	97.71 289	99.67 164	99.42 272

UniMVSNet (Re)		97.29 264	96.85 271	98.59 248	98.49 344	99.13 187	100.00 1	99.42 144	96.52 262	98.24 315	98.90 373	94.93 242	98.89 317	97.54 296	87.61 390	97.75 300

BH-w/o		98.82 176	98.81 158	98.88 232	99.62 207	96.71 321	100.00 1	99.28 272	97.09 212	98.81 275	100.00 1	94.91 243	99.96 154	99.54 195	100.00 1	99.96 130

AUN-MVS		96.26 315	95.67 327	98.06 290	99.68 174	95.60 339	99.82 305	99.42 144	96.78 238	99.88 185	99.80 276	94.84 244	99.47 273	97.48 298	73.29 422	99.12 277

test_fmvsmconf0.1_n		99.25 119	99.05 127	99.82 104	98.92 321	99.55 130	100.00 1	99.23 303	98.91 47	99.75 210	99.97 212	94.79 245	99.94 179	99.94 105	99.99 103	99.97 124

fmvsm_l_conf0.5_n_3		99.38 91	99.20 111	99.92 74	99.80 145	99.78 94	100.00 1	99.35 234	98.94 40	100.00 1	100.00 1	94.77 246	99.99 100	99.99 69	99.92 131	100.00 1

fmvsm_s_conf0.5_n_6		99.30 108	99.12 121	99.84 101	99.24 289	99.56 128	100.00 1	99.31 253	98.90 50	100.00 1	100.00 1	94.75 247	99.97 137	99.98 84	99.88 139	100.00 1

PCF-MVS	98.23 3	98.69 186	98.37 205	99.62 152	99.78 154	99.02 196	99.23 386	99.06 370	96.43 266	98.08 318	100.00 1	94.72 248	99.95 167	98.16 272	99.91 133	99.90 168
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
VNet		99.04 140	98.75 163	99.90 79	99.81 132	99.75 99	99.50 356	99.47 79	98.36 97	100.00 1	99.99 198	94.66 249	100.00 1	99.90 111	97.09 268	99.96 130

diffmvs		98.96 161	98.73 166	99.63 150	99.54 230	99.16 185	100.00 1	99.18 324	97.33 195	99.96 138	100.00 1	94.60 250	99.91 188	99.66 175	98.33 215	99.82 214
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
BH-untuned		98.64 189	98.65 177	98.60 247	99.59 216	96.17 328	100.00 1	99.28 272	96.67 252	98.41 299	100.00 1	94.52 251	99.83 210	99.41 203	100.00 1	99.81 223

nrg030		97.64 245	97.27 260	98.75 240	98.34 348	99.53 135	100.00 1	99.22 307	96.21 284	98.27 311	99.95 236	94.40 252	98.98 307	99.23 217	89.78 371	97.75 300

ppachtmachnet_test		96.17 321	95.89 311	97.02 336	97.61 381	95.24 342	99.99 232	99.24 299	93.31 369	96.71 368	99.62 312	94.34 253	98.07 380	89.87 395	92.30 340	97.75 300

MVStest1		94.27 351	93.30 360	97.19 331	98.83 332	97.18 309	99.93 284	98.79 396	86.80 411	84.88 423	99.04 358	94.32 254	98.25 366	90.55 390	86.57 398	96.12 406

fmvsm_s_conf0.5_n_8		99.34 99	99.14 118	99.91 75	99.83 124	99.74 102	100.00 1	99.38 213	98.94 40	100.00 1	100.00 1	94.25 255	99.99 100	100.00 1	99.91 133	100.00 1

D2MVS		97.63 248	97.83 237	97.05 334	98.83 332	94.60 362	100.00 1	99.82 40	96.89 231	98.28 309	99.03 361	94.05 256	99.47 273	98.58 255	94.97 310	97.09 388

RPSCF		97.37 260	98.24 214	94.76 378	99.80 145	84.57 415	99.99 232	99.05 372	94.95 322	99.82 200	100.00 1	94.03 257	100.00 1	98.15 273	98.38 209	99.70 258

CANet_DTU		99.02 147	98.90 151	99.41 183	99.88 116	98.71 218	100.00 1	99.29 266	98.84 59	100.00 1	100.00 1	94.02 258	100.00 1	98.08 274	99.96 120	99.52 269

LCM-MVSNet-Re		96.52 297	97.21 264	94.44 379	99.27 286	85.80 412	99.85 300	96.61 429	95.98 289	92.75 402	98.48 389	93.97 259	97.55 398	99.58 190	98.43 203	99.98 117

Effi-MVS+		98.58 196	98.24 214	99.61 153	99.60 212	99.26 172	97.85 422	99.10 351	96.22 283	99.97 131	99.89 253	93.75 260	99.77 224	99.43 201	98.34 212	99.81 223

pmmvs4		97.17 267	96.80 272	98.27 268	97.68 378	98.64 223	100.00 1	99.18 324	94.22 343	98.55 289	99.71 285	93.67 261	98.47 355	95.66 338	92.57 335	97.71 343

CHOSEN 1792x2688		99.00 150	98.91 148	99.25 210	99.90 112	97.79 285	100.00 1	99.99 13	98.79 71	98.28 309	100.00 1	93.63 262	99.95 167	99.66 175	99.95 122	100.00 1

fmvsm_s_conf0.5_n		99.21 124	99.01 131	99.83 102	99.84 121	99.53 135	100.00 1	99.38 213	98.29 103	100.00 1	100.00 1	93.62 263	99.99 100	99.99 69	99.93 129	99.98 117

WB-MVSnew		97.02 278	97.24 262	96.37 358	99.44 266	97.36 299	100.00 1	99.43 125	96.12 287	99.35 239	99.89 253	93.60 264	98.42 358	88.91 405	98.39 207	93.33 420

cdsmvs_eth3d_5k		24.41 405	32.55 407	0.00 421	0.00 444	0.00 446	0.00 432	99.39 210	0.00 439	0.00 440	100.00 1	93.55 265	0.00 440	0.00 439	0.00 438	0.00 436

AllTest		98.55 199	98.40 201	98.99 224	99.93 105	97.35 300	100.00 1	99.40 197	97.08 214	99.09 254	99.98 203	93.37 266	99.95 167	96.94 313	99.84 150	99.68 260

TestCases				98.99 224	99.93 105	97.35 300		99.40 197	97.08 214	99.09 254	99.98 203	93.37 266	99.95 167	96.94 313	99.84 150	99.68 260

FMVSNet3		97.30 263	96.95 267	98.37 262	99.65 192	99.25 174	99.71 330	99.28 272	94.23 342	98.53 291	98.91 372	93.30 268	98.11 375	95.31 344	93.60 320	97.73 329

Fast-Effi-MVS+		98.40 215	98.02 231	99.55 165	99.63 200	99.06 191	100.00 1	99.15 332	95.07 319	99.42 230	99.95 236	93.26 269	99.73 232	97.44 299	98.24 222	99.87 198

baseline		98.69 186	98.45 198	99.41 183	99.52 241	98.67 221	100.00 1	99.17 329	97.03 217	99.13 251	100.00 1	93.17 270	99.74 230	99.70 160	98.34 212	99.81 223

QAPM		98.99 154	98.66 176	99.96 45	99.01 308	99.87 79	99.88 296	99.93 30	97.99 123	98.68 281	100.00 1	93.17 270	100.00 1	99.32 210	100.00 1	100.00 1

PatchMatch-RL		99.02 147	98.78 160	99.74 130	99.99 49	99.29 168	100.00 1	100.00 1	98.38 93	99.89 183	99.81 273	93.14 272	99.99 100	97.85 285	99.98 113	99.95 136

WR-MVS_H		96.73 287	96.32 295	97.95 301	98.26 356	97.88 279	99.72 329	99.43 125	95.06 320	96.99 358	98.68 382	93.02 273	98.53 350	97.43 300	88.33 386	97.43 378

3Dnovator	95.63 14	99.06 137	98.76 162	99.96 45	98.86 329	99.90 63	99.98 258	99.93 30	98.95 37	98.49 296	100.00 1	92.91 274	100.00 1	99.71 157	100.00 1	100.00 1

WB-MVS		88.24 384	90.09 380	82.68 409	91.56 424	69.51 429	100.00 1	98.73 398	90.72 394	87.29 417	98.12 397	92.87 275	85.01 431	62.19 432	89.34 376	93.54 419

3Dnovator+	95.58 15	99.03 142	98.71 170	99.96 45	98.99 315	99.89 70	100.00 1	99.51 76	98.96 34	98.32 306	100.00 1	92.78 276	100.00 1	99.87 118	100.00 1	100.00 1

casdiffmvs		98.65 188	98.38 203	99.46 174	99.52 241	98.74 217	100.00 1	99.15 332	96.91 228	99.05 259	100.00 1	92.75 277	99.83 210	99.70 160	98.38 209	99.81 223
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
casdiffmvs_mvg		98.64 189	98.39 202	99.40 187	99.50 250	98.60 225	100.00 1	99.22 307	96.85 232	99.10 253	100.00 1	92.75 277	99.78 223	99.71 157	98.35 211	99.81 223
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
NR-MVSNet		96.63 293	96.04 305	98.38 261	98.31 351	98.98 203	99.22 388	99.35 234	95.87 292	94.43 393	99.65 300	92.73 279	98.40 359	96.78 321	88.05 387	97.75 300

SSC-MVS		87.61 385	89.47 383	82.04 410	90.63 427	68.77 430	99.99 232	98.66 399	90.34 397	86.70 418	98.08 398	92.72 280	84.12 432	59.41 435	88.71 384	93.22 423

COLMAP_ROB	97.10 7	98.29 221	98.17 219	98.65 243	99.94 103	97.39 297	99.30 377	99.40 197	95.64 300	97.75 338	100.00 1	92.69 281	99.95 167	98.89 233	99.92 131	98.62 284
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
RRT-MVS		98.75 181	98.52 192	99.44 177	99.65 192	98.57 227	99.90 290	99.08 357	96.51 263	99.96 138	99.95 236	92.59 282	99.96 154	99.60 185	99.45 176	99.81 223

EU-MVSNet		96.63 293	96.53 282	96.94 341	97.59 383	96.87 317	99.76 319	99.47 79	96.35 275	96.85 363	99.78 279	92.57 283	96.27 411	95.33 343	91.08 360	97.68 350

MVP-Stereo		96.51 299	96.48 286	96.60 353	95.65 409	94.25 368	98.84 413	98.16 405	95.85 296	95.23 384	99.04 358	92.54 284	99.13 297	92.98 372	99.98 113	96.43 401
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Syy-MVS		96.17 321	96.57 281	95.00 373	99.50 250	87.37 410	100.00 1	99.57 68	96.23 280	98.07 319	100.00 1	92.41 285	97.81 391	85.34 411	97.96 238	99.82 214

DeepC-MVS	97.84 5	99.00 150	98.80 159	99.60 155	99.93 105	99.03 194	100.00 1	99.40 197	98.61 83	99.33 240	100.00 1	92.23 286	99.95 167	99.74 148	99.96 120	99.83 209
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DU-MVS		96.93 281	96.49 285	98.22 273	98.31 351	98.41 233	100.00 1	99.37 217	96.41 270	97.76 335	99.65 300	92.14 287	98.50 352	97.98 279	86.84 394	97.75 300

Baseline_NR-MVSNet		96.16 323	95.70 323	97.56 316	98.28 355	96.79 320	100.00 1	97.86 417	91.93 385	97.63 341	99.47 331	92.14 287	98.35 361	97.13 308	86.83 396	97.54 372

cascas		98.43 210	98.07 227	99.50 169	99.65 192	99.02 196	100.00 1	99.22 307	94.21 344	99.72 213	99.98 203	92.03 289	99.93 183	99.68 168	98.12 229	99.54 268

test_djsdf		97.55 251	97.38 253	98.07 286	97.50 387	97.99 269	100.00 1	99.13 341	95.46 312	98.47 297	99.85 263	92.01 290	98.59 344	98.63 250	95.36 290	97.62 365

fmvsm_s_conf0.5_n_7		98.98 158	98.85 154	99.37 192	99.67 182	98.34 243	100.00 1	99.31 253	98.97 32	100.00 1	100.00 1	91.70 291	99.97 137	99.99 69	99.97 116	99.80 240

v8		96.35 310	95.73 322	98.21 275	98.11 364	98.23 252	99.94 281	99.07 362	92.66 381	98.29 308	99.00 364	91.46 292	98.77 328	94.17 358	88.83 383	97.62 365

OpenMVS	95.20 17	98.76 179	98.41 200	99.78 123	98.89 324	99.81 90	99.99 232	99.76 49	98.02 121	98.02 324	100.00 1	91.44 293	100.00 1	99.63 180	99.97 116	99.55 267

v148		96.29 313	95.84 314	97.63 311	97.74 376	96.53 326	100.00 1	99.07 362	93.52 361	98.01 325	99.42 334	91.22 294	98.60 342	96.37 329	87.22 393	97.75 300

GeoE		98.06 230	97.65 245	99.29 203	99.47 260	98.41 233	100.00 1	99.19 317	94.85 324	98.88 267	100.00 1	91.21 295	99.59 242	97.02 311	98.19 226	99.88 187

XVG-OURS		98.30 219	98.36 207	98.13 283	99.58 221	95.91 332	100.00 1	99.36 223	98.69 77	99.23 244	100.00 1	91.20 296	99.92 186	99.34 208	97.82 249	98.56 285

WR-MVS		97.09 271	96.64 277	98.46 254	98.43 345	99.09 188	99.97 264	99.33 243	95.62 302	97.76 335	99.67 296	91.17 297	98.56 349	98.49 257	89.28 377	97.74 322

V42		96.65 292	96.16 301	98.11 285	98.17 363	98.23 252	99.99 232	99.09 356	93.97 349	98.74 279	99.05 357	91.09 298	98.82 323	95.46 342	89.90 369	97.27 384

v10		96.14 325	95.50 331	98.07 286	98.19 361	97.96 273	99.83 302	99.07 362	92.10 384	98.07 319	98.94 370	91.07 299	98.61 339	92.41 378	89.82 370	97.63 363

dmvs_testset		93.27 362	95.48 335	86.65 402	98.74 335	68.42 431	99.92 286	98.91 389	96.19 285	93.28 399	100.00 1	91.06 300	91.67 427	89.64 398	91.54 352	99.86 202

v7n		96.06 329	95.42 339	97.99 300	97.58 384	97.35 300	99.86 298	99.11 348	92.81 380	97.91 330	99.49 329	90.99 301	98.92 313	92.51 375	88.49 385	97.70 344

v1144		96.51 299	95.97 309	98.13 283	97.98 369	98.04 267	99.99 232	99.08 357	93.51 362	98.62 285	98.98 365	90.98 302	98.62 338	93.79 364	90.79 363	97.74 322

fmvsm_s_conf0.1_n_2		98.95 164	98.69 174	99.73 133	99.61 209	99.74 102	100.00 1	99.23 303	98.95 37	99.97 131	100.00 1	90.92 303	99.97 137	100.00 1	99.58 171	99.47 271

fmvsm_s_conf0.5_n_4		98.98 158	98.74 165	99.68 143	99.81 132	99.50 142	100.00 1	99.26 289	98.91 47	100.00 1	100.00 1	90.87 304	99.97 137	99.99 69	99.81 153	99.57 266

dmvs_re		97.54 252	97.88 235	96.54 354	99.55 229	90.35 401	99.86 298	99.46 95	97.00 219	99.41 235	100.00 1	90.78 305	99.30 290	99.60 185	95.24 297	99.96 130

fmvsm_s_conf0.5_n_5		99.00 150	98.70 172	99.88 87	99.81 132	99.64 118	100.00 1	99.26 289	98.78 74	99.97 131	100.00 1	90.65 306	99.99 100	100.00 1	99.89 136	99.99 114

ab-mvs		98.42 212	98.02 231	99.61 153	99.71 164	99.00 201	99.10 403	99.64 64	96.70 248	99.04 260	99.81 273	90.64 307	99.98 130	99.64 177	97.93 241	99.84 205

Anonymous202405211		97.87 236	97.53 247	98.90 230	99.81 132	96.70 322	99.35 371	99.46 95	92.98 375	98.83 274	99.99 198	90.63 308	100.00 1	99.70 160	97.03 269	100.00 1

Anonymous20231206		93.45 360	93.17 361	94.30 382	95.00 414	89.69 403	99.98 258	98.43 402	93.30 370	94.50 392	98.59 385	90.52 309	95.73 416	77.46 427	90.73 365	97.48 377

anonymousdsp		97.16 268	96.88 269	98.00 298	97.08 397	98.06 265	99.81 306	99.15 332	94.58 332	97.84 334	99.62 312	90.49 310	98.60 342	97.98 279	95.32 291	97.33 383

v2v482		96.70 290	96.18 299	98.27 268	98.04 366	98.39 236	100.00 1	99.13 341	94.19 346	98.58 287	99.08 354	90.48 311	98.67 334	95.69 337	90.44 367	97.75 300

v144192		96.40 307	95.81 315	98.17 278	97.89 372	98.11 259	99.99 232	99.06 370	93.39 366	98.75 278	99.09 353	90.43 312	98.66 335	93.10 371	90.55 366	97.75 300

Vis-MVSNet		98.52 204	98.25 211	99.34 195	99.68 174	98.55 228	99.68 336	99.41 193	97.34 193	99.94 168	100.00 1	90.38 313	99.70 235	99.03 227	98.84 188	99.76 251
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
fmvsm_s_conf0.5_n_3		98.99 154	98.69 174	99.89 82	99.70 166	99.69 113	100.00 1	99.39 210	98.93 43	100.00 1	100.00 1	90.20 314	99.99 100	100.00 1	99.95 122	100.00 1

test_fmvsmconf0.01_n		98.60 194	98.24 214	99.67 144	96.90 398	99.21 179	99.99 232	99.04 375	98.80 68	99.57 220	99.96 229	90.12 315	99.91 188	99.89 113	99.89 136	99.90 168

CP-MVSNet		96.73 287	96.25 296	98.18 276	98.21 359	98.67 221	99.77 317	99.32 246	95.06 320	97.20 355	99.65 300	90.10 316	98.19 368	98.06 277	88.90 381	97.66 355

TranMVSNet+NR-MVSNet		96.45 303	96.01 306	97.79 309	98.00 368	97.62 290	100.00 1	99.35 234	95.98 289	97.31 352	99.64 304	90.09 317	98.00 385	96.89 316	86.80 397	97.75 300

SDMVSNet		98.49 207	98.08 225	99.73 133	99.82 126	99.53 135	99.99 232	99.45 103	97.62 159	99.38 237	99.86 258	90.06 318	99.88 198	99.92 108	96.61 278	99.79 245

DSMNet-mixed		95.18 345	95.21 342	95.08 370	96.03 404	90.21 402	99.65 338	93.64 435	92.91 376	98.34 304	97.40 406	90.05 319	95.51 417	91.02 386	97.86 245	99.51 270

N_pmnet		91.88 372	93.37 359	87.40 401	97.24 396	66.33 434	99.90 290	91.05 437	89.77 401	95.65 382	98.58 386	90.05 319	98.11 375	85.39 410	92.72 331	97.75 300

fmvsm_s_conf0.1_n_a		98.71 183	98.36 207	99.78 123	99.09 298	99.42 156	100.00 1	99.26 289	97.42 187	100.00 1	100.00 1	89.78 321	99.96 154	99.82 130	99.85 148	99.97 124

GA-MVS		97.72 243	97.27 260	99.06 217	99.24 289	97.93 276	100.00 1	99.24 299	95.80 298	98.99 262	99.64 304	89.77 322	99.36 285	95.12 348	97.62 263	99.89 174

fmvsm_s_conf0.1_n		98.77 178	98.42 199	99.82 104	99.47 260	99.52 139	100.00 1	99.27 282	97.53 173	100.00 1	100.00 1	89.73 323	99.96 154	99.84 124	99.93 129	99.97 124

MIMVSNet		97.06 274	96.73 275	98.05 294	99.38 279	96.64 324	98.47 418	99.35 234	93.41 365	99.48 225	98.53 387	89.66 324	97.70 397	94.16 360	98.11 230	99.80 240

IterMVS-SCA-FT		96.72 289	96.42 289	97.62 313	99.40 275	96.83 318	99.99 232	99.14 337	94.65 331	97.55 347	99.72 283	89.65 325	98.31 362	95.62 340	92.05 342	97.73 329

SCA		98.30 219	97.98 233	99.23 211	99.41 270	98.25 251	99.99 232	99.45 103	96.91 228	99.76 209	99.58 318	89.65 325	99.54 259	98.31 265	98.79 189	99.91 157

IterMVS		96.76 286	96.46 287	97.63 311	99.41 270	96.89 316	99.99 232	99.13 341	94.74 328	97.59 346	99.66 298	89.63 327	98.28 364	95.71 336	92.31 339	97.72 335
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1192		96.18 319	95.49 333	98.26 270	98.01 367	98.15 256	99.99 232	99.08 357	93.36 367	98.54 290	98.97 368	89.47 328	98.89 317	91.15 385	90.82 362	97.75 300

v1921920		96.16 323	95.50 331	98.14 280	97.88 373	97.96 273	99.99 232	99.07 362	93.33 368	98.60 286	99.24 345	89.37 329	98.71 332	91.28 383	90.74 364	97.75 300

XVG-OURS-SEG-HR		98.27 224	98.31 209	98.14 280	99.59 216	95.92 331	100.00 1	99.36 223	98.48 88	99.21 245	100.00 1	89.27 330	99.94 179	99.76 143	99.17 179	98.56 285

fmvsm_s_conf0.5_n_2		98.90 170	98.57 187	99.90 79	99.79 150	99.78 94	100.00 1	99.25 293	98.97 32	100.00 1	100.00 1	89.22 331	99.99 100	100.00 1	99.88 139	99.92 154

test20.03		93.11 363	92.85 367	93.88 387	95.19 413	91.83 391	100.00 1	98.87 392	93.68 356	92.76 401	98.88 374	89.20 332	92.71 425	77.88 425	89.19 378	97.09 388

MDA-MVSNet_test_wron		92.61 367	91.09 375	97.19 331	96.71 400	97.26 306	100.00 1	99.14 337	88.61 404	67.90 432	98.32 395	89.03 333	96.57 406	90.47 392	89.59 372	97.74 322

BH-RMVSNet		98.46 208	98.08 225	99.59 157	99.61 209	99.19 181	100.00 1	99.28 272	97.06 216	98.95 263	100.00 1	88.99 334	99.82 213	98.83 238	100.00 1	99.77 249

v1240		95.96 331	95.25 340	98.07 286	97.91 371	97.87 281	99.96 270	99.07 362	93.24 371	98.64 284	98.96 369	88.98 335	98.61 339	89.58 399	90.92 361	97.75 300

Anonymous20231211		96.29 313	95.70 323	98.07 286	99.80 145	97.49 293	99.15 397	99.40 197	89.11 402	97.75 338	99.45 332	88.93 336	98.98 307	98.26 270	89.47 374	97.73 329

TR-MVS		98.14 228	97.74 240	99.33 198	99.59 216	98.28 249	99.27 378	99.21 313	96.42 269	99.15 250	99.94 242	88.87 337	99.79 219	98.88 234	98.29 218	99.93 152

CL-MVSNet_self_test		91.07 376	90.35 379	93.24 389	93.27 418	89.16 405	99.55 350	99.25 293	92.34 382	95.23 384	97.05 409	88.86 338	93.59 423	80.67 420	66.95 426	96.96 391

YYNet1		92.44 368	90.92 376	97.03 335	96.20 402	97.06 314	99.99 232	99.14 337	88.21 407	67.93 431	98.43 392	88.63 339	96.28 410	90.64 387	89.08 379	97.74 322

HQP2-MVS												88.61 340

HQP-MVS		97.73 242	97.85 236	97.39 319	99.07 300	94.82 350	100.00 1	99.40 197	99.04 16	99.17 246	99.97 212	88.61 340	99.57 247	99.79 133	95.58 282	97.77 287

HQP_MVS		97.71 244	97.82 238	97.37 320	99.00 312	94.80 353	100.00 1	99.40 197	99.00 27	99.08 256	99.97 212	88.58 342	99.55 256	99.79 133	95.57 286	97.76 289

plane_prior6					99.06 304	94.80 353						88.58 342

tfpnnormal		96.36 309	95.69 326	98.37 262	98.55 341	98.71 218	99.69 334	99.45 103	93.16 373	96.69 369	99.71 285	88.44 344	98.99 306	94.17 358	91.38 357	97.41 379

test1111		98.42 212	98.12 221	99.29 203	99.88 116	98.15 256	99.46 358	100.00 1	98.36 97	99.42 230	100.00 1	87.91 345	99.79 219	99.31 211	98.78 190	99.94 141

ECVR-MVS		98.43 210	98.14 220	99.32 200	99.89 114	98.21 254	99.46 358	100.00 1	98.38 93	99.47 228	100.00 1	87.91 345	99.80 218	99.35 206	98.78 190	99.94 141

TransMVSNet (Re)		94.78 347	93.72 354	97.93 304	98.34 348	97.88 279	99.23 386	97.98 414	91.60 386	94.55 390	99.71 285	87.89 347	98.36 360	89.30 401	84.92 401	97.56 371

DTE-MVSNet		95.52 338	94.99 346	97.08 333	97.49 389	96.45 327	100.00 1	99.25 293	93.82 352	96.17 376	99.57 322	87.81 348	97.18 399	94.57 353	86.26 400	97.62 365

XXY-MVS		97.14 270	96.63 278	98.67 242	98.65 337	98.92 206	99.54 352	99.29 266	95.57 304	97.63 341	99.83 266	87.79 349	99.35 287	98.39 261	92.95 328	97.75 300

UGNet		98.41 214	98.11 222	99.31 202	99.54 230	98.55 228	99.18 389	100.00 1	98.64 82	99.79 204	99.04 358	87.61 350	100.00 1	99.30 212	99.89 136	99.40 273
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
CLD-MVS		97.64 245	97.74 240	97.36 321	99.01 308	94.76 358	100.00 1	99.34 241	99.30 4	99.00 261	99.97 212	87.49 351	99.57 247	99.96 97	95.58 282	97.75 300
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_cas_vis1_n_1920		98.63 192	98.25 211	99.77 126	99.69 169	99.32 165	100.00 1	99.31 253	98.84 59	99.96 138	100.00 1	87.42 352	99.99 100	99.14 220	99.86 145	100.00 1

PEN-MVS		96.01 330	95.48 335	97.58 315	97.74 376	97.26 306	99.90 290	99.29 266	94.55 333	96.79 365	99.55 324	87.38 353	97.84 390	96.92 315	87.24 392	97.65 359

ACMM	97.17 6	97.37 260	97.40 252	97.29 326	99.01 308	94.64 361	100.00 1	99.25 293	98.07 119	98.44 298	99.98 203	87.38 353	99.55 256	99.25 214	95.19 300	97.69 348
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
jajsoiax		97.07 273	96.79 274	97.89 306	97.28 395	97.12 311	99.95 276	99.19 317	96.55 259	97.31 352	99.69 291	87.35 355	98.91 314	98.70 244	95.12 305	97.66 355

pmmvs5		95.94 332	95.61 328	96.95 340	97.42 392	94.66 359	100.00 1	98.08 409	93.60 359	97.05 357	99.43 333	87.02 356	98.46 356	95.76 334	92.12 341	97.72 335

VPA-MVSNet		97.03 276	96.43 288	98.82 234	98.64 338	99.32 165	99.38 368	99.47 79	96.73 245	98.91 266	98.94 370	87.00 357	99.40 283	99.23 217	89.59 372	97.76 289

PS-CasMVS		96.34 311	95.78 319	98.03 297	98.18 362	98.27 250	99.71 330	99.32 246	94.75 326	96.82 364	99.65 300	86.98 358	98.15 370	97.74 288	88.85 382	97.66 355

LPG-MVS_test		97.31 262	97.32 256	97.28 327	98.85 330	94.60 362	100.00 1	99.37 217	97.35 191	98.85 270	99.98 203	86.66 359	99.56 251	99.55 192	95.26 294	97.70 344

LGP-MVS_train				97.28 327	98.85 330	94.60 362		99.37 217	97.35 191	98.85 270	99.98 203	86.66 359	99.56 251	99.55 192	95.26 294	97.70 344

mvs_tets		97.00 279	96.69 276	97.94 302	97.41 394	97.27 305	99.60 345	99.18 324	96.51 263	97.35 351	99.69 291	86.53 361	98.91 314	98.84 236	95.09 306	97.65 359

ttmdpeth		96.24 316	95.88 312	97.32 324	97.80 374	96.61 325	99.95 276	98.77 397	97.80 141	93.42 398	99.28 343	86.42 362	99.01 303	97.63 292	91.84 347	96.33 403

pm-mvs1		95.76 335	95.01 345	98.00 298	98.23 358	97.45 295	99.24 381	99.04 375	93.13 374	95.93 380	99.72 283	86.28 363	98.84 322	95.62 340	87.92 388	97.72 335

KD-MVS_self_test		91.16 375	90.09 380	94.35 381	94.44 416	91.27 396	99.74 322	99.08 357	90.82 393	94.53 391	94.91 419	86.11 364	94.78 419	82.67 416	68.52 425	96.99 390

MVS-HIRNet		94.12 355	92.73 369	98.29 267	99.33 281	95.95 330	99.38 368	99.19 317	74.54 426	98.26 312	86.34 430	86.07 365	99.06 300	91.60 382	99.87 144	99.85 203

DeepMVS_CX				89.98 395	98.90 323	71.46 426		99.18 324	97.61 163	96.92 359	99.83 266	86.07 365	99.83 210	96.02 332	97.65 261	98.65 283

OPM-MVS		97.21 265	97.18 265	97.32 324	98.08 365	94.66 359	100.00 1	99.28 272	98.65 81	98.92 264	99.98 203	86.03 367	99.56 251	98.28 269	95.41 288	97.72 335
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
new_pmnet		94.11 356	93.47 358	96.04 365	96.60 401	92.82 383	99.97 264	98.91 389	90.21 398	95.26 383	98.05 401	85.89 368	98.14 371	84.28 413	92.01 343	97.16 386

ACMP	97.00 8	97.19 266	97.16 266	97.27 329	98.97 317	94.58 365	100.00 1	99.32 246	97.97 127	97.45 349	99.98 203	85.79 369	99.56 251	99.70 160	95.24 297	97.67 354
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OurMVSNet-221017-0		96.14 325	95.98 308	96.62 352	97.49 389	93.44 376	99.92 286	98.16 405	95.86 294	97.65 340	99.95 236	85.71 370	98.78 325	94.93 350	94.18 318	97.64 362

sd_testset		97.81 239	97.48 248	98.79 238	99.82 126	96.80 319	99.32 373	99.45 103	97.62 159	99.38 237	99.86 258	85.56 371	99.77 224	99.72 153	96.61 278	99.79 245

SixPastTwentyTwo		95.71 336	95.49 333	96.38 357	97.42 392	93.01 380	99.84 301	98.23 404	94.75 326	95.98 379	99.97 212	85.35 372	98.43 357	94.71 352	93.17 325	97.69 348

test_fmvs1		98.37 217	98.04 229	99.34 195	99.84 121	98.07 263	100.00 1	99.00 381	98.85 57	100.00 1	100.00 1	85.11 373	99.96 154	99.69 167	99.88 139	100.00 1

LTVRE_ROB	95.29 16	96.32 312	96.10 302	96.99 338	98.55 341	93.88 371	99.45 360	99.28 272	94.50 336	96.46 371	99.52 327	84.86 374	99.48 271	97.26 307	95.03 307	97.59 369
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
ITE_SJBPF				96.84 347	98.96 318	93.49 375		98.12 407	98.12 116	98.35 303	99.97 212	84.45 375	99.56 251	95.63 339	95.25 296	97.49 375

PVSNet_0	93.57 19	96.41 304	95.74 321	98.41 259	99.84 121	95.22 343	100.00 1	100.00 1	98.08 118	97.55 347	99.78 279	84.40 376	100.00 1	100.00 1	81.99 410	100.00 1

K. test v3		95.46 340	95.14 343	96.40 356	97.53 386	93.40 377	99.99 232	99.23 303	95.49 310	92.70 403	99.73 282	84.26 377	98.12 373	93.94 363	93.38 324	97.68 350

GBi-Net		96.07 327	95.80 317	96.89 344	99.53 233	94.87 347	99.18 389	99.27 282	93.71 353	98.53 291	98.81 376	84.23 378	98.07 380	95.31 344	93.60 320	97.72 335

test1		96.07 327	95.80 317	96.89 344	99.53 233	94.87 347	99.18 389	99.27 282	93.71 353	98.53 291	98.81 376	84.23 378	98.07 380	95.31 344	93.60 320	97.72 335

FMVSNet2		96.22 317	95.60 329	98.06 290	99.53 233	98.33 244	99.45 360	99.27 282	93.71 353	98.03 322	98.84 375	84.23 378	98.10 378	93.97 362	93.40 323	97.73 329

testgi		96.18 319	95.93 310	96.93 342	98.98 316	94.20 370	100.00 1	99.07 362	97.16 206	96.06 378	99.86 258	84.08 381	97.79 394	90.38 393	97.80 251	98.81 281

Anonymous20240521		93.29 361	92.76 368	94.90 377	95.64 410	91.27 396	99.97 264	98.82 394	87.04 410	94.71 388	98.19 396	83.86 382	96.80 402	84.04 414	92.56 336	96.64 397

ACMH	96.25 11	96.77 285	96.62 279	97.21 330	98.96 318	94.43 367	99.64 339	99.33 243	97.43 186	96.55 370	99.97 212	83.52 383	99.54 259	99.07 226	95.13 304	97.66 355
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240529		96.93 281	96.22 298	99.05 219	99.79 150	97.30 304	99.16 395	99.47 79	88.51 405	98.69 280	100.00 1	83.50 384	100.00 1	99.83 125	97.02 270	99.83 209

lessismore_v0				96.05 364	97.55 385	91.80 392		99.22 307		91.87 404	99.91 250	83.50 384	98.68 333	92.48 376	90.42 368	97.68 350

UnsupCasMVSNet_eth		94.25 352	93.89 352	95.34 369	97.63 379	92.13 389	99.73 327	99.36 223	94.88 323	92.78 400	98.63 384	82.72 386	96.53 407	94.57 353	84.73 402	97.36 381

LF4IMVS		96.19 318	96.18 299	96.23 362	98.26 356	92.09 390	100.00 1	97.89 416	97.82 139	97.94 327	99.87 256	82.71 387	99.38 284	97.41 301	93.71 319	97.20 385

ACMH+	96.20 13	96.49 302	96.33 294	97.00 337	99.06 304	93.80 372	99.81 306	99.31 253	97.32 196	95.89 381	99.97 212	82.62 388	99.54 259	98.34 264	94.63 314	97.65 359

pmmvs3		90.62 379	89.36 385	94.40 380	90.53 428	91.49 394	100.00 1	96.73 427	84.21 417	93.65 397	96.65 411	82.56 389	94.83 418	82.28 417	77.62 419	96.89 393

XVG-ACMP-BASELINE		96.60 295	96.52 284	96.84 347	98.41 346	93.29 379	99.99 232	99.32 246	97.76 146	98.51 294	99.29 342	81.95 390	99.54 259	98.40 260	95.03 307	97.68 350

VPNet		96.41 304	95.76 320	98.33 265	98.61 339	98.30 248	99.48 357	99.45 103	96.98 221	98.87 269	99.88 255	81.57 391	98.93 312	99.22 219	87.82 389	97.76 289

MDA-MVSNet-bldmvs		91.65 374	89.94 382	96.79 350	96.72 399	96.70 322	99.42 365	98.94 386	88.89 403	66.97 434	98.37 393	81.43 392	95.91 414	89.24 402	89.46 375	97.75 300

MS-PatchMatch		95.66 337	95.87 313	95.05 371	97.80 374	89.25 404	98.88 412	99.30 259	96.35 275	96.86 362	99.01 363	81.35 393	99.43 280	93.30 369	99.98 113	96.46 400

USDC		95.90 333	95.70 323	96.50 355	98.60 340	92.56 388	100.00 1	98.30 403	97.77 144	96.92 359	99.94 242	81.25 394	99.45 278	93.54 367	94.96 311	97.49 375

TDRefinement		91.93 370	90.48 378	96.27 361	81.60 434	92.65 387	99.10 403	97.61 422	93.96 350	93.77 396	99.85 263	80.03 395	99.53 264	97.82 286	70.59 424	96.63 398

test_0402		94.35 350	93.70 355	96.32 360	97.92 370	93.60 373	99.61 344	98.85 393	88.19 408	94.68 389	99.48 330	80.01 396	98.58 346	89.39 400	95.15 303	96.77 394

tt0805		96.52 297	96.23 297	97.40 318	99.30 285	93.55 374	99.32 373	99.45 103	96.75 241	97.88 331	99.99 198	79.99 397	99.59 242	97.39 303	95.98 281	99.06 279

TinyColmap		95.50 339	95.12 344	96.64 351	98.69 336	93.00 381	99.40 366	97.75 419	96.40 271	96.14 377	99.87 256	79.47 398	99.50 269	93.62 366	94.72 313	97.40 380

LFMVS		97.42 258	96.62 279	99.81 109	99.80 145	99.50 142	99.16 395	99.56 70	94.48 337	100.00 1	100.00 1	79.35 399	100.00 1	99.89 113	97.37 264	99.94 141

pmmvs-eth3d		91.73 373	90.67 377	94.92 376	91.63 423	92.71 386	99.90 290	98.54 401	91.19 389	88.08 414	95.50 414	79.31 400	96.13 412	90.55 390	81.32 413	95.91 409

SSC-MVS3.2		95.32 341	94.97 347	96.37 358	98.29 354	92.75 384	100.00 1	99.30 259	95.46 312	98.36 301	99.42 334	78.92 401	98.63 337	93.28 370	91.72 350	97.72 335

new-patchmatchnet		90.30 380	89.46 384	92.84 391	90.77 426	88.55 408	99.83 302	98.80 395	90.07 400	87.86 415	95.00 417	78.77 402	94.30 421	84.86 412	79.15 416	95.68 412

test123		79.44 394	79.23 396	80.05 412	80.03 435	71.72 425	100.00 1	77.93 443	62.52 429	94.81 387	99.69 291	78.21 403	74.53 436	92.57 374	27.33 436	93.90 416

CMPMVS	66.12 22	90.65 378	92.04 371	86.46 403	96.18 403	66.87 433	98.03 421	99.38 213	83.38 419	85.49 420	99.55 324	77.59 404	98.80 324	94.44 355	94.31 317	93.72 418
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
mvs5depth		93.81 357	93.00 364	96.23 362	94.25 417	93.33 378	97.43 424	98.07 410	93.47 363	94.15 395	99.58 318	77.52 405	98.97 309	93.64 365	88.92 380	96.39 402

test_vis1_n_1920		97.77 241	97.24 262	99.34 195	99.79 150	98.04 267	100.00 1	99.25 293	98.88 52	100.00 1	100.00 1	77.52 405	100.00 1	99.88 115	99.85 148	100.00 1

pmmvs6		93.64 358	92.87 366	95.94 366	97.47 391	91.41 395	98.92 410	99.02 378	87.84 409	95.01 386	99.61 314	77.24 407	98.77 328	94.33 356	86.41 399	97.63 363

mmtdpeth		94.58 348	94.18 350	95.81 367	98.82 334	91.09 398	99.99 232	98.61 400	96.38 272	100.00 1	97.23 407	76.52 408	99.85 206	99.82 130	80.22 414	96.48 399

tmp_tt		75.80 398	74.26 400	80.43 411	52.91 443	53.67 442	87.42 430	97.98 414	61.80 430	67.04 433	100.00 1	76.43 409	96.40 408	96.47 325	28.26 435	91.23 425

APD_test1		93.07 365	94.14 351	89.85 396	99.18 291	72.49 424	99.76 319	98.90 391	92.86 379	96.35 372	99.94 242	75.56 410	99.91 188	86.73 408	97.98 236	97.15 387

MIMVSNet1		91.96 369	91.20 372	94.23 384	94.94 415	91.69 393	99.34 372	99.22 307	88.23 406	94.18 394	98.45 390	75.52 411	93.41 424	79.37 423	91.49 354	97.60 368

test_fmvs1_n		97.43 257	96.86 270	99.15 215	99.68 174	97.48 294	99.99 232	98.98 384	98.82 63	100.00 1	100.00 1	74.85 412	99.96 154	99.67 171	99.70 161	100.00 1

VDDNet		96.39 308	95.55 330	98.90 230	99.27 286	97.45 295	99.15 397	99.92 34	91.28 388	99.98 125	100.00 1	73.55 413	100.00 1	99.85 121	96.98 271	99.24 274

test_fmvs2		95.17 346	95.23 341	95.01 372	98.95 320	88.99 406	99.99 232	97.77 418	97.79 142	98.58 287	99.70 288	73.36 414	99.34 288	95.88 333	95.03 307	96.70 396

EGC-MVSNET		79.46 393	74.04 401	95.72 368	96.00 405	92.73 385	99.09 405	99.04 375	5.08 438	16.72 438	98.71 380	73.03 415	98.74 331	82.05 418	96.64 277	95.69 411

FMVSNet1		94.45 349	93.63 356	96.89 344	98.87 328	94.87 347	99.18 389	99.27 282	90.95 392	97.31 352	98.81 376	72.89 416	98.07 380	92.61 373	92.81 330	97.72 335

VDD-MVS		96.58 296	95.99 307	98.34 264	99.52 241	95.33 341	99.18 389	99.38 213	96.64 255	99.77 207	100.00 1	72.51 417	100.00 1	100.00 1	96.94 272	99.70 258

EG-PatchMatch MVS		92.94 366	92.49 370	94.29 383	95.87 406	87.07 411	99.07 408	98.11 408	93.19 372	88.98 412	98.66 383	70.89 418	99.08 299	92.43 377	95.21 299	96.72 395

test_method		91.04 377	91.10 374	90.85 393	98.34 348	77.63 420	100.00 1	98.93 388	76.69 424	96.25 375	98.52 388	70.44 419	97.98 386	89.02 404	91.74 348	96.92 392

UniMVSNet_ETH3D		95.28 343	94.41 349	97.89 306	98.91 322	95.14 344	99.13 400	99.35 234	92.11 383	97.17 356	99.66 298	70.28 420	99.36 285	97.88 284	95.18 301	99.16 275

OpenMVS_ROB	88.34 20	91.89 371	91.12 373	94.19 385	95.55 411	87.63 409	99.26 379	98.03 411	86.61 413	90.65 410	96.82 410	70.14 421	98.78 325	86.54 409	96.50 280	96.15 404

testmvs		80.17 391	81.95 394	74.80 414	58.54 441	59.58 439	100.00 1	87.14 440	76.09 425	99.61 219	100.00 1	67.06 422	74.19 437	98.84 236	50.30 431	90.64 426

test_vis1_n		96.69 291	95.81 315	99.32 200	99.14 293	97.98 270	99.97 264	98.98 384	98.45 90	100.00 1	100.00 1	66.44 423	99.99 100	99.78 139	99.57 173	100.00 1

UnsupCasMVSNet_bld		89.50 381	88.00 387	93.99 386	95.30 412	88.86 407	98.52 417	99.28 272	85.50 415	87.80 416	94.11 420	61.63 424	96.96 401	90.63 388	79.26 415	96.15 404

test_vis1_rt		93.10 364	92.93 365	93.58 388	99.63 200	85.07 413	99.99 232	93.71 434	97.49 179	90.96 406	97.10 408	60.40 425	99.95 167	99.24 216	97.90 243	95.72 410

Gipuma		84.73 388	83.50 393	88.40 399	97.50 387	82.21 417	88.87 428	99.05 372	65.81 428	85.71 419	90.49 425	53.70 426	96.31 409	78.64 424	91.74 348	86.67 427
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
mvsany_test3		89.36 382	88.96 386	90.56 394	91.95 420	78.97 419	99.74 322	96.59 430	96.84 233	89.25 411	96.07 412	52.59 427	97.11 400	95.17 347	82.44 409	95.58 413

EMVS		69.88 400	69.09 403	72.24 418	84.70 431	65.82 435	99.96 270	87.08 441	49.82 435	71.51 429	84.74 432	49.30 428	75.32 435	50.97 437	43.71 433	75.59 433

PM-MVS		88.39 383	87.41 388	91.31 392	91.73 422	82.02 418	99.79 311	96.62 428	91.06 391	90.71 409	95.73 413	48.60 429	95.96 413	90.56 389	81.91 412	95.97 408

E-PMN		70.72 399	70.06 402	72.69 417	83.92 432	65.48 436	99.95 276	92.72 436	49.88 434	72.30 428	86.26 431	47.17 430	77.43 434	53.83 436	44.49 432	75.17 434

testf1		84.40 389	84.79 391	83.23 407	95.71 407	58.71 440	98.79 414	97.75 419	81.58 420	84.94 421	98.07 399	45.33 431	97.73 395	77.09 428	83.85 404	93.24 421

APD_test2		84.40 389	84.79 391	83.23 407	95.71 407	58.71 440	98.79 414	97.75 419	81.58 420	84.94 421	98.07 399	45.33 431	97.73 395	77.09 428	83.85 404	93.24 421

ambc				88.45 398	86.84 430	70.76 427	97.79 423	98.02 413		90.91 407	95.14 415	38.69 433	98.51 351	94.97 349	84.23 403	96.09 407

test_f		86.87 387	86.06 390	89.28 397	91.45 425	76.37 422	99.87 297	97.11 424	91.10 390	88.46 413	93.05 423	38.31 434	96.66 405	91.77 381	83.46 407	94.82 414

test_fmvs3		87.19 386	87.02 389	87.71 400	92.69 419	76.64 421	99.96 270	97.27 423	93.55 360	90.82 408	94.03 421	38.00 435	92.19 426	93.49 368	83.35 408	94.32 415

FPMVS		77.92 397	79.45 395	73.34 416	76.87 437	46.81 443	98.24 419	99.05 372	59.89 431	73.55 427	98.34 394	36.81 436	86.55 429	80.96 419	91.35 358	86.65 428

PMMVS2		79.15 395	77.28 398	84.76 405	82.34 433	72.66 423	99.70 332	95.11 433	71.68 427	84.78 424	90.87 424	32.05 437	89.99 428	75.53 430	63.45 429	91.64 424

LCM-MVSNet		79.01 396	76.93 399	85.27 404	78.28 436	68.01 432	96.57 425	98.03 411	55.10 432	82.03 425	93.27 422	31.99 438	93.95 422	82.72 415	74.37 421	93.84 417

test_vis3_rt		79.61 392	78.19 397	83.86 406	88.68 429	69.56 428	99.81 306	82.19 442	86.78 412	68.57 430	84.51 433	25.06 439	98.26 365	89.18 403	78.94 417	83.75 430

ANet_high		66.05 402	63.44 406	73.88 415	61.14 440	63.45 437	95.68 427	87.18 439	79.93 422	47.35 436	80.68 436	22.35 440	72.33 438	61.24 433	35.42 434	85.88 429

wuyk23d		28.28 404	29.73 408	23.92 420	75.89 438	32.61 445	66.50 431	12.88 444	16.09 437	14.59 439	16.59 438	12.35 441	32.36 439	39.36 438	13.36 437	6.79 435

PMVS	60.66 23	65.98 403	65.05 404	68.75 419	55.06 442	38.40 444	88.19 429	96.98 425	48.30 436	44.82 437	88.52 428	12.22 442	86.49 430	67.58 431	83.79 406	81.35 432
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	68.59 21	67.22 401	64.68 405	74.84 413	74.67 439	62.32 438	95.84 426	90.87 438	50.98 433	58.72 435	81.05 435	12.20 443	78.95 433	61.06 434	56.75 430	83.24 431
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
mmdepth		0.01 409	0.02 412	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.14 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

monomultidepth		0.01 409	0.02 412	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.14 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

test_blank		0.07 408	0.09 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.79 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet_test		0.01 409	0.02 412	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.14 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

DCPMVS		0.01 409	0.02 412	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.14 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

sosnet-low-res		0.01 409	0.02 412	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.14 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

sosnet		0.01 409	0.02 412	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.14 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uncertanet		0.01 409	0.02 412	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.14 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

Regformer		0.01 409	0.02 412	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.14 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

ab-mvs-re		8.33 406	11.11 409	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	100.00 1	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet		0.01 409	0.02 412	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.14 440	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

WAC-MVS						97.98 270								95.74 335

FOURS1					100.00 1	99.97 21	100.00 1	99.42 144	98.52 86	100.00 1

MSC_two_6792asdad				100.00 1	100.00 1	100.00 1		99.42 144					100.00 1	100.00 1	100.00 1	100.00 1

No_MVS				100.00 1	100.00 1	100.00 1		99.42 144					100.00 1	100.00 1	100.00 1	100.00 1

eth-test2					0.00 444

eth-test					0.00 444

IU-MVS					100.00 1	99.99 5		99.42 144	99.12 7	100.00 1				100.00 1	100.00 1	100.00 1

save fliter					99.99 49	99.93 47	100.00 1	99.42 144	98.93 43

test_0728_SECOND				100.00 1	99.99 49	99.99 5	100.00 1	99.42 144					100.00 1	100.00 1	100.00 1	100.00 1

GSMVS																99.91 157

test_part2					100.00 1	99.99 5				100.00 1

MTGPA								99.42 144

MTMP							100.00 1	99.18 324

gm-plane-assit					99.52 241	97.26 306			95.86 294		100.00 1		99.43 280	98.76 241

test9_res														100.00 1	100.00 1	100.00 1

agg_prior2														100.00 1	100.00 1	100.00 1

agg_prior					100.00 1	99.88 77		99.42 144		100.00 1			99.97 137

test_prior4						99.93 47	100.00 1

test_prior				99.90 79	100.00 1	99.75 99		99.73 56					99.97 137			100.00 1

旧先验2							100.00 1		98.11 117	100.00 1			100.00 1	99.67 171

新几何2							100.00 1

无先验							100.00 1	99.80 43	97.98 125				100.00 1	99.33 209		100.00 1

原ACMM2							100.00 1

testdata2													100.00 1	97.36 304

testdata1							100.00 1		98.77 75

plane_prior7					99.00 312	94.78 357

plane_prior5								99.40 197					99.55 256	99.79 133	95.57 286	97.76 289

plane_prior4											99.97 212

plane_prior3						94.79 356			99.03 21	99.08 256

plane_prior2							100.00 1		99.00 27

plane_prior1					99.02 307

plane_prior						94.80 353	100.00 1		99.03 21						95.58 282

n2								0.00 445

nn								0.00 445

door-mid								96.32 431

test11								99.42 144

door								96.13 432

HQP5-MVS						94.82 350

HQP-NCC					99.07 300		100.00 1		99.04 16	99.17 246

ACMP_Plane					99.07 300		100.00 1		99.04 16	99.17 246

BP-MVS														99.79 133

HQP4-MVS										99.17 246			99.57 247			97.77 287

HQP3-MVS								99.40 197							95.58 282

NP-MVS					99.07 300	94.81 352					99.97 212

ACMMP++_ref															94.58 316

ACMMP++															95.17 302

High-resolution multi-view benchmark