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.

DP-MVS Recon		91.72 112	90.85 123	94.34 42	99.50 1	85.00 85	98.51 50	95.96 176	80.57 325	88.08 187	97.63 101	76.84 150	99.89 11	85.67 229	94.88 145	98.13 94

TestfortrainingZip				97.22 3	99.48 2	91.93 7	98.35 58	97.26 24	85.61 188	99.54 1	99.26 1	91.36 5	99.98 2		96.55 117	99.73 3

MCST-MVS		96.17 4	96.12 7	96.32 8	99.42 3	89.36 11	98.94 32	97.10 37	95.17 4	92.11 110	98.46 41	87.33 28	99.97 3	97.21 48	99.31 4	99.63 8

MG-MVS		94.25 38	93.72 50	95.85 13	99.38 4	89.35 12	97.98 82	98.09 9	89.99 70	92.34 104	96.97 136	81.30 76	98.99 130	88.54 197	98.88 20	99.20 26

AdaColmap		88.81 204	87.61 216	92.39 149	99.33 5	79.95 249	96.70 202	95.58 204	77.51 382	83.05 276	96.69 149	61.90 354	99.72 60	84.29 239	93.47 171	97.50 162

CNVR-MVS		96.30 1	96.54 1	95.55 16	99.31 6	87.69 26	99.06 24	97.12 35	94.66 11	96.79 31	98.78 16	86.42 33	99.95 6	97.59 41	99.18 7	99.00 34

NCCC		95.63 8	95.94 10	94.69 34	99.21 7	85.15 79	99.16 12	96.96 50	94.11 16	95.59 51	98.64 26	85.07 40	99.91 8	95.61 66	99.10 9	99.00 34

OPU-MVS				97.30 2	99.19 8	92.31 3	99.12 17				98.54 31	92.06 3	99.84 19	99.11 5	99.37 1	99.74 1

aaEdge-Enhanced		94.82 22	95.04 24	94.17 53	99.17 9	83.70 111	97.66 107	97.22 25	85.79 184	95.34 54	98.90 6	84.89 41	99.86 15	97.78 37	98.60 36	98.94 39

ZD-MVS					99.09 10	83.22 124		96.60 102	82.88 282	93.61 85	98.06 73	82.93 66	99.14 120	95.51 69	98.49 43

aaatest				94.20 52	99.06 11	83.70 111	98.35 58	97.14 31	87.45 125	97.03 28	98.90 6		99.96 4	97.78 37	98.60 36	98.94 39

MED-MVS		95.59 10	96.05 9	94.21 49	99.06 11	83.70 111	98.35 58	97.14 31	87.65 119	97.03 28	98.83 11	89.87 13	99.96 4	97.78 37	98.71 31	98.97 37

TestfortrainingZip a		94.24 39	94.19 44	94.40 41	99.06 11	84.33 97	98.35 58	96.81 67	87.65 119	95.97 47	98.83 11	84.06 54	99.89 11	91.98 128	95.03 144	98.97 37

DVP-MVS++		96.05 5	96.41 4	94.96 26	99.05 14	85.34 68	98.13 72	96.77 74	88.38 94	97.70 15	98.77 17	92.06 3	99.84 19	97.47 42	99.37 1	99.70 4

MSC_two_6792asdad				97.14 4	99.05 14	92.19 4		96.83 63					99.81 29	98.08 27	98.81 24	99.43 12

No_MVS				97.14 4	99.05 14	92.19 4		96.83 63					99.81 29	98.08 27	98.81 24	99.43 12

DVP-MVS		95.58 11	95.91 11	94.57 37	99.05 14	85.18 74	99.06 24	96.46 123	88.75 84	96.69 32	98.76 19	87.69 26	99.76 47	97.90 31	98.85 21	98.77 48
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					99.05 14	85.18 74	99.11 20	96.78 68	88.75 84	97.65 19	98.91 3	87.69 26

test_0728_SECOND				95.14 22	99.04 19	86.14 45	99.06 24	96.77 74					99.84 19	97.90 31	98.85 21	99.45 11

SED-MVS		95.88 6	96.22 5	94.87 27	99.03 20	85.03 83	99.12 17	96.78 68	88.72 86	97.79 12	98.91 3	88.48 20	99.82 25	98.15 23	98.97 17	99.74 1

IU-MVS					99.03 20	85.34 68		96.86 61	92.05 43	98.74 2				98.15 23	98.97 17	99.42 14

test_241102_ONE					99.03 20	85.03 83		96.78 68	88.72 86	97.79 12	98.90 6	88.48 20	99.82 25

test-260524					99.01 23	85.87 52		96.82 66		95.25 56		86.23 35	99.92 7	97.87 34	98.71 31

test_one_0601					98.91 24	84.56 94		96.70 85	88.06 104	96.57 37	98.77 17	88.04 24

test_part2					98.90 25	85.14 80				96.07 44

PAPR		92.74 74	92.17 95	94.45 39	98.89 26	84.87 89	97.20 146	96.20 155	87.73 114	88.40 177	98.12 65	78.71 112	99.76 47	87.99 204	96.28 121	98.74 50

DeepC-MVS_fast	89.06 2	94.48 32	94.30 41	95.02 24	98.86 27	85.68 58	98.06 78	96.64 96	93.64 22	91.74 117	98.54 31	80.17 89	99.90 9	92.28 120	98.75 29	99.49 9
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
APDe-MVS		94.56 29	94.75 28	93.96 59	98.84 28	83.40 120	98.04 80	96.41 129	85.79 184	95.00 64	98.28 55	84.32 51	99.18 117	97.35 45	98.77 28	99.28 22
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DPE-MVS		95.32 13	95.55 15	94.64 35	98.79 29	84.87 89	97.77 98	96.74 79	86.11 170	96.54 38	98.89 9	88.39 22	99.74 55	97.67 40	99.05 12	99.31 21
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APD-MVS		93.61 51	93.59 55	93.69 74	98.76 30	83.26 123	97.21 144	96.09 163	82.41 293	94.65 71	98.21 57	81.96 73	98.81 142	94.65 81	98.36 51	99.01 33
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
HFP-MVS		92.89 68	92.86 75	92.98 110	98.71 31	81.12 196	97.58 114	96.70 85	85.20 202	91.75 116	97.97 80	78.47 116	99.71 63	90.95 140	98.41 47	98.12 95

region2R		92.72 77	92.70 77	92.79 121	98.68 32	80.53 229	97.53 119	96.51 116	85.22 200	91.94 114	97.98 78	77.26 138	99.67 71	90.83 147	98.37 50	98.18 88

test_prior				93.09 105	98.68 32	81.91 167		96.40 131					99.06 127			98.29 80

ACMMPR		92.69 82	92.67 78	92.75 123	98.66 34	80.57 223	97.58 114	96.69 87	85.20 202	91.57 118	97.92 81	77.01 147	99.67 71	90.95 140	98.41 47	98.00 108

API-MVS		90.18 163	88.97 180	93.80 63	98.66 34	82.95 130	97.50 123	95.63 203	75.16 407	86.31 222	97.69 93	72.49 238	99.90 9	81.26 278	96.07 128	98.56 62

CDPH-MVS		93.12 61	92.91 72	93.74 67	98.65 36	83.88 104	97.67 106	96.26 149	83.00 279	93.22 89	98.24 56	81.31 75	99.21 110	89.12 181	98.74 30	98.14 92

TEST9					98.64 37	83.71 109	97.82 93	96.65 93	84.29 239	95.16 58	98.09 68	84.39 47	99.36 100

train_agg		94.28 36	94.45 36	93.74 67	98.64 37	83.71 109	97.82 93	96.65 93	84.50 229	95.16 58	98.09 68	84.33 48	99.36 100	95.91 62	98.96 19	98.16 90

test_8					98.63 39	83.64 115	97.81 95	96.63 98	84.50 229	95.10 61	98.11 66	84.33 48	99.23 108

HPM-MVS++		95.32 13	95.48 17	94.85 28	98.62 40	86.04 46	97.81 95	96.93 54	92.45 32	95.69 49	98.50 36	85.38 38	99.85 17	94.75 79	99.18 7	98.65 58

agg_prior					98.59 41	83.13 126		96.56 108		94.19 76			99.16 119

CSCG		92.02 102	91.65 105	93.12 103	98.53 42	80.59 220	97.47 124	97.18 29	77.06 390	84.64 247	97.98 78	83.98 56	99.52 88	90.72 149	97.33 86	99.23 25

XVS		92.69 82	92.71 76	92.63 132	98.52 43	80.29 235	97.37 135	96.44 125	87.04 145	91.38 120	97.83 89	77.24 140	99.59 79	90.46 155	98.07 59	98.02 101

X-MVStestdata		86.26 268	84.14 289	92.63 132	98.52 43	80.29 235	97.37 135	96.44 125	87.04 145	91.38 120	20.73 538	77.24 140	99.59 79	90.46 155	98.07 59	98.02 101

FOURS1					98.51 45	78.01 320	98.13 72	96.21 154	83.04 276	94.39 74

CP-MVS		92.54 88	92.60 80	92.34 152	98.50 46	79.90 251	98.40 56	96.40 131	84.75 217	90.48 138	98.09 68	77.40 136	99.21 110	91.15 137	98.23 56	97.92 115

PAPM_NR		91.46 119	90.82 124	93.37 93	98.50 46	81.81 175	95.03 326	96.13 160	84.65 222	86.10 226	97.65 99	79.24 102	99.75 52	83.20 257	96.88 105	98.56 62

MAR-MVS		90.63 145	90.22 142	91.86 190	98.47 48	78.20 316	97.18 148	96.61 99	83.87 253	88.18 184	98.18 59	68.71 290	99.75 52	83.66 251	97.15 93	97.63 145
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
patch_mono-2		95.14 15	96.08 8	92.33 154	98.44 49	77.84 328	98.43 53	97.21 26	92.58 30	97.68 17	97.65 99	86.88 30	99.83 23	98.25 19	97.60 75	99.33 19

mPP-MVS		91.88 108	91.82 101	92.07 175	98.38 50	78.63 297	97.29 141	96.09 163	85.12 208	88.45 176	97.66 95	75.53 184	99.68 69	89.83 167	98.02 62	97.88 117

SR-MVS		92.16 99	92.27 90	91.83 197	98.37 51	78.41 304	96.67 204	95.76 193	82.19 297	91.97 112	98.07 72	76.44 159	98.64 146	93.71 94	97.27 88	98.45 68

test12				94.25 46	98.34 52	85.55 64		96.35 141		92.36 103		80.84 79	99.22 109		98.31 53	97.98 110

CPTT-MVS		89.72 175	89.87 160	89.29 294	98.33 53	73.30 396	97.70 104	95.35 225	75.68 402	87.40 196	97.44 111	70.43 274	98.25 172	89.56 176	96.90 103	96.33 244

MSP-MVS		95.62 9	96.54 1	92.86 116	98.31 54	80.10 246	97.42 131	96.78 68	92.20 38	97.11 25	98.29 54	93.46 1	99.10 124	96.01 59	99.30 5	99.38 15
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
MSLP-MVS++		94.28 36	94.39 38	93.97 58	98.30 55	84.06 103	98.64 45	96.93 54	90.71 59	93.08 92	98.70 24	79.98 93	99.21 110	94.12 88	99.07 11	98.63 59

PGM-MVS		91.93 105	91.80 102	92.32 156	98.27 56	79.74 258	95.28 306	97.27 22	83.83 256	90.89 132	97.78 91	76.12 170	99.56 85	88.82 190	97.93 66	97.66 141

ZNCC-MVS		92.75 73	92.60 80	93.23 97	98.24 57	81.82 174	97.63 108	96.50 118	85.00 213	91.05 128	97.74 92	78.38 117	99.80 33	90.48 153	98.34 52	98.07 98

save fliter					98.24 57	83.34 121	98.61 47	96.57 106	91.32 49

114514_t		88.79 206	87.57 218	92.45 143	98.21 59	81.74 177	96.99 168	95.45 215	75.16 407	82.48 280	95.69 173	68.59 291	98.50 156	80.33 283	95.18 142	97.10 202

GST-MVS		92.43 93	92.22 94	93.04 107	98.17 60	81.64 182	97.40 133	96.38 135	84.71 220	90.90 131	97.40 113	77.55 134	99.76 47	89.75 171	97.74 71	97.72 135

DP-MVS		81.47 356	78.28 375	91.04 237	98.14 61	78.48 300	95.09 325	86.97 469	61.14 481	71.12 412	92.78 289	59.59 365	99.38 97	53.11 473	86.61 281	95.27 281

MP-MVS		92.61 86	92.67 78	92.42 147	98.13 62	79.73 259	97.33 138	96.20 155	85.63 187	90.53 135	97.66 95	78.14 123	99.70 66	92.12 124	98.30 54	97.85 122
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
9.14			94.26 43		98.10 63		98.14 69	96.52 115	84.74 218	94.83 68	98.80 14	82.80 68	99.37 99	95.95 61	98.42 46

PHI-MVS		93.59 52	93.63 53	93.48 88	98.05 64	81.76 176	98.64 45	97.13 33	82.60 289	94.09 78	98.49 37	80.35 84	99.85 17	94.74 80	98.62 35	98.83 45

SMA-MVS		94.70 25	94.68 31	94.76 31	98.02 65	85.94 50	97.47 124	96.77 74	85.32 197	97.92 7	98.70 24	83.09 65	99.84 19	95.79 63	99.08 10	98.49 65
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
PLC	83.97 7	88.00 230	87.38 224	89.83 284	98.02 65	76.46 358	97.16 152	94.43 289	79.26 361	81.98 290	96.28 156	69.36 283	99.27 104	77.71 318	92.25 193	93.77 315
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MTAPA		92.45 91	92.31 89	92.86 116	97.90 67	80.85 213	92.88 388	96.33 142	87.92 108	90.20 143	98.18 59	76.71 155	99.76 47	92.57 117	98.09 58	97.96 114

APD-MVS_3200maxsize		91.23 127	91.35 110	90.89 246	97.89 68	76.35 362	96.30 235	95.52 209	79.82 348	91.03 129	97.88 86	74.70 204	98.54 154	92.11 125	96.89 104	97.77 130

HPM-MVS		91.62 116	91.53 108	91.89 188	97.88 69	79.22 273	96.99 168	95.73 196	82.07 299	89.50 156	97.19 125	75.59 182	98.93 137	90.91 142	97.94 64	97.54 154
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
SD-MVS		94.84 21	95.02 26	94.29 44	97.87 70	84.61 92	97.76 100	96.19 157	89.59 76	96.66 34	98.17 62	84.33 48	99.60 78	96.09 58	98.50 42	98.66 57
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
NormalMVS		92.88 69	92.97 71	92.59 136	97.80 71	82.02 158	97.94 85	94.70 259	92.34 34	92.15 108	96.53 152	77.03 145	98.57 150	91.13 138	97.12 95	97.19 196

lecture		93.17 59	93.57 57	91.96 184	97.80 71	78.79 293	98.50 51	96.98 46	86.61 160	94.75 70	98.16 63	78.36 119	99.35 102	93.89 90	97.12 95	97.75 132

dcpmvs_2		93.10 62	93.46 61	92.02 182	97.77 73	79.73 259	94.82 332	93.86 339	86.91 148	91.33 123	96.76 145	85.20 39	98.06 180	96.90 53	97.60 75	98.27 82

原ACMM1				91.22 232	97.77 73	78.10 318		96.61 99	81.05 314	91.28 125	97.42 112	77.92 127	98.98 131	79.85 292	98.51 40	96.59 235

SR-MVS-dyc-post		91.29 125	91.45 109	90.80 248	97.76 75	76.03 367	96.20 245	95.44 216	80.56 326	90.72 133	97.84 87	75.76 178	98.61 147	91.99 126	96.79 110	97.75 132

RE-MVS-def			91.18 117		97.76 75	76.03 367	96.20 245	95.44 216	80.56 326	90.72 133	97.84 87	73.36 225		91.99 126	96.79 110	97.75 132

TSAR-MVS + MP.		94.79 24	95.17 23	93.64 77	97.66 77	84.10 102	95.85 281	96.42 128	91.26 50	97.49 22	96.80 144	86.50 32	98.49 157	95.54 68	99.03 13	98.33 74
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MGCNet		95.58 11	95.44 18	96.01 11	97.63 78	89.26 13	99.27 6	96.59 103	94.71 10	97.08 26	97.99 75	78.69 113	99.86 15	99.15 3	97.85 67	98.91 42

HPM-MVS_fast		90.38 158	90.17 145	91.03 238	97.61 79	77.35 343	97.15 154	95.48 212	79.51 354	88.79 169	96.90 137	71.64 258	98.81 142	87.01 219	97.44 80	96.94 215

EI-MVSNet-Vis-set		91.84 109	91.77 103	92.04 181	97.60 80	81.17 194	96.61 205	96.87 59	88.20 101	89.19 160	97.55 107	78.69 113	99.14 120	90.29 162	90.94 214	95.80 257

CNLPA		86.96 253	85.37 263	91.72 204	97.59 81	79.34 270	97.21 144	91.05 435	74.22 414	78.90 322	96.75 147	67.21 305	98.95 134	74.68 357	90.77 217	96.88 221

ACMMP		90.39 156	89.97 154	91.64 207	97.58 82	78.21 315	96.78 193	96.72 83	84.73 219	84.72 244	97.23 123	71.22 262	99.63 75	88.37 202	92.41 189	97.08 207
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
SF-MVS		94.17 40	94.05 47	94.55 38	97.56 83	85.95 48	97.73 102	96.43 127	84.02 246	95.07 63	98.74 21	82.93 66	99.38 97	95.42 70	98.51 40	98.32 76

CANet		94.89 19	94.64 32	95.63 14	97.55 84	88.12 20	99.06 24	96.39 133	94.07 18	95.34 54	97.80 90	76.83 152	99.87 13	97.08 51	97.64 74	98.89 43

PVSNet_BlendedMVS		90.05 165	89.96 155	90.33 265	97.47 85	83.86 105	98.02 81	96.73 81	87.98 106	89.53 154	89.61 341	76.42 160	99.57 83	94.29 85	79.59 337	87.57 421

PVSNet_Blended		93.13 60	92.98 70	93.57 82	97.47 85	83.86 105	99.32 4	96.73 81	91.02 56	89.53 154	96.21 157	76.42 160	99.57 83	94.29 85	95.81 136	97.29 187

reproduce-ours		92.70 80	93.02 68	91.75 199	97.45 87	77.77 332	96.16 248	95.94 180	84.12 242	92.45 99	98.43 43	80.06 91	99.24 106	95.35 71	97.18 91	98.24 84

our_new_method		92.70 80	93.02 68	91.75 199	97.45 87	77.77 332	96.16 248	95.94 180	84.12 242	92.45 99	98.43 43	80.06 91	99.24 106	95.35 71	97.18 91	98.24 84

新几何1				93.12 103	97.44 89	81.60 185		96.71 84	74.54 413	91.22 126	97.57 103	79.13 104	99.51 90	77.40 325	98.46 44	98.26 83

LS3D		82.22 346	79.94 361	89.06 298	97.43 90	74.06 391	93.20 382	92.05 413	61.90 475	73.33 390	95.21 203	59.35 368	99.21 110	54.54 469	92.48 185	93.90 313

reproduce_model		92.53 89	92.87 73	91.50 215	97.41 91	77.14 349	96.02 258	95.91 183	83.65 264	92.45 99	98.39 47	79.75 96	99.21 110	95.27 74	96.98 100	98.14 92

test_yl		91.46 119	90.53 130	94.24 47	97.41 91	85.18 74	98.08 75	97.72 11	80.94 315	89.85 145	96.14 158	75.61 180	98.81 142	90.42 158	88.56 254	98.74 50

DCV-MVSNet		91.46 119	90.53 130	94.24 47	97.41 91	85.18 74	98.08 75	97.72 11	80.94 315	89.85 145	96.14 158	75.61 180	98.81 142	90.42 158	88.56 254	98.74 50

EI-MVSNet-UG-set		91.35 124	91.22 113	91.73 202	97.39 94	80.68 217	96.47 217	96.83 63	87.92 108	88.30 181	97.36 114	77.84 128	99.13 122	89.43 179	89.45 230	95.37 276

旧先验1					97.39 94	79.58 264		96.54 112			98.08 71	84.00 55			97.42 82	97.62 147

TSAR-MVS + GP.		94.35 35	94.50 34	93.89 60	97.38 96	83.04 128	98.10 74	95.29 230	91.57 46	93.81 81	97.45 108	86.64 31	99.43 95	96.28 57	94.01 158	99.20 26

MVS_111021_HR		93.41 57	93.39 62	93.47 90	97.34 97	82.83 133	97.56 116	98.27 6	89.16 82	89.71 148	97.14 126	79.77 95	99.56 85	93.65 95	97.94 64	98.02 101

MP-MVS-pluss		92.58 87	92.35 86	93.29 94	97.30 98	82.53 139	96.44 220	96.04 169	84.68 221	89.12 162	98.37 50	77.48 135	99.74 55	93.31 102	98.38 49	97.59 150
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
EPNet		94.06 44	94.15 45	93.76 65	97.27 99	84.35 96	98.29 64	97.64 14	94.57 12	95.36 53	96.88 139	79.96 94	99.12 123	91.30 134	96.11 127	97.82 126
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP_NAP		93.46 56	93.23 65	94.17 53	97.16 100	84.28 100	96.82 188	96.65 93	86.24 167	94.27 75	97.99 75	77.94 125	99.83 23	93.39 97	98.57 38	98.39 72

LFMVS		89.27 190	87.64 213	94.16 56	97.16 100	85.52 65	97.18 148	94.66 267	79.17 362	89.63 151	96.57 150	55.35 410	98.22 173	89.52 178	89.54 229	98.74 50

DeepPCF-MVS	89.82 1	94.61 26	96.17 6	89.91 281	97.09 102	70.21 432	98.99 30	96.69 87	95.57 2	95.08 62	99.23 2	86.40 34	99.87 13	97.84 35	98.66 34	99.65 7

VNet		92.11 101	91.22 113	94.79 30	96.91 103	86.98 33	97.91 88	97.96 10	86.38 164	93.65 83	95.74 168	70.16 277	98.95 134	93.39 97	88.87 243	98.43 70

TAPA-MVS	81.61 12	85.02 296	83.67 295	89.06 298	96.79 104	73.27 399	95.92 265	94.79 256	74.81 410	80.47 306	96.83 141	71.07 264	98.19 175	49.82 483	92.57 182	95.71 264
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Anonymous202405211		84.41 309	81.93 330	91.85 192	96.78 105	78.41 304	97.44 127	91.34 429	70.29 447	84.06 255	94.26 249	41.09 470	98.96 132	79.46 294	82.65 320	98.17 89

reproduce_monomvs		87.80 235	87.60 217	88.40 313	96.56 106	80.26 238	95.80 284	96.32 144	91.56 47	73.60 383	88.36 360	88.53 19	96.25 323	90.47 154	67.23 429	88.67 396

SPE-MVS-test		92.98 64	93.67 52	90.90 245	96.52 107	76.87 351	98.68 42	94.73 258	90.36 67	94.84 67	97.89 85	77.94 125	97.15 275	94.28 87	97.80 69	98.70 56

BridgeMVS		94.60 28	94.30 41	95.48 18	96.45 108	88.82 15	96.33 232	95.58 204	91.12 52	95.84 48	93.87 266	83.47 61	98.37 167	97.26 46	98.81 24	99.24 24

DELS-MVS		94.98 16	94.49 35	96.44 7	96.42 109	90.59 8	99.21 9	97.02 43	94.40 15	91.46 119	97.08 131	83.32 62	99.69 67	92.83 111	98.70 33	99.04 32
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
balanced_ft_v1		92.00 103	91.12 118	94.64 35	96.35 110	86.78 35	94.96 327	94.70 259	87.65 119	90.20 143	93.01 284	69.71 280	98.02 183	97.40 44	96.13 126	99.11 29

MM		95.85 7	95.74 12	96.15 9	96.34 111	89.50 10	99.18 10	98.10 8	95.68 1	96.64 35	97.92 81	80.72 80	99.80 33	99.16 2	97.96 63	99.15 28

thres200		88.92 200	87.65 212	92.73 125	96.30 112	85.62 63	97.85 91	98.86 1	84.38 234	84.82 241	93.99 262	75.12 198	98.01 185	70.86 389	86.67 280	94.56 301

CS-MVS		92.73 75	93.48 60	90.48 258	96.27 113	75.93 372	98.55 48	94.93 244	89.32 79	94.54 73	97.67 94	78.91 108	97.02 280	93.80 91	97.32 87	98.49 65

DPM-MVS		96.21 3	95.53 16	98.26 1	96.26 114	95.09 1	99.15 13	96.98 46	93.39 24	96.45 39	98.79 15	90.17 10	99.99 1	89.33 180	99.25 6	99.70 4

tfpn200view9		88.48 214	87.15 228	92.47 141	96.21 115	85.30 72	97.44 127	98.85 2	83.37 268	83.99 257	93.82 268	75.36 191	97.93 188	69.04 397	86.24 287	94.17 305

thres400		88.42 217	87.15 228	92.23 162	96.21 115	85.30 72	97.44 127	98.85 2	83.37 268	83.99 257	93.82 268	75.36 191	97.93 188	69.04 397	86.24 287	93.45 321

myMVS_eth3d28		92.72 77	92.23 92	94.21 49	96.16 117	87.46 31	97.37 135	96.99 45	88.13 103	88.18 184	95.47 189	84.12 53	98.04 181	92.46 119	91.17 210	97.14 199

test222					96.15 118	78.41 304	95.87 279	96.46 123	71.97 439	89.66 150	97.45 108	76.33 163			98.24 55	98.30 79

HY-MVS	84.06 6	91.63 115	90.37 137	95.39 21	96.12 119	88.25 19	90.22 424	97.58 15	88.33 97	90.50 137	91.96 303	79.26 101	99.06 127	90.29 162	89.07 239	98.88 44

thres100view900		88.30 220	86.95 235	92.33 154	96.10 120	84.90 88	97.14 155	98.85 2	82.69 287	83.41 270	93.66 272	75.43 188	97.93 188	69.04 397	86.24 287	94.17 305

thres600view7		88.06 227	86.70 243	92.15 170	96.10 120	85.17 78	97.14 155	98.85 2	82.70 286	83.41 270	93.66 272	75.43 188	97.82 198	67.13 406	85.88 292	93.45 321

WTY-MVS		92.65 85	91.68 104	95.56 15	96.00 122	88.90 14	98.23 66	97.65 13	88.57 89	89.82 147	97.22 124	79.29 100	99.06 127	89.57 174	88.73 245	98.73 54

testing91		91.90 107	91.31 112	93.66 76	95.99 123	85.68 58	97.39 134	96.89 57	86.75 156	88.85 168	95.23 201	83.93 57	97.90 195	88.91 184	87.89 269	97.41 173

testing99		91.91 106	91.35 110	93.60 80	95.98 124	85.70 56	97.31 139	96.92 56	86.82 152	88.91 166	95.25 197	84.26 52	97.89 196	88.80 191	87.94 268	97.21 192

MVSTER		89.25 191	88.92 183	90.24 268	95.98 124	84.66 91	96.79 191	95.36 223	87.19 139	80.33 309	90.61 325	90.02 12	95.97 333	85.38 232	78.64 346	90.09 352

testing11		92.48 90	92.04 99	93.78 64	95.94 126	86.00 47	97.56 116	97.08 38	87.52 123	89.32 157	95.40 192	84.60 44	98.02 183	91.93 130	89.04 240	97.32 182

testing3-2		91.37 122	91.01 121	92.44 145	95.93 127	83.77 108	98.83 37	97.45 16	86.88 149	86.63 216	94.69 235	84.57 45	97.75 201	89.65 172	84.44 302	95.80 257

testdata				90.13 271	95.92 128	74.17 389		96.49 121	73.49 422	94.82 69	97.99 75	78.80 111	97.93 188	83.53 254	97.52 77	98.29 80

FBQ-MVS		91.64 114	90.94 122	93.73 69	95.88 129	84.93 86	96.78 193	96.95 51	87.21 138	90.53 135	94.44 245	80.88 77	97.92 193	87.30 214	88.50 260	98.33 74

PatchMatch-RL		85.00 297	83.66 296	89.02 300	95.86 130	74.55 386	92.49 393	93.60 370	79.30 359	79.29 321	91.47 309	58.53 375	98.45 162	70.22 393	92.17 195	94.07 310

testing222		91.09 130	90.49 132	92.87 115	95.82 131	85.04 82	96.51 215	97.28 21	86.05 173	89.13 161	95.34 194	80.16 90	96.62 310	85.82 227	88.31 264	96.96 214

ETVMVS		90.99 133	90.26 140	93.19 100	95.81 132	85.64 62	96.97 173	97.18 29	85.43 194	88.77 171	94.86 227	82.00 72	96.37 317	82.70 262	88.60 250	97.57 151

sasdasda		92.27 96	91.22 113	95.41 19	95.80 133	88.31 17	97.09 162	94.64 270	88.49 91	92.99 94	97.31 116	72.68 234	98.57 150	93.38 99	88.58 252	99.36 17

canonicalmvs		92.27 96	91.22 113	95.41 19	95.80 133	88.31 17	97.09 162	94.64 270	88.49 91	92.99 94	97.31 116	72.68 234	98.57 150	93.38 99	88.58 252	99.36 17

fmvsm_s_conf0.5_n_9		94.52 30	95.22 21	92.41 148	95.79 135	78.61 298	98.73 39	96.00 171	94.91 9	97.73 14	98.73 22	79.09 105	99.79 37	99.14 4	96.86 107	98.83 45

Anonymous20240529		83.15 329	80.60 350	90.80 248	95.74 136	78.27 310	96.81 190	94.92 245	60.10 485	81.89 292	92.54 290	45.82 452	98.82 141	79.25 300	78.32 352	95.31 278

MVS_111021_LR		91.60 117	91.64 106	91.47 218	95.74 136	78.79 293	96.15 250	96.77 74	88.49 91	88.64 173	97.07 132	72.33 242	99.19 116	93.13 108	96.48 119	96.43 239

MGCFI-Net		91.95 104	91.03 120	94.72 33	95.68 138	86.38 40	96.93 178	94.48 280	88.25 99	92.78 97	97.24 122	72.34 241	98.46 160	93.13 108	88.43 261	99.32 20

fmvsm_s_conf0.5_n_11		94.41 33	95.19 22	92.09 172	95.65 139	80.91 211	99.23 8	94.85 251	94.92 8	97.68 17	98.82 13	79.31 99	99.78 40	98.83 9	97.38 84	95.60 268

PS-MVSNAJ		94.17 40	93.52 58	96.10 10	95.65 139	92.35 2	98.21 67	95.79 192	92.42 33	96.24 41	98.18 59	71.04 265	99.17 118	96.77 54	97.39 83	96.79 225

WBMVS		87.73 238	86.79 239	90.56 255	95.61 141	85.68 58	97.63 108	95.52 209	83.77 258	78.30 329	88.44 359	86.14 36	95.78 346	82.54 263	73.15 381	90.21 347

UBG		92.68 84	92.35 86	93.70 73	95.61 141	85.65 61	97.25 142	97.06 40	87.92 108	89.28 158	95.03 215	86.06 37	98.07 179	92.24 121	90.69 218	97.37 177

Anonymous20231211		79.72 376	77.19 384	87.33 350	95.59 143	77.16 348	95.18 317	94.18 318	59.31 489	72.57 398	86.20 401	47.89 445	95.66 354	74.53 361	69.24 409	89.18 373

PRO-TEST		93.79 49	93.63 53	94.29 44	95.54 144	86.59 39	97.30 140	95.42 220	92.49 31	95.39 52	97.33 115	75.72 179	97.16 270	97.19 49	96.29 120	99.11 29

alignmvs		92.97 65	92.26 91	95.12 23	95.54 144	87.77 24	98.67 43	96.38 135	88.04 105	93.01 93	97.45 108	79.20 103	98.60 148	93.25 103	88.76 244	98.99 36

PVSNet	82.34 9	89.02 196	87.79 210	92.71 126	95.49 146	81.50 186	97.70 104	97.29 20	87.76 113	85.47 233	95.12 211	56.90 398	98.90 138	80.33 283	94.02 157	97.71 137

tpmvs		83.04 332	80.77 346	89.84 283	95.43 147	77.96 322	85.59 465	95.32 227	75.31 406	76.27 358	83.70 432	73.89 216	97.41 245	59.53 447	81.93 327	94.14 307

SteuartSystems-ACMMP		94.13 43	94.44 37	93.20 99	95.41 148	81.35 191	99.02 28	96.59 103	89.50 78	94.18 77	98.36 51	83.68 60	99.45 94	94.77 78	98.45 45	98.81 47
Skip Steuart: Steuart Systems R&D Blog.
EPMVS		87.47 248	85.90 253	92.18 167	95.41 148	82.26 153	87.00 455	96.28 146	85.88 182	84.23 252	85.57 409	75.07 199	96.26 321	71.14 387	92.50 184	98.03 100

MVSMamba_PlusPlus		92.37 95	91.55 107	94.83 29	95.37 150	87.69 26	95.60 295	95.42 220	74.65 412	93.95 80	92.81 286	83.11 64	97.70 203	94.49 83	98.53 39	99.11 29

BH-RMVSNet		86.84 256	85.28 266	91.49 216	95.35 151	80.26 238	96.95 176	92.21 411	82.86 283	81.77 295	95.46 190	59.34 369	97.64 209	69.79 395	93.81 165	96.57 236

OMC-MVS		88.80 205	88.16 203	90.72 251	95.30 152	77.92 325	94.81 333	94.51 278	86.80 153	84.97 239	96.85 140	67.53 300	98.60 148	85.08 233	87.62 272	95.63 266

test_fmvsm_n_1920		94.81 23	95.60 13	92.45 143	95.29 153	80.96 208	99.29 5	97.21 26	94.50 14	97.29 24	98.44 42	82.15 70	99.78 40	98.56 13	97.68 73	96.61 234

MVS_Test		90.29 162	89.18 173	93.62 79	95.23 154	84.93 86	94.41 340	94.66 267	84.31 235	90.37 142	91.02 317	75.13 197	97.82 198	83.11 259	94.42 153	98.12 95

F-COLMAP		84.50 308	83.44 305	87.67 338	95.22 155	72.22 406	95.95 262	93.78 351	75.74 401	76.30 357	95.18 206	59.50 367	98.45 162	72.67 375	86.59 282	92.35 331

baseline1		88.85 203	87.49 220	92.93 114	95.21 156	86.85 34	95.47 300	94.61 273	87.29 131	83.11 275	94.99 219	80.70 81	96.89 294	82.28 267	73.72 374	95.05 287

fmvsm_l_conf0.5_n_9		94.91 17	95.60 13	92.84 119	95.20 157	80.55 224	99.45 2	96.36 140	95.17 4	98.48 4	98.55 29	80.53 83	99.78 40	98.87 7	97.79 70	98.19 87

fmvsm_s_conf0.5_n_10		94.36 34	94.73 29	93.23 97	95.19 158	82.87 132	99.18 10	96.39 133	93.97 19	97.91 9	98.53 33	75.88 176	99.82 25	98.58 12	96.95 102	97.00 210

SymmetryMVS		92.45 91	92.33 88	92.82 120	95.19 158	82.02 158	97.94 85	97.43 17	92.34 34	92.15 108	96.53 152	77.03 145	98.57 150	91.13 138	91.19 208	97.87 119

CHOSEN 1792x2688		91.07 132	90.21 143	93.64 77	95.18 160	83.53 117	96.26 238	96.13 160	88.92 83	84.90 240	93.10 282	72.86 230	99.62 77	88.86 185	95.67 137	97.79 129

UGNet		87.73 238	86.55 245	91.27 227	95.16 161	79.11 277	96.35 230	96.23 152	88.14 102	87.83 192	90.48 326	50.65 430	99.09 125	80.13 288	94.03 156	95.60 268
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
fmvsm_s_conf0.5_n_8		94.52 30	95.04 24	92.96 111	95.15 162	81.14 195	99.09 21	96.66 92	95.53 3	97.84 11	98.71 23	76.33 163	99.81 29	99.24 1	96.85 109	97.92 115

VDD-MVS		88.28 221	87.02 233	92.06 176	95.09 163	80.18 243	97.55 118	94.45 286	83.09 274	89.10 163	95.92 164	47.97 443	98.49 157	93.08 110	86.91 279	97.52 160

PVSNet_Blended_VisFu		91.24 126	90.77 125	92.66 128	95.09 163	82.40 147	97.77 98	95.87 189	88.26 98	86.39 221	93.94 264	76.77 153	99.27 104	88.80 191	94.00 159	96.31 245

h-mvs33		89.30 189	88.95 182	90.36 264	95.07 165	76.04 366	96.96 175	97.11 36	90.39 65	92.22 106	95.10 212	74.70 204	98.86 139	93.14 106	65.89 440	96.16 247

xiu_mvs_v2_base		93.92 47	93.26 64	95.91 12	95.07 165	92.02 6	98.19 68	95.68 199	92.06 41	96.01 46	98.14 64	70.83 270	98.96 132	96.74 56	96.57 116	96.76 229

cl22		85.11 293	84.17 287	87.92 332	95.06 167	78.82 285	95.51 298	94.22 311	79.74 350	76.77 347	87.92 368	75.96 172	95.68 353	79.93 291	72.42 383	89.27 370

BH-w/o		88.24 222	87.47 222	90.54 257	95.03 168	78.54 299	97.41 132	93.82 345	84.08 244	78.23 330	94.51 239	69.34 284	97.21 266	80.21 287	94.58 150	95.87 256

CHOSEN 280x420		91.71 113	91.85 100	91.29 226	94.94 169	82.69 136	87.89 448	96.17 158	85.94 180	87.27 201	94.31 247	90.27 9	95.65 356	94.04 89	95.86 134	95.53 272

GG-mvs-BLEND				93.49 87	94.94 169	86.26 41	81.62 480	97.00 44		88.32 179	94.30 248	91.23 6	96.21 325	88.49 199	97.43 81	98.00 108

HyFIR lowres test		89.36 187	88.60 188	91.63 209	94.91 171	80.76 216	95.60 295	95.53 207	82.56 290	84.03 256	91.24 314	78.03 124	96.81 301	87.07 218	88.41 262	97.32 182

miper_enhance_ethall		85.95 273	85.20 267	88.19 326	94.85 172	79.76 254	96.00 259	94.06 326	82.98 280	77.74 335	88.76 350	79.42 97	95.46 366	80.58 281	72.42 383	89.36 368

mvsmamba		90.53 151	90.08 147	91.88 189	94.81 173	80.93 209	93.94 359	94.45 286	88.24 100	87.02 208	92.35 293	68.04 292	95.80 344	94.86 77	97.03 99	98.92 41

mvs_anonymous		88.68 207	87.62 215	91.86 190	94.80 174	81.69 180	93.53 371	94.92 245	82.03 300	78.87 324	90.43 328	75.77 177	95.34 370	85.04 234	93.16 176	98.55 64

CANet_DTU		90.98 134	90.04 150	93.83 62	94.76 175	86.23 44	96.32 233	93.12 395	93.11 26	93.71 82	96.82 143	63.08 339	99.48 92	84.29 239	95.12 143	95.77 262

fmvsm_l_mol_unc0.5_1		96.23 2	96.47 3	95.50 17	94.71 176	88.70 16	99.47 1	95.70 197	95.05 7	98.42 5	98.85 10	89.10 15	99.77 44	98.76 10	98.14 57	98.02 101

PMMVS		89.46 182	89.92 157	88.06 329	94.64 177	69.57 439	96.22 243	94.95 243	87.27 134	91.37 122	96.54 151	65.88 316	97.39 249	88.54 197	93.89 163	97.23 188

TR-MVS		86.30 267	84.93 275	90.42 260	94.63 178	77.58 338	96.57 209	93.82 345	80.30 336	82.42 282	95.16 207	58.74 373	97.55 221	74.88 355	87.82 270	96.13 249

EPNet_dtu		87.65 243	87.89 207	86.93 359	94.57 179	71.37 424	96.72 198	96.50 118	88.56 90	87.12 206	95.02 216	75.91 175	94.01 423	66.62 410	90.00 224	95.42 275
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_s_conf0.5_n		93.69 50	94.13 46	92.34 152	94.56 180	82.01 160	99.07 23	97.13 33	92.09 39	96.25 40	98.53 33	76.47 158	99.80 33	98.39 15	94.71 148	95.22 282

FMVSNet3		84.71 300	82.71 319	90.70 252	94.55 181	87.71 25	95.92 265	94.67 266	81.73 305	75.82 366	88.08 366	66.99 307	94.47 414	71.23 384	75.38 365	89.91 356

ETV-MVS		92.72 77	92.87 73	92.28 158	94.54 182	81.89 169	97.98 82	95.21 234	89.77 74	93.11 91	96.83 141	77.23 142	97.50 230	95.74 64	95.38 141	97.44 171

fmvsm_l_conf0.5_n_3		94.61 26	94.92 27	93.68 75	94.52 183	82.80 134	99.33 3	96.37 138	95.08 6	97.59 21	98.48 39	77.40 136	99.79 37	98.28 17	97.21 90	98.44 69

EIA-MVS		91.73 110	92.05 98	90.78 250	94.52 183	76.40 361	98.06 78	95.34 226	89.19 81	88.90 167	97.28 121	77.56 133	97.73 202	90.77 148	96.86 107	98.20 86

BH-untuned		86.95 254	85.94 251	89.99 276	94.52 183	77.46 340	96.78 193	93.37 384	81.80 303	76.62 350	93.81 270	66.64 311	97.02 280	76.06 340	93.88 164	95.48 274

DeepC-MVS	86.58 3	91.53 118	91.06 119	92.94 113	94.52 183	81.89 169	95.95 262	95.98 174	90.76 58	83.76 263	96.76 145	73.24 226	99.71 63	91.67 132	96.96 101	97.22 189
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
gg-mvs-nofinetune		85.48 285	82.90 315	93.24 96	94.51 187	85.82 53	79.22 487	96.97 49	61.19 480	87.33 198	53.01 517	90.58 7	96.07 329	86.07 226	97.23 89	97.81 128

fmvsm_l_conf0.5_n_a		94.91 17	95.30 19	93.72 71	94.50 188	84.30 99	99.14 15	96.00 171	91.94 44	97.91 9	98.60 27	84.78 43	99.77 44	98.84 8	96.03 130	97.08 207

3Dnovator+	82.88 8	89.63 179	87.85 208	94.99 25	94.49 189	86.76 37	97.84 92	95.74 195	86.10 171	75.47 371	96.02 161	65.00 324	99.51 90	82.91 261	97.07 98	98.72 55

RRT-MVS		89.67 177	88.67 186	92.67 127	94.44 190	81.08 198	94.34 345	94.45 286	86.05 173	85.79 228	92.39 292	63.39 337	98.16 177	93.22 104	93.95 162	98.76 49

nomal-1		89.71 176	89.18 173	91.30 225	94.43 191	81.03 200	94.35 344	96.27 147	85.05 210	83.05 276	90.78 322	80.87 78	97.21 266	89.53 177	88.34 263	95.66 265

fmvsm_l_conf0.5_n		94.89 19	95.24 20	93.86 61	94.42 192	84.61 92	99.13 16	96.15 159	92.06 41	97.92 7	98.52 35	84.52 46	99.74 55	98.76 10	95.67 137	97.22 189

fmvsm_s_conf0.5_n_3		93.95 46	94.53 33	92.20 166	94.41 193	80.04 248	98.90 34	95.96 176	94.53 13	97.63 20	98.58 28	75.95 173	99.79 37	98.25 19	96.60 115	96.77 227

ET-MVSNet_ETH3D		90.01 166	89.03 176	92.95 112	94.38 194	86.77 36	98.14 69	96.31 145	89.30 80	63.33 456	96.72 148	90.09 11	93.63 431	90.70 151	82.29 324	98.46 67

tpmrst		88.36 218	87.38 224	91.31 223	94.36 195	79.92 250	87.32 452	95.26 232	85.32 197	88.34 178	86.13 402	80.60 82	96.70 306	83.78 245	85.34 299	97.30 185

FE-MVS		86.06 271	84.15 288	91.78 198	94.33 196	79.81 252	84.58 472	96.61 99	76.69 396	85.00 238	87.38 376	70.71 272	98.37 167	70.39 392	91.70 200	97.17 198

MVS		90.60 146	88.64 187	96.50 6	94.25 197	90.53 9	93.33 376	97.21 26	77.59 381	78.88 323	97.31 116	71.52 260	99.69 67	89.60 173	98.03 61	99.27 23

dp		84.30 311	82.31 324	90.28 267	94.24 198	77.97 321	86.57 458	95.53 207	79.94 347	80.75 303	85.16 417	71.49 261	96.39 316	63.73 427	83.36 310	96.48 238

FA-MVS(test-final)		87.71 241	86.23 249	92.17 168	94.19 199	80.55 224	87.16 454	96.07 166	82.12 298	85.98 227	88.35 361	72.04 252	98.49 157	80.26 285	89.87 226	97.48 164

UWE-MVS		88.56 213	88.91 184	87.50 346	94.17 200	72.19 409	95.82 283	97.05 41	84.96 214	84.78 242	93.51 276	81.33 74	94.75 405	79.43 295	89.17 237	95.57 270

sss		90.87 139	89.96 155	93.60 80	94.15 201	83.84 107	97.14 155	98.13 7	85.93 181	89.68 149	96.09 160	71.67 256	99.30 103	87.69 210	89.16 238	97.66 141

SDMVSNet		87.02 252	85.61 258	91.24 229	94.14 202	83.30 122	93.88 361	95.98 174	84.30 237	79.63 317	92.01 299	58.23 377	97.68 205	90.28 164	82.02 325	92.75 325

sd_testset		84.62 304	83.11 310	89.17 296	94.14 202	77.78 331	91.54 412	94.38 295	84.30 237	79.63 317	92.01 299	52.28 423	96.98 286	77.67 319	82.02 325	92.75 325

PatchmatchNet		86.83 257	85.12 271	91.95 185	94.12 204	82.27 152	86.55 459	95.64 202	84.59 224	82.98 278	84.99 421	77.26 138	95.96 336	68.61 400	91.34 207	97.64 143
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
fmvsm_s_conf0.5_n_2		92.97 65	93.38 63	91.73 202	94.10 205	80.64 219	98.96 31	95.89 185	94.09 17	97.05 27	98.40 46	68.92 289	99.80 33	98.53 14	94.50 152	94.74 295

MDTV_nov1_ep13			83.69 293		94.09 206	81.01 201	86.78 457	96.09 163	83.81 257	84.75 243	84.32 426	74.44 210	96.54 311	63.88 426	85.07 300

UA-Net		88.92 200	88.48 196	90.24 268	94.06 207	77.18 347	93.04 384	94.66 267	87.39 129	91.09 127	93.89 265	74.92 200	98.18 176	75.83 343	91.43 204	95.35 277

Fast-Effi-MVS+		87.93 232	86.94 236	90.92 243	94.04 208	79.16 275	98.26 65	93.72 361	81.29 309	83.94 260	92.90 285	69.83 278	96.68 307	76.70 331	91.74 199	96.93 216

QAPM		86.88 255	84.51 278	93.98 57	94.04 208	85.89 51	97.19 147	96.05 167	73.62 419	75.12 374	95.62 180	62.02 351	99.74 55	70.88 388	96.06 129	96.30 246

thisisatest0515		90.95 136	90.26 140	93.01 108	94.03 210	84.27 101	97.91 88	96.67 89	83.18 272	86.87 214	95.51 186	88.66 18	97.85 197	80.46 282	89.01 241	96.92 218

fmvsm_s_conf0.5_n_4		93.59 52	94.32 40	91.41 220	93.89 211	79.24 271	98.89 35	96.53 114	92.82 28	97.37 23	98.47 40	77.21 144	99.78 40	98.11 26	95.59 139	95.21 283

Vis-MVSNet (Re-imp)		88.88 202	88.87 185	88.91 302	93.89 211	74.43 387	96.93 178	94.19 317	84.39 233	83.22 273	95.67 174	78.24 120	94.70 407	78.88 305	94.40 154	97.61 148

ADS-MVSNet2		79.57 378	77.53 381	85.71 380	93.78 213	72.13 410	79.48 485	86.11 477	73.09 425	80.14 311	79.99 464	62.15 347	90.14 469	59.49 448	83.52 307	94.85 292

ADS-MVSNet		81.26 360	78.36 374	89.96 279	93.78 213	79.78 253	79.48 485	93.60 370	73.09 425	80.14 311	79.99 464	62.15 347	95.24 378	59.49 448	83.52 307	94.85 292

EPP-MVSNet		89.76 174	89.72 162	89.87 282	93.78 213	76.02 369	97.22 143	96.51 116	79.35 356	85.11 236	95.01 217	84.82 42	97.10 278	87.46 213	88.21 266	96.50 237

3Dnovator	82.32 10	89.33 188	87.64 213	94.42 40	93.73 216	85.70 56	97.73 102	96.75 78	86.73 157	76.21 360	95.93 162	62.17 344	99.68 69	81.67 271	97.81 68	97.88 117

E3new		90.90 138	90.35 139	92.55 138	93.63 217	82.40 147	96.79 191	94.49 279	87.07 144	88.54 174	95.70 171	73.85 217	97.60 211	91.23 136	91.86 198	97.64 143

Effi-MVS+		90.70 143	89.90 158	93.09 105	93.61 218	83.48 118	95.20 314	92.79 400	83.22 271	91.82 115	95.70 171	71.82 255	97.48 233	91.25 135	93.67 168	98.32 76

IS-MVSNet		88.67 208	88.16 203	90.20 270	93.61 218	76.86 352	96.77 196	93.07 396	84.02 246	83.62 266	95.60 181	74.69 207	96.24 324	78.43 309	93.66 169	97.49 163

AUN-MVS		86.25 269	85.57 259	88.26 319	93.57 220	73.38 394	95.45 301	95.88 187	83.94 250	85.47 233	94.21 252	73.70 222	96.67 308	83.54 253	64.41 444	94.73 299

test2506		90.96 135	90.39 135	92.65 129	93.54 221	82.46 145	96.37 226	97.35 19	86.78 154	87.55 194	95.25 197	77.83 129	97.50 230	84.07 241	94.80 146	97.98 110

ECVR-MVS		88.35 219	87.25 226	91.65 206	93.54 221	79.40 267	96.56 211	90.78 440	86.78 154	85.57 231	95.25 197	57.25 396	97.56 217	84.73 237	94.80 146	97.98 110

hse-mvs2		88.22 223	88.21 201	88.25 321	93.54 221	73.41 393	95.41 303	95.89 185	90.39 65	92.22 106	94.22 251	74.70 204	96.66 309	93.14 106	64.37 445	94.69 300

LCM-MVSNet-Re		83.75 319	83.54 302	84.39 406	93.54 221	64.14 466	92.51 392	84.03 488	83.90 252	66.14 444	86.59 390	67.36 303	92.68 438	84.89 236	92.87 179	96.35 241

EC-MVSNet		91.73 110	92.11 96	90.58 254	93.54 221	77.77 332	98.07 77	94.40 292	87.44 127	92.99 94	97.11 129	74.59 208	96.87 297	93.75 93	97.08 97	97.11 200

tpm cat1		83.63 321	81.38 338	90.39 261	93.53 226	78.19 317	85.56 466	95.09 237	70.78 445	78.51 326	83.28 437	74.80 203	97.03 279	66.77 408	84.05 305	95.95 252

fmvsm_s_conf0.5_n_6		94.17 40	94.70 30	92.58 137	93.50 227	81.20 193	99.08 22	96.48 122	92.24 37	98.62 3	98.39 47	78.58 115	99.72 60	98.08 27	97.36 85	96.81 224

thisisatest0530		89.65 178	89.02 177	91.53 212	93.46 228	80.78 215	96.52 213	96.67 89	81.69 306	83.79 262	94.90 224	88.85 17	97.68 205	77.80 314	87.49 276	96.14 248

MSDG		80.62 370	77.77 380	89.14 297	93.43 229	77.24 344	91.89 404	90.18 445	69.86 451	68.02 432	91.94 306	52.21 424	98.84 140	59.32 450	83.12 311	91.35 333

fmvsm_s_conf0.5_n_a		93.34 58	93.71 51	92.22 163	93.38 230	81.71 179	98.86 36	96.98 46	91.64 45	96.85 30	98.55 29	75.58 183	99.77 44	97.88 33	93.68 167	95.18 284

ab-mvs		87.08 251	84.94 274	93.48 88	93.34 231	83.67 114	88.82 437	95.70 197	81.18 311	84.55 248	90.14 334	62.72 340	98.94 136	85.49 231	82.54 321	97.85 122

viewdifsd2359ckpt09		90.00 167	89.28 172	92.15 170	93.31 232	81.38 189	96.37 226	93.64 366	86.34 165	86.62 217	95.64 176	71.58 259	97.52 227	88.93 183	91.06 212	97.54 154

VortexMVS		85.45 286	84.40 282	88.63 308	93.25 233	81.66 181	95.39 305	94.34 297	87.15 142	75.10 375	87.65 372	66.58 313	95.19 380	86.89 220	73.21 380	89.03 384

viewcassd2359sk11		90.66 144	90.06 149	92.47 141	93.22 234	82.21 155	96.70 202	94.47 283	86.94 147	88.22 183	95.50 187	73.15 227	97.59 213	90.86 144	91.48 202	97.60 149

1314		88.94 199	87.20 227	94.17 53	93.21 235	85.73 55	93.33 376	96.64 96	82.89 281	75.98 363	96.36 154	66.83 310	99.39 96	83.52 255	96.02 131	97.39 176

1112_ss		88.60 211	87.47 222	92.00 183	93.21 235	80.97 203	96.47 217	92.46 403	83.64 265	80.86 302	97.30 119	80.24 87	97.62 210	77.60 320	85.49 296	97.40 175

GeoE		86.36 265	85.20 267	89.83 284	93.17 237	76.13 364	97.53 119	92.11 412	79.58 353	80.99 299	94.01 259	66.60 312	96.17 328	73.48 369	89.30 235	97.20 195

test1111		88.11 225	87.04 232	91.35 222	93.15 238	78.79 293	96.57 209	90.78 440	86.88 149	85.04 237	95.20 204	57.23 397	97.39 249	83.88 243	94.59 149	97.87 119

Test_1112_low_res		88.03 228	86.73 240	91.94 187	93.15 238	80.88 212	96.44 220	92.41 407	83.59 267	80.74 304	91.16 315	80.18 88	97.59 213	77.48 323	85.40 297	97.36 178

CostFormer		89.08 194	88.39 197	91.15 234	93.13 240	79.15 276	88.61 440	96.11 162	83.14 273	89.58 152	86.93 385	83.83 59	96.87 297	88.22 203	85.92 291	97.42 172

IB-MVS	85.34 4	88.67 208	87.14 230	93.26 95	93.12 241	84.32 98	98.76 38	97.27 22	87.19 139	79.36 320	90.45 327	83.92 58	98.53 155	84.41 238	69.79 403	96.93 216
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
diffmvs		91.17 128	90.74 126	92.44 145	93.11 242	82.50 144	96.25 239	93.62 368	87.79 112	90.40 140	95.93 162	73.44 224	97.42 243	93.62 96	92.55 183	97.41 173
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt13		90.08 164	89.36 169	92.26 159	93.03 243	81.90 168	96.37 226	94.34 297	86.16 168	87.44 195	95.30 195	70.93 269	97.55 221	89.05 182	91.59 201	97.35 180

tttt0517		88.57 212	88.19 202	89.71 288	93.00 244	75.99 370	95.67 290	96.67 89	80.78 320	81.82 293	94.40 246	88.97 16	97.58 215	76.05 341	86.31 284	95.57 270

MVSFormer		91.36 123	90.57 129	93.73 69	93.00 244	88.08 21	94.80 334	94.48 280	80.74 321	94.90 65	97.13 127	78.84 109	95.10 389	83.77 246	97.46 78	98.02 101

lupinMVS		93.87 48	93.58 56	94.75 32	93.00 244	88.08 21	99.15 13	95.50 211	91.03 55	94.90 65	97.66 95	78.84 109	97.56 217	94.64 82	97.46 78	98.62 60

casdiffmvs_mvg		91.13 129	90.45 133	93.17 101	92.99 247	83.58 116	97.46 126	94.56 276	87.69 116	87.19 204	94.98 220	74.50 209	97.60 211	91.88 131	92.79 180	98.34 73
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewmanbaseed2359cas		90.74 142	90.07 148	92.76 122	92.98 248	82.93 131	96.53 212	94.28 303	87.08 143	88.96 165	95.64 176	72.03 253	97.58 215	90.85 145	92.26 192	97.76 131

test_fmvs1		87.79 236	88.52 195	85.62 383	92.98 248	64.31 464	97.88 90	92.42 406	87.95 107	92.24 105	95.82 165	47.94 444	98.44 164	95.31 73	94.09 155	94.09 309

mamba_0408		85.26 291	83.10 311	91.74 201	92.94 250	82.53 139	72.52 502	91.77 418	80.36 333	83.50 267	94.01 259	64.97 325	96.90 292	79.37 296	88.51 257	95.79 259

SSM_04072		84.64 302	83.10 311	89.25 295	92.94 250	82.53 139	72.52 502	91.77 418	80.36 333	83.50 267	94.01 259	64.97 325	89.41 471	79.37 296	88.51 257	95.79 259

SSM_0407		87.33 250	85.87 254	91.71 205	92.94 250	82.53 139	94.30 348	92.33 409	80.11 341	83.50 267	94.18 254	64.68 329	96.80 303	82.34 265	88.51 257	95.79 259

SSM_0404		87.69 242	86.26 247	91.95 185	92.94 250	83.02 129	94.69 336	92.33 409	80.11 341	84.65 246	94.18 254	64.68 329	96.90 292	82.34 265	90.44 219	95.94 253

tpm2		87.35 249	86.26 247	90.62 253	92.93 254	78.67 296	88.06 447	95.99 173	79.33 357	87.40 196	86.43 396	80.28 86	96.40 315	80.23 286	85.73 295	96.79 225

baseline		90.76 141	90.10 146	92.74 124	92.90 255	82.56 138	94.60 337	94.56 276	87.69 116	89.06 164	95.67 174	73.76 219	97.51 229	90.43 157	92.23 194	98.16 90

fmvsm_s_conf0.5_n_5		93.57 54	93.75 49	93.01 108	92.87 256	82.73 135	98.93 33	95.90 184	90.96 57	95.61 50	98.39 47	76.57 156	99.63 75	98.32 16	96.24 122	96.68 233

GDP-MVS		92.85 72	92.55 82	93.75 66	92.82 257	85.76 54	97.63 108	95.05 240	88.34 96	93.15 90	97.10 130	86.92 29	98.01 185	87.95 205	94.00 159	97.47 165

test_fmvsmconf_n		93.99 45	94.36 39	92.86 116	92.82 257	81.12 196	99.26 7	96.37 138	93.47 23	95.16 58	98.21 57	79.00 106	99.64 73	98.21 21	96.73 113	97.83 124

casdiffmvs		90.95 136	90.39 135	92.63 132	92.82 257	82.53 139	96.83 185	94.47 283	87.69 116	88.47 175	95.56 183	74.04 215	97.54 224	90.90 143	92.74 181	97.83 124
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
fmvsm_s_conf0.5_n_7		92.88 69	93.82 48	90.08 272	92.79 260	76.45 359	98.54 49	96.74 79	92.28 36	95.22 57	98.49 37	74.91 201	98.15 178	98.28 17	97.13 94	95.63 266

Casviewmamba		90.52 153	90.00 153	92.06 176	92.72 261	80.42 233	96.87 182	94.28 303	87.45 125	87.30 199	95.73 169	73.10 228	97.67 207	90.27 165	92.29 191	98.10 97

onestephybrid01		90.58 147	90.37 137	91.20 233	92.69 262	78.81 287	96.04 257	93.94 331	86.55 162	90.40 140	95.64 176	72.84 231	97.43 242	93.77 92	91.46 203	97.36 178

Vis-MVSNet		88.67 208	87.82 209	91.24 229	92.68 263	78.82 285	96.95 176	93.85 340	87.55 122	87.07 207	95.13 210	63.43 336	97.21 266	77.58 321	96.15 125	97.70 138
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
E2		90.33 159	89.65 164	92.37 150	92.66 264	81.99 161	96.58 207	94.39 293	86.71 158	87.88 189	95.25 197	72.18 245	97.56 217	90.37 160	90.88 215	97.57 151

GBi-Net		82.42 342	80.43 353	88.39 314	92.66 264	81.95 163	94.30 348	93.38 381	79.06 365	75.82 366	85.66 405	56.38 404	93.84 426	71.23 384	75.38 365	89.38 364

test1		82.42 342	80.43 353	88.39 314	92.66 264	81.95 163	94.30 348	93.38 381	79.06 365	75.82 366	85.66 405	56.38 404	93.84 426	71.23 384	75.38 365	89.38 364

FMVSNet2		82.79 336	80.44 352	89.83 284	92.66 264	85.43 66	95.42 302	94.35 296	79.06 365	74.46 379	87.28 377	56.38 404	94.31 418	69.72 396	74.68 371	89.76 357

E3		90.33 159	89.65 164	92.37 150	92.64 268	81.99 161	96.58 207	94.39 293	86.71 158	87.87 190	95.27 196	72.17 246	97.56 217	90.37 160	90.88 215	97.57 151

BP-MVS1		93.55 55	93.50 59	93.71 72	92.64 268	85.39 67	97.78 97	96.84 62	89.52 77	92.00 111	97.06 133	88.21 23	98.03 182	91.45 133	96.00 132	97.70 138

miper_ehance_all_eth		84.57 306	83.60 301	87.50 346	92.64 268	78.25 311	95.40 304	93.47 376	79.28 360	76.41 354	87.64 373	76.53 157	95.24 378	78.58 307	72.42 383	89.01 388

cascas		86.50 261	84.48 280	92.55 138	92.64 268	85.95 48	97.04 166	95.07 239	75.32 405	80.50 305	91.02 317	54.33 418	97.98 187	86.79 223	87.62 272	93.71 316

TESTMET0.1,1		89.83 173	89.34 170	91.31 223	92.54 272	80.19 242	97.11 158	96.57 106	86.15 169	86.85 215	91.83 308	79.32 98	96.95 288	81.30 276	92.35 190	96.77 227

guyue		89.85 171	89.33 171	91.40 221	92.53 273	80.15 244	96.82 188	95.68 199	89.66 75	86.43 220	94.23 250	67.00 306	97.16 270	91.96 129	89.65 228	96.89 219

hybridcas		90.40 155	89.67 163	92.60 135	92.39 274	82.32 151	96.83 185	94.25 307	87.19 139	86.59 218	95.43 191	72.54 236	97.65 208	88.77 193	93.02 178	97.82 126

COLMAP_ROB	73.24 19	75.74 414	73.00 421	83.94 408	92.38 275	69.08 441	91.85 406	86.93 470	61.48 478	65.32 448	90.27 330	42.27 463	96.93 291	50.91 479	75.63 364	85.80 450
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
hybridnocas07		90.53 151	90.02 151	92.05 180	92.36 276	81.48 187	96.27 236	93.57 373	86.86 151	89.28 158	95.48 188	72.17 246	97.47 234	92.77 112	91.41 205	97.21 192

test_vis1_n_1920		89.95 168	90.59 128	88.03 331	92.36 276	68.98 442	99.12 17	94.34 297	93.86 20	93.64 84	97.01 135	51.54 425	99.59 79	96.76 55	96.71 114	95.53 272

viewdifsd2359ckpt07		89.04 195	88.30 199	91.27 227	92.32 278	78.90 282	95.89 275	93.77 354	84.48 231	85.18 235	95.16 207	69.83 278	97.70 203	88.75 194	89.29 236	97.22 189

xiu_mvs_v1_base_debu		90.54 148	89.54 166	93.55 83	92.31 279	87.58 28	96.99 168	94.87 248	87.23 135	93.27 86	97.56 104	57.43 392	98.32 169	92.72 113	93.46 172	94.74 295

xiu_mvs_v1_base		90.54 148	89.54 166	93.55 83	92.31 279	87.58 28	96.99 168	94.87 248	87.23 135	93.27 86	97.56 104	57.43 392	98.32 169	92.72 113	93.46 172	94.74 295

xiu_mvs_v1_base_debi		90.54 148	89.54 166	93.55 83	92.31 279	87.58 28	96.99 168	94.87 248	87.23 135	93.27 86	97.56 104	57.43 392	98.32 169	92.72 113	93.46 172	94.74 295

icg_test_0407_2		87.55 245	86.59 244	90.43 259	92.30 282	78.81 287	92.17 399	93.84 341	85.14 204	83.68 264	94.49 241	67.75 295	95.02 397	81.33 272	88.61 246	97.46 166

IMVS_0407		87.82 234	86.72 241	91.14 235	92.30 282	78.81 287	93.34 375	93.84 341	85.14 204	83.68 264	94.49 241	67.75 295	97.14 276	81.33 272	88.61 246	97.46 166

IMVS_0404		85.34 288	83.69 293	90.29 266	92.30 282	78.81 287	90.62 421	93.84 341	85.14 204	72.51 400	94.49 241	54.36 417	94.61 410	81.33 272	88.61 246	97.46 166

IMVS_0403		88.07 226	87.02 233	91.24 229	92.30 282	78.81 287	93.62 367	93.84 341	85.14 204	84.36 249	94.49 241	69.49 282	97.46 241	81.33 272	88.61 246	97.46 166

SCA		85.63 279	83.64 299	91.60 210	92.30 282	81.86 171	92.88 388	95.56 206	84.85 215	82.52 279	85.12 419	58.04 380	95.39 367	73.89 365	87.58 274	97.54 154

fmvsm_s_conf0.1_n_2		92.26 98	92.48 84	91.60 210	92.29 287	80.55 224	98.73 39	94.33 300	93.80 21	96.18 42	98.11 66	66.93 308	99.75 52	98.19 22	93.74 166	94.50 302

gm-plane-assit					92.27 288	79.64 262			84.47 232		95.15 209		97.93 188	85.81 228

test-LLR		88.48 214	87.98 205	89.98 277	92.26 289	77.23 345	97.11 158	95.96 176	83.76 259	86.30 223	91.38 311	72.30 243	96.78 304	80.82 279	91.92 196	95.94 253

test-mter		88.95 198	88.60 188	89.98 277	92.26 289	77.23 345	97.11 158	95.96 176	85.32 197	86.30 223	91.38 311	76.37 162	96.78 304	80.82 279	91.92 196	95.94 253

PAPM		92.87 71	92.40 85	94.30 43	92.25 291	87.85 23	96.40 225	96.38 135	91.07 54	88.72 172	96.90 137	82.11 71	97.37 255	90.05 166	97.70 72	97.67 140

viewmambaseed2359dif		89.52 180	89.02 177	91.03 238	92.24 292	78.83 284	95.89 275	93.77 354	83.04 276	88.28 182	95.80 167	72.08 251	97.40 247	89.76 170	90.32 220	96.87 222

hybrid		90.42 154	89.87 160	92.06 176	92.20 293	81.45 188	96.09 254	93.61 369	85.80 183	89.55 153	95.52 185	72.14 250	97.39 249	92.60 116	91.36 206	97.34 181

cl____		83.27 326	82.12 326	86.74 360	92.20 293	75.95 371	95.11 322	93.27 387	78.44 374	74.82 377	87.02 384	74.19 212	95.19 380	74.67 358	69.32 407	89.09 376

DIV-MVS_self_test		83.27 326	82.12 326	86.74 360	92.19 295	75.92 373	95.11 322	93.26 388	78.44 374	74.81 378	87.08 383	74.19 212	95.19 380	74.66 359	69.30 408	89.11 375

AllTest		75.92 412	73.06 420	84.47 402	92.18 296	67.29 448	91.07 416	84.43 483	67.63 457	63.48 453	90.18 331	38.20 476	97.16 270	57.04 459	73.37 376	88.97 391

TestCases				84.47 402	92.18 296	67.29 448		84.43 483	67.63 457	63.48 453	90.18 331	38.20 476	97.16 270	57.04 459	73.37 376	88.97 391

KinetiMVS		89.13 193	87.95 206	92.65 129	92.16 298	82.39 149	97.04 166	96.05 167	86.59 161	88.08 187	94.85 228	61.54 356	98.38 166	81.28 277	93.99 161	97.19 196

CLD-MVS		87.97 231	87.48 221	89.44 292	92.16 298	80.54 228	98.14 69	94.92 245	91.41 48	79.43 319	95.40 192	62.34 343	97.27 262	90.60 152	82.90 316	90.50 342
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
viewmamba		90.30 161	89.90 158	91.48 217	92.14 300	79.76 254	95.92 265	93.50 375	87.73 114	88.32 179	95.82 165	72.39 239	97.36 256	92.19 123	91.12 211	97.30 185

Syy-MVS		77.97 397	78.05 377	77.74 456	92.13 301	56.85 490	93.97 357	94.23 309	82.43 291	73.39 386	93.57 274	57.95 383	87.86 480	32.40 510	82.34 322	88.51 399

myMVS_eth3d		81.93 349	82.18 325	81.18 437	92.13 301	67.18 450	93.97 357	94.23 309	82.43 291	73.39 386	93.57 274	76.98 148	87.86 480	50.53 481	82.34 322	88.51 399

c3_l		83.80 318	82.65 320	87.25 354	92.10 303	77.74 336	95.25 311	93.04 397	78.58 371	76.01 362	87.21 381	75.25 196	95.11 388	77.54 322	68.89 411	88.91 394

HQP-NCC					92.08 304		97.63 108		90.52 62	82.30 283

ACMP_Plane					92.08 304		97.63 108		90.52 62	82.30 283

HQP-MVS		87.91 233	87.55 219	88.98 301	92.08 304	78.48 300	97.63 108	94.80 254	90.52 62	82.30 283	94.56 237	65.40 320	97.32 257	87.67 211	83.01 313	91.13 334

PCF-MVS	84.09 5	86.77 259	85.00 273	92.08 173	92.06 307	83.07 127	92.14 400	94.47 283	79.63 352	76.90 346	94.78 230	71.15 263	99.20 115	72.87 373	91.05 213	93.98 311
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffseed414692147		88.22 223	86.93 237	92.08 173	92.04 308	81.84 172	96.08 256	94.08 324	84.56 225	85.59 230	93.98 263	67.37 302	97.42 243	80.12 289	88.52 256	96.99 211

NP-MVS					92.04 308	78.22 312					94.56 237

diffmvs_AUTHOR		90.86 140	90.41 134	92.24 160	92.01 310	82.22 154	96.18 247	93.64 366	87.28 132	90.46 139	95.64 176	72.82 232	97.39 249	93.17 105	92.46 186	97.11 200

plane_prior6					91.98 311	77.92 325						64.77 327

Effi-MVS+-dtu		84.61 305	84.90 276	83.72 413	91.96 312	63.14 472	94.95 328	93.34 385	85.57 189	79.79 315	87.12 382	61.99 352	95.61 360	83.55 252	85.83 293	92.41 329

plane_prior1					91.95 313

CDS-MVSNet		89.50 181	88.96 181	91.14 235	91.94 314	80.93 209	97.09 162	95.81 191	84.26 240	84.72 244	94.20 253	80.31 85	95.64 357	83.37 256	88.96 242	96.85 223
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
E4		89.85 171	89.06 175	92.22 163	91.88 315	81.63 183	96.43 222	94.27 305	86.32 166	87.29 200	94.97 221	70.81 271	97.52 227	89.57 174	90.00 224	97.51 161

HQP_MVS		87.50 247	87.09 231	88.74 306	91.86 316	77.96 322	97.18 148	94.69 263	89.89 72	81.33 296	94.15 256	64.77 327	97.30 259	87.08 216	82.82 317	90.96 336

plane_prior7					91.86 316	77.55 339

eth_miper_zixun_eth		83.12 330	82.01 328	86.47 365	91.85 318	74.80 382	94.33 346	93.18 391	79.11 363	75.74 369	87.25 380	72.71 233	95.32 372	76.78 330	67.13 430	89.27 370

dtuplus		89.18 192	88.59 190	90.96 241	91.84 319	78.40 307	95.89 275	93.81 348	83.26 270	87.77 193	95.53 184	70.57 273	97.49 232	88.57 196	90.08 222	96.99 211

E5new		89.38 183	88.55 191	91.85 192	91.77 320	80.97 203	95.90 271	94.22 311	86.03 175	86.88 210	94.90 224	69.05 285	97.47 234	88.86 185	89.35 231	97.10 202

E5		89.38 183	88.55 191	91.85 192	91.77 320	80.97 203	95.90 271	94.22 311	86.03 175	86.88 210	94.90 224	69.05 285	97.47 234	88.86 185	89.35 231	97.10 202

E6new		89.37 185	88.55 191	91.85 192	91.75 322	80.97 203	95.90 271	94.22 311	86.03 175	86.88 210	94.91 222	69.05 285	97.47 234	88.86 185	89.34 233	97.10 202

E6		89.37 185	88.55 191	91.85 192	91.75 322	80.97 203	95.90 271	94.22 311	86.03 175	86.88 210	94.91 222	69.05 285	97.47 234	88.86 185	89.34 233	97.10 202

viewmacassd2359aftdt		89.89 170	89.01 179	92.52 140	91.56 324	82.46 145	96.32 233	94.06 326	86.41 163	88.11 186	95.01 217	69.68 281	97.47 234	88.73 195	91.19 208	97.63 145

VDDNet		86.44 262	84.51 278	92.22 163	91.56 324	81.83 173	97.10 161	94.64 270	69.50 452	87.84 191	95.19 205	48.01 442	97.92 193	89.82 168	86.92 278	96.89 219

EI-MVSNet		85.80 275	85.20 267	87.59 342	91.55 326	77.41 341	95.13 320	95.36 223	80.43 331	80.33 309	94.71 233	73.72 220	95.97 333	76.96 329	78.64 346	89.39 362

CVMVSNet		84.83 299	85.57 259	82.63 425	91.55 326	60.38 482	95.13 320	95.03 241	80.60 324	82.10 289	94.71 233	66.40 314	90.19 468	74.30 362	90.32 220	97.31 184

ACMP	81.66 11	84.00 315	83.22 309	86.33 366	91.53 328	72.95 404	95.91 270	93.79 350	83.70 262	73.79 382	92.22 295	54.31 419	96.89 294	83.98 242	79.74 335	89.16 374
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
IterMVS-LS		83.93 316	82.80 318	87.31 352	91.46 329	77.39 342	95.66 291	93.43 379	80.44 329	75.51 370	87.26 379	73.72 220	95.16 383	76.99 327	70.72 394	89.39 362
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dmvs_re		84.10 313	82.90 315	87.70 336	91.41 330	73.28 397	90.59 422	93.19 389	85.02 211	77.96 334	93.68 271	57.92 385	96.18 326	75.50 349	80.87 329	93.63 317

WB-MVSnew		84.08 314	83.51 303	85.80 376	91.34 331	76.69 356	95.62 294	96.27 147	81.77 304	81.81 294	92.81 286	58.23 377	94.70 407	66.66 409	87.06 277	85.99 446

Patchmatch-test		78.25 392	74.72 407	88.83 304	91.20 332	74.10 390	73.91 500	88.70 462	59.89 486	66.82 439	85.12 419	78.38 117	94.54 412	48.84 486	79.58 338	97.86 121

miper_lstm_enhance		81.66 355	80.66 349	84.67 398	91.19 333	71.97 414	91.94 403	93.19 389	77.86 378	72.27 401	85.26 413	73.46 223	93.42 434	73.71 368	67.05 431	88.61 397

ACMM	80.70 13	83.72 320	82.85 317	86.31 369	91.19 333	72.12 411	95.88 278	94.29 302	80.44 329	77.02 344	91.96 303	55.24 411	97.14 276	79.30 299	80.38 332	89.67 358
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
testing3		80.74 368	81.17 341	79.44 447	91.15 335	63.48 470	97.16 152	95.76 193	80.83 318	71.36 408	93.15 281	78.22 121	87.30 485	43.19 495	79.67 336	87.55 424

UWE-MVS-28		85.41 287	86.36 246	82.59 426	91.12 336	66.81 455	93.88 361	97.03 42	83.86 255	78.55 325	93.84 267	77.76 131	88.55 475	73.47 370	87.69 271	92.41 329

TAMVS		88.48 214	87.79 210	90.56 255	91.09 337	79.18 274	96.45 219	95.88 187	83.64 265	83.12 274	93.33 277	75.94 174	95.74 352	82.40 264	88.27 265	96.75 230

ACMH+	76.62 16	77.47 403	74.94 404	85.05 392	91.07 338	71.58 421	93.26 380	90.01 446	71.80 440	64.76 450	88.55 353	41.62 466	96.48 313	62.35 434	71.00 391	87.09 430

OpenMVS	79.58 14	86.09 270	83.62 300	93.50 86	90.95 339	86.71 38	97.44 127	95.83 190	75.35 404	72.64 397	95.72 170	57.42 395	99.64 73	71.41 382	95.85 135	94.13 308

LPG-MVS_test		84.20 312	83.49 304	86.33 366	90.88 340	73.06 400	95.28 306	94.13 320	82.20 295	76.31 355	93.20 278	54.83 415	96.95 288	83.72 248	80.83 330	88.98 389

LGP-MVS_train				86.33 366	90.88 340	73.06 400		94.13 320	82.20 295	76.31 355	93.20 278	54.83 415	96.95 288	83.72 248	80.83 330	88.98 389

test_fmvsmvis_n_1920		92.12 100	92.10 97	92.17 168	90.87 342	81.04 199	98.34 62	93.90 336	92.71 29	87.24 202	97.90 84	74.83 202	99.72 60	96.96 52	96.20 123	95.76 263

KD-MVS_2432*1600		77.63 400	74.92 405	85.77 377	90.86 343	79.44 265	88.08 445	93.92 334	76.26 398	67.05 437	82.78 439	72.15 248	91.92 449	61.53 435	41.62 503	85.94 447

miper_refine_blended		77.63 400	74.92 405	85.77 377	90.86 343	79.44 265	88.08 445	93.92 334	76.26 398	67.05 437	82.78 439	72.15 248	91.92 449	61.53 435	41.62 503	85.94 447

baseline2		90.39 156	90.21 143	90.93 242	90.86 343	80.99 202	95.20 314	97.41 18	86.03 175	80.07 314	94.61 236	90.58 7	97.47 234	87.29 215	89.86 227	94.35 303

AstraMVS		88.99 197	88.35 198	90.92 243	90.81 346	78.29 308	96.73 197	94.24 308	89.96 71	86.13 225	95.04 214	62.12 349	97.41 245	92.54 118	87.57 275	97.06 209

PVSNet_0	77.72 15	81.70 353	78.95 372	89.94 280	90.77 347	76.72 355	95.96 261	96.95 51	85.01 212	70.24 423	88.53 355	52.32 422	98.20 174	86.68 224	44.08 500	94.89 290

ACMH	75.40 17	77.99 395	74.96 403	87.10 357	90.67 348	76.41 360	93.19 383	91.64 423	72.47 434	63.44 455	87.61 374	43.34 458	97.16 270	58.34 453	73.94 373	87.72 416
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVS-HIRNet		71.36 440	67.00 446	84.46 404	90.58 349	69.74 436	79.15 488	87.74 466	46.09 502	61.96 465	50.50 518	45.14 453	95.64 357	53.74 471	88.11 267	88.00 413

fmvsm_s_conf0.1_n		92.93 67	93.16 67	92.24 160	90.52 350	81.92 166	98.42 55	96.24 151	91.17 51	96.02 45	98.35 52	75.34 194	99.74 55	97.84 35	94.58 150	95.05 287

jason		92.73 75	92.23 92	94.21 49	90.50 351	87.30 32	98.65 44	95.09 237	90.61 61	92.76 98	97.13 127	75.28 195	97.30 259	93.32 101	96.75 112	98.02 101
jason: jason.
LTVRE_ROB	73.68 18	77.99 395	75.74 397	84.74 395	90.45 352	72.02 412	86.41 460	91.12 432	72.57 432	66.63 441	87.27 378	54.95 414	96.98 286	56.29 463	75.98 360	85.21 453
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
viewdifsd2359ckpt11		86.38 263	85.29 264	89.66 290	90.42 353	75.65 376	95.27 309	92.45 404	85.54 192	84.27 251	94.73 231	62.16 345	97.39 249	87.78 207	74.97 368	95.96 250

viewmsd2359difaftdt		86.38 263	85.29 264	89.67 289	90.42 353	75.65 376	95.27 309	92.45 404	85.54 192	84.28 250	94.73 231	62.16 345	97.39 249	87.78 207	74.97 368	95.96 250

XVG-OURS		85.18 292	84.38 283	87.59 342	90.42 353	71.73 419	91.06 417	94.07 325	82.00 301	83.29 272	95.08 213	56.42 403	97.55 221	83.70 250	83.42 309	93.49 320

VPA-MVSNet		85.32 289	83.83 292	89.77 287	90.25 356	82.63 137	96.36 229	97.07 39	83.03 278	81.21 298	89.02 347	61.58 355	96.31 320	85.02 235	70.95 392	90.36 343

XVG-OURS-SEG-HR		85.74 277	85.16 270	87.49 348	90.22 357	71.45 422	91.29 413	94.09 323	81.37 308	83.90 261	95.22 202	60.30 362	97.53 226	85.58 230	84.42 304	93.50 319

SD_0403		81.29 359	81.13 343	81.78 434	90.20 358	60.43 481	89.97 426	91.31 431	83.87 253	71.78 404	93.08 283	63.86 333	89.61 470	60.00 446	86.07 290	95.30 279

tpm		85.55 283	84.47 281	88.80 305	90.19 359	75.39 379	88.79 438	94.69 263	84.83 216	83.96 259	85.21 415	78.22 121	94.68 409	76.32 339	78.02 354	96.34 242

CR-MVSNet		83.53 322	81.36 339	90.06 273	90.16 360	79.75 256	79.02 489	91.12 432	84.24 241	82.27 287	80.35 461	75.45 186	93.67 430	63.37 431	86.25 285	96.75 230

RPMNet		79.85 374	75.92 394	91.64 207	90.16 360	79.75 256	79.02 489	95.44 216	58.43 492	82.27 287	72.55 492	73.03 229	98.41 165	46.10 490	86.25 285	96.75 230

test_cas_vis1_n_1920		89.90 169	90.02 151	89.54 291	90.14 362	74.63 384	98.71 41	94.43 289	93.04 27	92.40 102	96.35 155	53.41 421	99.08 126	95.59 67	96.16 124	94.90 289

FIs		86.73 260	86.10 250	88.61 309	90.05 363	80.21 240	96.14 251	96.95 51	85.56 191	78.37 328	92.30 294	76.73 154	95.28 374	79.51 293	79.27 340	90.35 344

FMVSNet5		76.46 410	74.16 413	83.35 418	90.05 363	76.17 363	89.58 430	89.85 447	71.39 443	65.29 449	80.42 460	50.61 431	87.70 483	61.05 441	69.24 409	86.18 441

0.4-1-1-0.2		87.73 238	85.82 255	93.46 91	89.97 365	85.31 71	98.49 52	96.55 109	81.24 310	87.14 205	89.63 340	76.16 168	97.02 280	86.84 222	66.38 437	98.05 99

0.3-1-1-0.015		87.79 236	85.93 252	93.38 92	89.87 366	85.09 81	98.43 53	96.55 109	81.13 312	87.21 203	89.75 337	77.23 142	97.02 280	86.87 221	66.38 437	98.02 101

IterMVS		80.67 369	79.16 369	85.20 390	89.79 367	76.08 365	92.97 386	91.86 415	80.28 337	71.20 410	85.14 418	57.93 384	91.34 457	72.52 376	70.74 393	88.18 410
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SSC-MVS3.2		81.06 363	79.49 367	85.75 379	89.78 368	73.00 402	94.40 343	95.23 233	83.76 259	76.61 351	87.82 370	49.48 437	94.88 399	66.80 407	71.56 388	89.38 364

mvsany_test1		87.58 244	88.22 200	85.67 381	89.78 368	67.18 450	95.25 311	87.93 464	83.96 249	88.79 169	97.06 133	72.52 237	94.53 413	92.21 122	86.45 283	95.30 279

UniMVSNet (Re)		85.31 290	84.23 285	88.55 310	89.75 370	80.55 224	96.72 198	96.89 57	85.42 195	78.40 327	88.93 348	75.38 190	95.52 364	78.58 307	68.02 420	89.57 361

Patchmtry		77.36 404	74.59 408	85.67 381	89.75 370	75.75 375	77.85 492	91.12 432	60.28 483	71.23 409	80.35 461	75.45 186	93.56 432	57.94 454	67.34 428	87.68 418

JIA-IIPM		79.00 384	77.20 383	84.40 405	89.74 372	64.06 467	75.30 497	95.44 216	62.15 474	81.90 291	59.08 511	78.92 107	95.59 361	66.51 413	85.78 294	93.54 318

0.4-1-1-0.1		87.53 246	85.67 257	93.13 102	89.70 373	84.41 95	98.30 63	96.55 109	80.85 317	86.94 209	89.53 342	76.18 166	96.99 285	86.62 225	66.36 439	97.98 110

kuosan		73.55 424	72.39 424	77.01 460	89.68 374	66.72 456	85.24 469	93.44 377	67.76 456	60.04 474	83.40 435	71.90 254	84.25 494	45.34 492	54.75 467	80.06 489

MS-PatchMatch		83.05 331	81.82 332	86.72 364	89.64 375	79.10 278	94.88 330	94.59 275	79.70 351	70.67 415	89.65 339	50.43 432	96.82 300	70.82 391	95.99 133	84.25 462

IterMVS-SCA-FT		80.51 371	79.10 370	84.73 396	89.63 376	74.66 383	92.98 385	91.81 417	80.05 344	71.06 413	85.18 416	58.04 380	91.40 456	72.48 377	70.70 395	88.12 411

mmtdpeth		78.04 394	76.76 388	81.86 433	89.60 377	66.12 458	92.34 398	87.18 468	76.83 394	85.55 232	76.49 480	46.77 449	97.02 280	90.85 145	45.24 497	82.43 475

Fast-Effi-MVS+-dtu		83.33 325	82.60 321	85.50 385	89.55 378	69.38 440	96.09 254	91.38 426	82.30 294	75.96 364	91.41 310	56.71 399	95.58 362	75.13 354	84.90 301	91.54 332

PatchT		79.75 375	76.85 387	88.42 311	89.55 378	75.49 378	77.37 493	94.61 273	63.07 469	82.46 281	73.32 489	75.52 185	93.41 435	51.36 477	84.43 303	96.36 240

GA-MVS		85.79 276	84.04 291	91.02 240	89.47 380	80.27 237	96.90 181	94.84 252	85.57 189	80.88 300	89.08 345	56.56 402	96.47 314	77.72 317	85.35 298	96.34 242

UniMVSNet_NR-MVSNet		85.49 284	84.59 277	88.21 325	89.44 381	79.36 268	96.71 200	96.41 129	85.22 200	78.11 331	90.98 319	76.97 149	95.14 386	79.14 301	68.30 417	90.12 350

FC-MVSNet-test		85.96 272	85.39 262	87.66 339	89.38 382	78.02 319	95.65 292	96.87 59	85.12 208	77.34 337	91.94 306	76.28 165	94.74 406	77.09 326	78.82 344	90.21 347

WR-MVS		84.32 310	82.96 313	88.41 312	89.38 382	80.32 234	96.59 206	96.25 150	83.97 248	76.63 349	90.36 329	67.53 300	94.86 401	75.82 344	70.09 401	90.06 354

VPNet		84.69 301	82.92 314	90.01 275	89.01 384	83.45 119	96.71 200	95.46 214	85.71 186	79.65 316	92.18 298	56.66 401	96.01 332	83.05 260	67.84 423	90.56 341

Elysia		85.62 280	83.66 296	91.51 213	88.76 385	82.21 155	95.15 318	94.70 259	76.96 392	84.13 253	92.20 296	50.81 428	97.26 263	77.81 312	92.42 187	95.06 285

StellarMVS		85.62 280	83.66 296	91.51 213	88.76 385	82.21 155	95.15 318	94.70 259	76.96 392	84.13 253	92.20 296	50.81 428	97.26 263	77.81 312	92.42 187	95.06 285

nrg030		86.79 258	85.43 261	90.87 247	88.76 385	85.34 68	97.06 165	94.33 300	84.31 235	80.45 307	91.98 302	72.36 240	96.36 318	88.48 200	71.13 390	90.93 338

DU-MVS		84.57 306	83.33 306	88.28 318	88.76 385	79.36 268	96.43 222	95.41 222	85.42 195	78.11 331	90.82 320	67.61 297	95.14 386	79.14 301	68.30 417	90.33 345

NR-MVSNet		83.35 324	81.52 337	88.84 303	88.76 385	81.31 192	94.45 339	95.16 235	84.65 222	67.81 433	90.82 320	70.36 275	94.87 400	74.75 356	66.89 433	90.33 345

test_0402		72.68 430	69.54 438	82.09 431	88.67 390	71.81 418	92.72 390	86.77 473	61.52 477	62.21 463	83.91 430	43.22 459	93.76 429	34.60 506	72.23 386	80.72 488

RPSCF		77.73 399	76.63 389	81.06 438	88.66 391	55.76 495	87.77 449	87.88 465	64.82 466	74.14 381	92.79 288	49.22 438	96.81 301	67.47 404	76.88 356	90.62 340

LuminaMVS		88.02 229	86.89 238	91.43 219	88.65 392	83.16 125	94.84 331	94.41 291	83.67 263	86.56 219	91.95 305	62.04 350	96.88 296	89.78 169	90.06 223	94.24 304

FMVSNet1		79.50 379	76.54 390	88.39 314	88.47 393	81.95 163	94.30 348	93.38 381	73.14 424	72.04 403	85.66 405	43.86 455	93.84 426	65.48 417	72.53 382	89.38 364

test_fmvsmconf0.1_n		93.08 63	93.22 66	92.65 129	88.45 394	80.81 214	99.00 29	95.11 236	93.21 25	94.00 79	97.91 83	76.84 150	99.59 79	97.91 30	96.55 117	97.54 154

MonoMVSNet		85.68 278	84.22 286	90.03 274	88.43 395	77.83 329	92.95 387	91.46 425	87.28 132	78.11 331	85.96 404	66.31 315	94.81 403	90.71 150	76.81 357	97.46 166

OPM-MVS		85.84 274	85.10 272	88.06 329	88.34 396	77.83 329	95.72 286	94.20 316	87.89 111	80.45 307	94.05 258	58.57 374	97.26 263	83.88 243	82.76 319	89.09 376
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
tfpnnormal		78.14 393	75.42 401	86.31 369	88.33 397	79.24 271	94.41 340	96.22 153	73.51 420	69.81 426	85.52 411	55.43 409	95.75 349	47.65 488	67.86 422	83.95 465

TinyColmap		72.41 432	68.99 441	82.68 423	88.11 398	69.59 437	88.41 441	85.20 479	65.55 463	57.91 481	84.82 423	30.80 492	95.94 337	51.38 476	68.70 412	82.49 474

fmvsm_s_conf0.1_n_a		92.38 94	92.49 83	92.06 176	88.08 399	81.62 184	97.97 84	96.01 170	90.62 60	96.58 36	98.33 53	74.09 214	99.71 63	97.23 47	93.46 172	94.86 291

WR-MVS_H		81.02 364	80.09 356	83.79 410	88.08 399	71.26 425	94.46 338	96.54 112	80.08 343	72.81 396	86.82 386	70.36 275	92.65 439	64.18 424	67.50 426	87.46 426

CP-MVSNet		81.01 365	80.08 357	83.79 410	87.91 401	70.51 428	94.29 352	95.65 201	80.83 318	72.54 399	88.84 349	63.71 334	92.32 444	68.58 401	68.36 416	88.55 398

D2MVS		82.67 338	81.55 335	86.04 374	87.77 402	76.47 357	95.21 313	96.58 105	82.66 288	70.26 421	85.46 412	60.39 361	95.80 344	76.40 337	79.18 341	85.83 449

TranMVSNet+NR-MVSNet		83.24 328	81.71 333	87.83 333	87.71 403	78.81 287	96.13 253	94.82 253	84.52 228	76.18 361	90.78 322	64.07 332	94.60 411	74.60 360	66.59 436	90.09 352

USDC		78.65 390	76.25 391	85.85 375	87.58 404	74.60 385	89.58 430	90.58 443	84.05 245	63.13 457	88.23 363	40.69 474	96.86 299	66.57 412	75.81 363	86.09 443

PS-CasMVS		80.27 372	79.18 368	83.52 416	87.56 405	69.88 434	94.08 355	95.29 230	80.27 338	72.08 402	88.51 356	59.22 371	92.23 446	67.49 403	68.15 419	88.45 404

test_fmvs1_n		86.34 266	86.72 241	85.17 391	87.54 406	63.64 469	96.91 180	92.37 408	87.49 124	91.33 123	95.58 182	40.81 473	98.46 160	95.00 76	93.49 170	93.41 323

MIMVSNet		79.18 383	75.99 393	88.72 307	87.37 407	80.66 218	79.96 483	91.82 416	77.38 384	74.33 380	81.87 450	41.78 465	90.74 463	66.36 415	83.10 312	94.76 294

XXY-MVS		83.84 317	82.00 329	89.35 293	87.13 408	81.38 189	95.72 286	94.26 306	80.15 340	75.92 365	90.63 324	61.96 353	96.52 312	78.98 304	73.28 379	90.14 349

ITE_SJBPF				82.38 428	87.00 409	65.59 459		89.55 450	79.99 346	69.37 428	91.30 313	41.60 467	95.33 371	62.86 433	74.63 372	86.24 440

dongtai		69.47 446	68.98 442	70.93 472	86.87 410	58.45 487	88.19 443	93.18 391	63.98 467	56.04 486	80.17 463	70.97 268	79.24 501	33.46 508	47.94 493	75.09 496

test0.0.03 1		82.79 336	82.48 322	83.74 412	86.81 411	72.22 406	96.52 213	95.03 241	83.76 259	73.00 393	93.20 278	72.30 243	88.88 473	64.15 425	77.52 355	90.12 350

v8		81.88 350	80.06 359	87.32 351	86.63 412	79.04 281	94.41 340	93.65 365	78.77 369	73.19 392	85.57 409	66.87 309	95.81 343	73.84 367	67.61 425	87.11 429

usedtu_dtu_shiyan1		85.03 294	83.24 307	90.37 262	86.62 413	86.24 42	96.23 241	95.30 228	84.55 226	77.22 340	88.47 357	67.85 293	95.27 375	76.59 332	76.35 358	89.61 359

FE-MVSNET3		85.03 294	83.24 307	90.37 262	86.62 413	86.24 42	96.23 241	95.30 228	84.55 226	77.22 340	88.47 357	67.85 293	95.27 375	76.59 332	76.35 358	89.61 359

tt0805		81.20 362	79.06 371	87.61 340	86.50 415	72.97 403	93.66 365	95.48 212	74.11 415	76.23 359	91.99 301	41.36 469	97.40 247	77.44 324	74.78 370	92.45 328

v10		81.43 357	79.53 366	87.11 356	86.38 416	78.87 283	94.31 347	93.43 379	77.88 377	73.24 391	85.26 413	65.44 319	95.75 349	72.14 378	67.71 424	86.72 433

PEN-MVS		79.47 380	78.26 376	83.08 419	86.36 417	68.58 443	93.85 363	94.77 257	79.76 349	71.37 407	88.55 353	59.79 363	92.46 440	64.50 422	65.40 441	88.19 409

UniMVSNet_ETH3D		80.86 367	78.75 373	87.22 355	86.31 418	72.02 412	91.95 402	93.76 356	73.51 420	75.06 376	90.16 333	43.04 461	95.66 354	76.37 338	78.55 349	93.98 311

v1144		82.90 335	81.27 340	87.78 335	86.29 419	79.07 280	96.14 251	93.93 332	80.05 344	77.38 336	86.80 387	65.50 318	95.93 338	75.21 353	70.13 398	88.33 407

V42		83.04 332	81.53 336	87.57 344	86.27 420	79.09 279	95.87 279	94.11 322	80.35 335	77.22 340	86.79 388	65.32 322	96.02 331	77.74 316	70.14 397	87.61 420

v2v482		83.46 323	81.86 331	88.25 321	86.19 421	79.65 261	96.34 231	94.02 329	81.56 307	77.32 338	88.23 363	65.62 317	96.03 330	77.77 315	69.72 405	89.09 376

v148		82.41 344	80.89 344	86.99 358	86.18 422	76.81 353	96.27 236	93.82 345	80.49 328	75.28 373	86.11 403	67.32 304	95.75 349	75.48 350	67.03 432	88.42 405

dtuonly		84.63 303	84.08 290	86.30 371	86.14 423	69.59 437	92.71 391	90.28 444	82.00 301	80.87 301	94.51 239	62.61 341	96.18 326	79.00 303	88.60 250	93.14 324

pmmvs4		82.54 340	80.79 345	87.79 334	86.11 424	80.49 232	93.55 370	93.18 391	77.29 385	73.35 389	89.40 344	65.26 323	95.05 396	75.32 352	73.61 375	87.83 415

MVP-Stereo		82.65 339	81.67 334	85.59 384	86.10 425	78.29 308	93.33 376	92.82 399	77.75 379	69.17 430	87.98 367	59.28 370	95.76 348	71.77 379	96.88 105	82.73 471
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v1192		82.31 345	80.55 351	87.60 341	85.94 426	78.47 303	95.85 281	93.80 349	79.33 357	76.97 345	86.51 391	63.33 338	95.87 340	73.11 372	70.13 398	88.46 403

TransMVSNet (Re)		76.94 407	74.38 410	84.62 400	85.92 427	75.25 380	95.28 306	89.18 455	73.88 418	67.22 434	86.46 393	59.64 364	94.10 421	59.24 451	52.57 483	84.50 460

PS-MVSNAJss		84.91 298	84.30 284	86.74 360	85.89 428	74.40 388	94.95 328	94.16 319	83.93 251	76.45 353	90.11 335	71.04 265	95.77 347	83.16 258	79.02 343	90.06 354

v144192		82.43 341	80.73 347	87.54 345	85.81 429	78.22 312	95.98 260	93.78 351	79.09 364	77.11 343	86.49 392	64.66 331	95.91 339	74.20 363	69.42 406	88.49 401

v1921920		82.02 348	80.23 355	87.41 349	85.62 430	77.92 325	95.79 285	93.69 363	78.86 368	76.67 348	86.44 394	62.50 342	95.83 342	72.69 374	69.77 404	88.47 402

v1240		81.70 353	79.83 363	87.30 353	85.50 431	77.70 337	95.48 299	93.44 377	78.46 373	76.53 352	86.44 394	60.85 360	95.84 341	71.59 381	70.17 396	88.35 406

pm-mvs1		80.05 373	78.02 378	86.15 372	85.42 432	75.81 374	95.11 322	92.69 402	77.13 387	70.36 417	87.43 375	58.44 376	95.27 375	71.36 383	64.25 446	87.36 427

our_test_3		77.90 398	75.37 402	85.48 386	85.39 433	76.74 354	93.63 366	91.67 421	73.39 423	65.72 446	84.65 424	58.20 379	93.13 437	57.82 455	67.87 421	86.57 436

ppachtmachnet_test		77.19 405	74.22 412	86.13 373	85.39 433	78.22 312	93.98 356	91.36 428	71.74 441	67.11 436	84.87 422	56.67 400	93.37 436	52.21 474	64.59 443	86.80 432

MDA-MVSNet-bldmvs		71.45 438	67.94 445	81.98 432	85.33 435	68.50 444	92.35 397	88.76 460	70.40 446	42.99 501	81.96 449	46.57 450	91.31 458	48.75 487	54.39 471	86.11 442

Baseline_NR-MVSNet		81.22 361	80.07 358	84.68 397	85.32 436	75.12 381	96.48 216	88.80 459	76.24 400	77.28 339	86.40 397	67.61 297	94.39 417	75.73 345	66.73 434	84.54 459

DTE-MVSNet		78.37 391	77.06 385	82.32 430	85.22 437	67.17 453	93.40 372	93.66 364	78.71 370	70.53 416	88.29 362	59.06 372	92.23 446	61.38 438	63.28 451	87.56 422

pmmvs5		81.34 358	79.54 365	86.73 363	85.02 438	76.91 350	96.22 243	91.65 422	77.65 380	73.55 384	88.61 352	55.70 408	94.43 416	74.12 364	73.35 378	88.86 395

XVG-ACMP-BASELINE		79.38 381	77.90 379	83.81 409	84.98 439	67.14 454	89.03 436	93.18 391	80.26 339	72.87 395	88.15 365	38.55 475	96.26 321	76.05 341	78.05 353	88.02 412

test_vis1_n		85.60 282	85.70 256	85.33 388	84.79 440	64.98 461	96.83 185	91.61 424	87.36 130	91.00 130	94.84 229	36.14 480	97.18 269	95.66 65	93.03 177	93.82 314

MDA-MVSNet_test_wron		73.54 425	70.43 434	82.86 421	84.55 441	71.85 416	91.74 408	91.32 430	67.63 457	46.73 498	81.09 457	55.11 412	90.42 467	55.91 465	59.76 457	86.31 439

SixPastTwentyTwo		76.04 411	74.32 411	81.22 436	84.54 442	61.43 479	91.16 415	89.30 454	77.89 376	64.04 452	86.31 398	48.23 440	94.29 419	63.54 430	63.84 449	87.93 414

YYNet1		73.53 426	70.43 434	82.85 422	84.52 443	71.73 419	91.69 409	91.37 427	67.63 457	46.79 497	81.21 456	55.04 413	90.43 466	55.93 464	59.70 458	86.38 438

tt0320-xc		69.70 443	65.27 455	82.99 420	84.33 444	71.92 415	89.56 432	82.08 494	50.11 499	61.87 466	77.50 472	30.48 494	92.34 443	60.30 444	51.20 485	84.71 457

N_pmnet		61.30 459	60.20 462	64.60 482	84.32 445	17.00 537	91.67 410	10.98 537	61.77 476	58.45 480	78.55 468	49.89 435	91.83 452	42.27 497	63.94 448	84.97 455

mvs_tets		81.74 352	80.71 348	84.84 394	84.22 446	70.29 431	93.91 360	93.78 351	82.77 285	73.37 388	89.46 343	47.36 448	95.31 373	81.99 269	79.55 339	88.92 393

jajsoiax		82.12 347	81.15 342	85.03 393	84.19 447	70.70 427	94.22 353	93.95 330	83.07 275	73.48 385	89.75 337	49.66 436	95.37 369	82.24 268	79.76 333	89.02 386

EU-MVSNet		76.92 408	76.95 386	76.83 462	84.10 448	54.73 497	91.77 407	92.71 401	72.74 428	69.57 427	88.69 351	58.03 382	87.43 484	64.91 420	70.00 402	88.33 407

test_djsdf		83.00 334	82.45 323	84.64 399	84.07 449	69.78 435	94.80 334	94.48 280	80.74 321	75.41 372	87.70 371	61.32 359	95.10 389	83.77 246	79.76 333	89.04 382

v7n		79.32 382	77.34 382	85.28 389	84.05 450	72.89 405	93.38 373	93.87 338	75.02 409	70.68 414	84.37 425	59.58 366	95.62 359	67.60 402	67.50 426	87.32 428

test_vis1_rt		73.96 420	72.40 423	78.64 453	83.91 451	61.16 480	95.63 293	68.18 510	76.32 397	60.09 473	74.77 483	29.01 496	97.54 224	87.74 209	75.94 361	77.22 493

dmvs_testset		72.00 437	73.36 419	67.91 476	83.83 452	31.90 522	85.30 468	77.12 502	82.80 284	63.05 459	92.46 291	61.54 356	82.55 499	42.22 498	71.89 387	89.29 369

sc_t1		72.37 433	68.03 444	85.39 387	83.78 453	70.51 428	91.27 414	83.70 490	52.46 498	68.29 431	82.02 448	30.58 493	94.81 403	64.50 422	55.69 465	90.85 339

OurMVSNet-221017-0		77.18 406	76.06 392	80.55 441	83.78 453	60.00 484	90.35 423	91.05 435	77.01 391	66.62 442	87.92 368	47.73 446	94.03 422	71.63 380	68.44 415	87.62 419

EG-PatchMatch MVS		74.92 417	72.02 425	83.62 414	83.76 455	73.28 397	93.62 367	92.04 414	68.57 455	58.88 478	83.80 431	31.87 490	95.57 363	56.97 461	78.67 345	82.00 480

tt0320		70.21 442	66.07 450	82.64 424	83.42 456	70.82 426	89.63 428	84.10 486	49.75 501	62.71 461	77.28 475	33.35 486	92.45 442	58.78 452	55.62 466	84.64 458

K. test v3		73.62 422	71.59 427	79.69 445	82.98 457	59.85 485	90.85 419	88.83 458	77.13 387	58.90 477	82.11 446	43.62 456	91.72 454	65.83 416	54.10 472	87.50 425

test_fmvs2		79.59 377	79.90 362	78.67 452	82.86 458	55.82 494	95.20 314	89.55 450	81.09 313	80.12 313	89.80 336	34.31 485	93.51 433	87.82 206	78.36 351	86.69 434

test_fmvsmconf0.01_n		91.08 131	90.68 127	92.29 157	82.43 459	80.12 245	97.94 85	93.93 332	92.07 40	91.97 112	97.60 102	67.56 299	99.53 87	97.09 50	95.56 140	97.21 192

EGC-MVSNET		52.46 469	47.56 472	67.15 478	81.98 460	60.11 483	82.54 479	72.44 506	0.11 559	0.70 561	74.59 484	25.11 497	83.26 496	29.04 513	61.51 455	58.09 510

anonymousdsp		80.98 366	79.97 360	84.01 407	81.73 461	70.44 430	92.49 393	93.58 372	77.10 389	72.98 394	86.31 398	57.58 391	94.90 398	79.32 298	78.63 348	86.69 434

dtuonlycased		72.49 431	71.58 428	75.22 468	81.04 462	64.71 462	92.43 395	86.46 475	75.62 403	59.79 475	78.43 469	48.54 439	85.84 490	63.66 429	58.28 459	75.10 495

Anonymous20231206		75.29 416	73.64 417	80.22 443	80.75 463	63.38 471	93.36 374	90.71 442	73.09 425	67.12 435	83.70 432	50.33 433	90.85 462	53.63 472	70.10 400	86.44 437

Gipuma		45.11 475	42.05 476	54.30 494	80.69 464	51.30 499	35.80 522	83.81 489	28.13 512	27.94 517	34.53 527	11.41 512	76.70 508	21.45 523	54.65 468	34.90 527
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
lessismore_v0				79.98 444	80.59 465	58.34 488		80.87 496		58.49 479	83.46 434	43.10 460	93.89 425	63.11 432	48.68 490	87.72 416

OpenMVS_ROB	68.52 20	73.02 429	69.57 437	83.37 417	80.54 466	71.82 417	93.60 369	88.22 463	62.37 472	61.98 464	83.15 438	35.31 484	95.47 365	45.08 493	75.88 362	82.82 469

gbinet_0.2-2-1-0.02		78.67 389	75.67 398	87.70 336	80.38 467	79.60 263	96.25 239	94.03 328	72.51 433	71.41 406	83.33 436	55.97 407	94.45 415	73.37 371	53.73 478	89.04 382

testgi		74.88 418	73.40 418	79.32 448	80.13 468	61.75 476	93.21 381	86.64 474	79.49 355	66.56 443	91.06 316	35.51 483	88.67 474	56.79 462	71.25 389	87.56 422

blend_shiyan4		81.76 351	79.58 364	88.31 317	80.00 469	80.59 220	95.95 262	93.73 359	72.26 437	71.14 411	82.52 441	76.13 169	95.15 384	77.83 310	66.62 435	89.19 372

wanda-best-256-512		78.87 385	75.75 395	88.22 323	79.74 470	80.51 230	95.92 265	93.75 357	72.60 430	70.34 418	82.14 442	57.91 386	95.09 391	75.61 346	53.77 474	89.05 379

FE-blended-shiyan7		78.87 385	75.75 395	88.22 323	79.74 470	80.51 230	95.92 265	93.75 357	72.60 430	70.34 418	82.14 442	57.91 386	95.09 391	75.61 346	53.77 474	89.05 379

usedtu_blend_shiyan5		77.51 402	73.93 416	88.26 319	79.74 470	80.59 220	90.76 420	89.69 448	63.21 468	70.34 418	82.14 442	57.91 386	95.15 384	77.83 310	53.77 474	89.05 379

CMPMVS	54.94 21	75.71 415	74.56 409	79.17 449	79.69 473	55.98 492	89.59 429	93.30 386	60.28 483	53.85 490	89.07 346	47.68 447	96.33 319	76.55 334	81.02 328	85.22 452
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
blended_shiyan6		78.74 388	75.63 400	88.07 328	79.63 474	80.10 246	95.72 286	93.73 359	72.43 435	70.17 424	82.09 447	57.69 389	95.07 394	75.47 351	53.77 474	89.03 384

blended_shiyan8		78.76 387	75.65 399	88.10 327	79.58 475	80.20 241	95.70 289	93.71 362	72.43 435	70.26 421	82.12 445	57.66 390	95.08 393	75.57 348	53.80 473	89.02 386

LF4IMVS		72.36 434	70.82 430	76.95 461	79.18 476	56.33 491	86.12 462	86.11 477	69.30 453	63.06 458	86.66 389	33.03 488	92.25 445	65.33 418	68.64 413	82.28 476

pmmvs6		74.65 419	71.67 426	83.60 415	79.13 477	69.94 433	93.31 379	90.88 439	61.05 482	65.83 445	84.15 428	43.43 457	94.83 402	66.62 410	60.63 456	86.02 445

MVStest1		66.93 454	63.01 458	78.69 451	78.56 478	71.43 423	85.51 467	86.81 471	49.79 500	48.57 496	84.15 428	53.46 420	83.31 495	43.14 496	37.15 506	81.34 486

DeepMVS_CX				64.06 483	78.53 479	43.26 510		68.11 512	69.94 450	38.55 503	76.14 481	18.53 502	79.34 500	43.72 494	41.62 503	69.57 500

CL-MVSNet_self_test		75.81 413	74.14 414	80.83 440	78.33 480	67.79 447	94.22 353	93.52 374	77.28 386	69.82 425	81.54 453	61.47 358	89.22 472	57.59 457	53.51 479	85.48 451

test20.03		72.36 434	71.15 429	75.98 466	77.79 481	59.16 486	92.40 396	89.35 453	74.09 416	61.50 467	84.32 426	48.09 441	85.54 492	50.63 480	62.15 454	83.24 466

UnsupCasMVSNet_eth		73.25 427	70.57 433	81.30 435	77.53 482	66.33 457	87.24 453	93.89 337	80.38 332	57.90 482	81.59 451	42.91 462	90.56 464	65.18 419	48.51 491	87.01 431

DSMNet-mixed		73.13 428	72.45 422	75.19 469	77.51 483	46.82 502	85.09 470	82.01 495	67.61 461	69.27 429	81.33 455	50.89 427	86.28 488	54.54 469	83.80 306	92.46 327

Patchmatch-RL test		76.65 409	74.01 415	84.55 401	77.37 484	64.23 465	78.49 491	82.84 493	78.48 372	64.63 451	73.40 488	76.05 171	91.70 455	76.99 327	57.84 461	97.72 135

Anonymous20240521		72.06 436	69.91 436	78.50 454	77.11 485	61.67 478	91.62 411	90.97 437	65.52 464	62.37 462	79.05 467	36.32 479	90.96 461	57.75 456	68.52 414	82.87 468

test_method		56.77 463	54.53 467	63.49 484	76.49 486	40.70 512	75.68 496	74.24 504	19.47 522	48.73 495	71.89 494	19.31 501	65.80 517	57.46 458	47.51 495	83.97 464

MIMVSNet1		69.44 447	66.65 449	77.84 455	76.48 487	62.84 473	87.42 451	88.97 457	66.96 462	57.75 484	79.72 466	32.77 489	85.83 491	46.32 489	63.42 450	84.85 456

pmmvs-eth3d		73.59 423	70.66 432	82.38 428	76.40 488	73.38 394	89.39 434	89.43 452	72.69 429	60.34 472	77.79 471	46.43 451	91.26 459	66.42 414	57.06 463	82.51 472

new_pmnet		66.18 455	63.18 457	75.18 470	76.27 489	61.74 477	83.79 475	84.66 482	56.64 494	51.57 493	71.85 495	31.29 491	87.93 479	49.98 482	62.55 452	75.86 494

KD-MVS_self_test		70.97 441	69.31 439	75.95 467	76.24 490	55.39 496	87.45 450	90.94 438	70.20 449	62.96 460	77.48 473	44.01 454	88.09 478	61.25 439	53.26 480	84.37 461

ttmdpeth		69.58 444	66.92 448	77.54 458	75.95 491	62.40 474	88.09 444	84.32 485	62.87 471	65.70 447	86.25 400	36.53 478	88.53 476	55.65 467	46.96 496	81.70 483

mvs5depth		71.40 439	68.36 443	80.54 442	75.31 492	65.56 460	79.94 484	85.14 480	69.11 454	71.75 405	81.59 451	41.02 471	93.94 424	60.90 442	50.46 486	82.10 477

FE-MVSNET2		73.72 421	70.80 431	82.46 427	74.97 493	73.81 392	91.88 405	91.73 420	76.70 395	59.74 476	77.41 474	42.26 464	90.52 465	64.75 421	57.79 462	83.06 467

UnsupCasMVSNet_bld		68.60 452	64.50 456	80.92 439	74.63 494	67.80 446	83.97 474	92.94 398	65.12 465	54.63 489	68.23 499	35.97 481	92.17 448	60.13 445	44.83 498	82.78 470

FE-MVSNET		69.26 449	66.03 451	78.93 450	73.82 495	68.33 445	89.65 427	84.06 487	70.21 448	57.79 483	76.94 479	41.48 468	86.98 487	45.85 491	54.51 470	81.48 485

PM-MVS		69.32 448	66.93 447	76.49 463	73.60 496	55.84 493	85.91 463	79.32 500	74.72 411	61.09 469	78.18 470	21.76 500	91.10 460	70.86 389	56.90 464	82.51 472

new-patchmatchnet		68.85 451	65.93 452	77.61 457	73.57 497	63.94 468	90.11 425	88.73 461	71.62 442	55.08 488	73.60 487	40.84 472	87.22 486	51.35 478	48.49 492	81.67 484

ArgMatch-Sym		59.60 461	56.89 464	67.74 477	71.40 498	45.64 507	81.24 481	58.34 518	58.65 491	52.79 492	81.51 454	11.35 513	76.76 506	60.83 443	35.86 508	80.81 487

ArgMatch-SfM		60.14 460	57.35 463	68.50 475	71.14 499	45.17 509	80.16 482	63.06 514	59.74 488	51.33 494	80.81 458	11.74 511	78.30 502	61.13 440	37.05 507	82.04 479

WB-MVS		57.26 462	56.22 465	60.39 489	69.29 500	35.91 518	86.39 461	70.06 508	59.84 487	46.46 499	72.71 490	51.18 426	78.11 503	15.19 528	34.89 509	67.14 503

test_fmvs3		69.56 445	69.19 440	70.67 473	69.01 501	47.05 501	90.87 418	86.81 471	71.31 444	66.79 440	77.15 476	16.40 504	83.17 497	81.84 270	62.51 453	81.79 482

SSC-MVS		56.01 465	54.96 466	59.17 490	68.42 502	34.13 519	84.98 471	69.23 509	58.08 493	45.36 500	71.67 496	50.30 434	77.46 504	14.28 529	32.33 510	65.91 505

ambc				76.02 465	68.11 503	51.43 498	64.97 508	89.59 449		60.49 471	74.49 485	17.17 503	92.46 440	61.50 437	52.85 482	84.17 463

APD_test1		56.56 464	53.58 468	65.50 479	67.93 504	46.51 504	77.24 495	72.95 505	38.09 504	42.75 502	75.17 482	13.38 507	82.78 498	40.19 501	54.53 469	67.23 502

pmmvs3		65.75 456	62.18 459	76.45 464	67.12 505	64.54 463	88.68 439	85.05 481	54.77 496	57.54 485	73.79 486	29.40 495	86.21 489	55.49 468	47.77 494	78.62 491

TDRefinement		69.20 450	65.78 453	79.48 446	66.04 506	62.21 475	88.21 442	86.12 476	62.92 470	61.03 470	85.61 408	33.23 487	94.16 420	55.82 466	53.02 481	82.08 478

usedtu_dtu_shiyan2		64.65 457	60.40 461	77.38 459	64.24 507	57.84 489	89.16 435	87.60 467	52.95 497	53.43 491	71.31 498	23.41 498	88.27 477	51.95 475	49.58 488	86.03 444

mvsany_test3		67.19 453	65.34 454	72.72 471	63.08 508	48.57 500	83.12 477	78.09 501	72.07 438	61.21 468	77.11 477	22.94 499	87.78 482	78.59 306	51.88 484	81.80 481

test_f		64.01 458	62.13 460	69.65 474	63.00 509	45.30 508	83.66 476	80.68 497	61.30 479	55.70 487	72.62 491	14.23 506	84.64 493	69.84 394	58.11 460	79.00 490

DenseAffine		43.98 476	39.51 480	57.39 491	60.41 510	37.29 516	67.44 507	34.50 526	35.36 507	31.38 512	65.55 501	4.21 524	67.77 515	35.59 504	21.11 518	67.10 504

LoFTR		45.13 474	39.91 479	60.78 488	58.50 511	33.07 520	59.69 512	57.64 519	30.48 511	25.92 520	63.30 503	4.30 523	74.96 510	28.23 520	31.12 512	74.31 497

test_vis3_rt		54.10 467	51.04 470	63.27 485	58.16 512	46.08 506	84.17 473	49.32 524	56.48 495	36.56 505	49.48 521	8.03 516	91.91 451	67.29 405	49.87 487	51.82 518

FPMVS		55.09 466	52.93 469	61.57 486	55.98 513	40.51 513	83.11 478	83.41 492	37.61 505	34.95 507	71.95 493	14.40 505	76.95 505	29.81 512	65.16 442	67.25 501

PMMVS2		50.90 470	46.31 473	64.67 481	55.53 514	46.67 503	77.30 494	71.02 507	40.89 503	34.16 508	59.32 510	9.83 514	76.14 509	40.09 502	28.63 513	71.21 498

wuyk23d		14.10 500	13.89 503	14.72 517	55.23 515	22.91 532	33.83 523	3.56 555	4.94 534	4.11 544	2.28 559	2.06 541	19.66 537	10.23 533	8.74 542	1.59 557

E-PMN		32.70 487	32.39 486	33.65 508	53.35 516	25.70 528	74.07 499	53.33 521	21.08 520	17.17 529	33.63 529	11.85 510	54.84 522	12.98 531	14.04 524	20.42 532

testf1		45.70 472	42.41 474	55.58 492	53.29 517	40.02 514	68.96 505	62.67 515	27.45 513	29.85 514	61.58 507	5.98 520	73.83 512	28.49 517	43.46 501	52.90 514

APD_test2		45.70 472	42.41 474	55.58 492	53.29 517	40.02 514	68.96 505	62.67 515	27.45 513	29.85 514	61.58 507	5.98 520	73.83 512	28.49 517	43.46 501	52.90 514

MatchFormer		39.45 479	34.61 483	54.00 495	53.28 519	28.79 526	58.06 515	51.35 523	21.48 518	23.10 523	55.83 515	3.50 528	70.37 514	19.01 525	25.84 515	62.84 506

RoMa-SfM		40.68 478	36.49 481	53.24 496	52.27 520	33.01 521	62.88 509	23.78 531	32.85 508	31.33 513	67.39 500	3.87 525	64.89 518	33.77 507	20.24 520	61.82 508

EMVS		31.70 488	31.45 489	32.48 509	50.72 521	23.95 531	74.78 498	52.30 522	20.36 521	16.08 530	31.48 530	12.80 508	53.60 524	11.39 532	13.10 529	19.88 534

DKM		38.02 481	33.59 485	51.32 497	50.45 522	30.46 523	61.04 511	19.18 532	30.65 510	26.88 518	61.89 506	2.55 534	61.16 519	32.68 509	16.95 521	62.34 507

PDCNetPlus		37.10 482	34.54 484	44.76 500	50.06 523	29.19 525	58.72 514	23.89 530	37.05 506	24.11 522	58.95 512	6.11 519	55.29 521	40.76 500	11.21 537	49.81 519

LCM-MVSNet		52.52 468	48.24 471	65.35 480	47.63 524	41.45 511	72.55 501	83.62 491	31.75 509	37.66 504	57.92 513	9.19 515	76.76 506	49.26 484	44.60 499	77.84 492

DKM-HiRes		32.92 486	29.13 492	44.31 501	42.93 525	25.35 529	53.22 516	13.26 535	25.92 516	24.31 521	57.58 514	1.88 543	50.95 526	28.87 514	14.19 523	56.63 513

ALIKED-LG		17.53 497	16.82 500	19.64 514	42.07 526	19.09 533	31.53 525	11.93 536	7.76 530	10.68 534	26.90 533	3.52 527	22.14 533	3.10 542	13.89 525	17.68 535

MVE	35.65 22	33.85 483	29.49 491	46.92 499	41.86 527	36.28 517	50.45 518	56.52 520	18.75 523	18.28 526	37.84 525	2.41 537	58.41 520	18.71 526	20.62 519	46.06 523
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
RoMa-HiRes		33.28 485	29.63 490	44.22 502	41.01 528	25.30 530	51.82 517	14.13 534	25.85 517	26.34 519	61.96 505	2.78 532	54.52 523	28.42 519	14.36 522	52.83 517

ALIKED-MNN		16.35 498	15.48 502	18.95 515	40.20 529	19.09 533	30.16 527	10.63 539	6.03 531	9.48 537	24.90 535	2.59 533	21.29 534	2.88 544	12.46 531	16.48 536

ANet_high		46.22 471	41.28 478	61.04 487	39.91 530	46.25 505	70.59 504	76.18 503	58.87 490	23.09 524	48.00 523	12.58 509	66.54 516	28.65 516	13.62 526	70.35 499

ALIKED-NN		16.22 499	15.63 501	17.99 516	39.36 531	18.31 535	29.26 529	10.71 538	5.97 532	10.10 535	26.06 534	2.80 531	20.08 536	2.91 543	13.46 527	15.60 538

MVS_clip		23.81 494	25.14 495	19.82 513	33.23 532	11.41 542	26.86 530	4.32 549	5.29 533	31.51 511	63.24 504	7.08 518	7.43 545	28.82 515	25.90 514	40.62 525

MASt3R-SfM		33.79 484	32.03 487	39.08 505	30.86 533	18.05 536	44.70 519	25.59 529	21.32 519	31.97 510	71.52 497	3.78 526	38.14 531	35.97 503	22.58 517	61.06 509

PMVS	34.80 23	39.19 480	35.53 482	50.18 498	29.72 534	30.30 524	59.60 513	66.20 513	26.06 515	17.91 528	49.53 520	3.12 529	74.09 511	18.19 527	49.40 489	46.14 522
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
GLUNet-SfM		23.82 493	18.93 498	38.50 506	29.22 535	15.72 540	24.44 533	26.94 528	12.76 528	13.93 532	40.99 524	2.01 542	46.93 528	13.88 530	6.19 550	52.85 516

SP-LightGlue		12.02 501	12.06 506	11.90 518	28.59 536	6.58 552	24.58 532	7.89 544	3.94 538	6.94 541	17.94 540	2.45 535	7.82 541	3.96 538	12.26 532	21.30 528

SP-SuperGlue		12.00 502	12.07 505	11.81 519	28.37 537	6.58 552	24.63 531	8.02 543	3.99 537	7.02 540	18.00 539	2.44 536	7.72 543	3.95 539	12.19 533	21.13 530

PMatch-SfM		26.26 491	22.21 497	38.43 507	28.29 538	16.65 539	37.61 521	8.91 541	18.02 525	18.64 525	53.32 516	0.55 558	41.01 530	24.74 521	9.79 539	57.63 512

SP-MNN		11.64 504	11.60 509	11.74 520	27.48 539	6.11 558	24.23 534	7.72 545	3.40 541	6.22 543	17.81 542	2.13 539	7.94 540	3.69 541	11.73 535	21.18 529

SP-NN		11.53 505	11.59 510	11.38 522	27.20 540	6.14 557	24.02 535	7.42 547	3.57 539	6.38 542	17.94 540	2.17 538	7.78 542	3.71 540	11.86 534	20.23 533

ELoFTR		28.06 490	23.17 496	42.73 503	26.41 541	16.73 538	32.43 524	29.00 527	18.06 524	18.03 527	50.11 519	1.10 545	53.50 525	21.73 522	11.65 536	57.96 511

VLMVS		26.26 491	26.52 494	25.45 512	25.35 542	7.91 547	30.71 526	15.37 533	3.37 542	34.11 509	65.40 502	8.03 516	21.07 535	32.40 510	23.95 516	47.39 521

VLMVS_CLIP		31.24 489	31.62 488	30.09 511	23.48 543	9.99 543	39.45 520	43.68 525	8.32 529	35.12 506	61.15 509	5.95 522	42.45 529	35.23 505	32.16 511	37.83 526

PMatch-Up-SfM		21.53 495	18.34 499	31.10 510	23.05 544	12.66 541	29.81 528	5.63 548	13.87 527	16.04 531	48.08 522	0.39 562	31.11 532	21.09 524	7.09 547	49.53 520

SIFT-NN		7.34 511	7.57 516	6.67 525	22.83 545	8.78 544	12.92 539	4.04 551	2.52 543	3.88 545	11.56 544	0.86 546	6.16 546	0.95 547	8.56 543	5.09 541

SIFT-MNN		6.97 513	7.12 517	6.51 526	21.26 546	8.28 545	11.89 540	4.05 550	2.50 544	3.39 547	11.27 545	0.76 547	6.14 547	0.95 547	8.05 545	5.09 541

SIFT-NCM-Cal		6.46 515	6.58 519	6.10 528	20.43 547	7.62 548	11.15 543	3.59 553	2.40 549	2.33 555	10.33 552	0.68 552	6.03 548	0.77 555	7.51 546	4.64 547

tmp_tt		41.54 477	41.93 477	40.38 504	20.10 548	26.84 527	61.93 510	59.09 517	14.81 526	28.51 516	80.58 459	35.53 482	48.33 527	63.70 428	13.11 528	45.96 524

SIFT-NN-NCMNet		6.77 514	6.92 518	6.30 527	19.98 549	8.05 546	11.79 541	3.97 552	2.43 546	3.43 546	10.93 546	0.75 548	5.95 549	0.88 549	8.15 544	4.90 543

SIFT-ConvMatch		6.05 518	6.14 522	5.78 530	19.43 550	7.31 549	9.58 547	3.30 557	2.42 547	2.67 552	10.54 550	0.65 553	5.73 550	0.83 553	5.84 552	4.29 548

SIFT-UMatch		5.86 520	6.01 523	5.38 532	18.70 551	6.22 556	10.07 545	3.07 559	2.39 550	2.42 553	10.54 550	0.63 556	5.65 553	0.84 552	5.49 553	4.28 549

SIFT-CM-Cal		5.56 522	5.66 525	5.26 534	18.45 552	6.34 555	8.44 549	2.81 560	2.36 551	2.42 553	9.99 555	0.64 554	5.41 554	0.74 557	5.05 554	4.02 550

SIFT-NN-CMatch		6.23 516	6.33 520	5.94 529	18.10 553	7.22 550	10.34 544	3.54 556	2.42 547	3.36 548	10.93 546	0.72 550	5.71 551	0.87 550	6.67 549	4.89 544

SIFT-UM-Cal		5.40 523	5.58 526	4.87 536	18.00 554	5.37 560	9.03 548	2.49 562	2.33 552	2.14 557	10.11 554	0.60 557	5.27 556	0.77 555	4.78 556	3.95 551

SIFT-NN-UMatch		6.11 517	6.25 521	5.68 531	17.01 555	6.50 554	11.20 542	3.58 554	2.44 545	2.68 551	10.88 548	0.74 549	5.70 552	0.87 550	6.85 548	4.82 545

SIFT-NN-PointCN		5.63 521	5.80 524	5.10 535	16.00 556	5.22 562	10.00 546	3.21 558	2.26 553	2.92 549	10.15 553	0.72 550	5.35 555	0.81 554	6.14 551	4.74 546

SIFT-PCN-Cal		4.71 525	4.89 528	4.18 537	15.70 557	3.90 564	7.58 551	2.37 563	2.09 555	1.95 558	8.68 556	0.51 559	4.71 557	0.68 558	4.45 557	3.93 552

SIFT-PointCN		4.77 524	4.97 527	4.17 538	15.53 558	3.97 563	8.20 550	2.62 561	2.10 554	1.91 559	8.44 557	0.47 560	4.70 558	0.67 559	4.79 555	3.85 553

SIFT-NCMNet		4.03 526	4.21 529	3.50 539	14.53 559	3.56 565	6.14 552	1.51 564	2.08 556	1.72 560	7.39 558	0.42 561	4.00 559	0.57 560	3.56 558	2.93 554

SP-DiffGlue		11.69 503	11.68 508	11.70 521	11.01 560	7.08 551	18.35 536	8.44 542	4.41 535	11.18 533	28.64 532	2.84 530	7.44 544	7.44 534	12.85 530	20.56 531

XFeat-MNN		10.03 506	9.79 512	10.74 523	9.46 561	6.05 559	16.60 537	9.52 540	4.29 536	8.53 539	22.45 536	2.10 540	13.28 538	5.47 535	9.68 540	12.89 539

XFeat-NN		9.17 508	9.18 513	9.14 524	8.78 562	5.26 561	15.30 538	7.57 546	3.56 540	8.63 538	22.05 537	1.87 544	11.03 539	4.95 536	9.92 538	11.13 540

MVS_baseline		7.08 512	7.68 515	5.28 533	7.84 563	0.20 568	2.38 553	0.52 565	0.10 560	10.02 536	34.66 526	0.64 554	0.00 562	4.06 537	8.92 541	15.64 537

testmvs		9.92 507	12.94 504	0.84 541	0.65 564	0.29 567	93.78 364	0.39 566	0.42 557	2.85 550	15.84 543	0.17 564	0.30 561	2.18 545	0.21 559	1.91 556

test123		9.07 509	11.73 507	1.11 540	0.50 565	0.77 566	89.44 433	0.20 567	0.34 558	2.15 556	10.72 549	0.34 563	0.32 560	1.79 546	0.08 560	2.23 555

PatchmatchNet2					0.00 566	72.22 406	92.05 401	89.18 455	62.36 473
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
mmdepth		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

monomultidepth		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

test_blank		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

eth-test2					0.00 566

eth-test					0.00 566

uanet_test		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

DCPMVS		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

cdsmvs_eth3d_5k		21.43 496	28.57 493	0.00 542	0.00 566	0.00 569	0.00 554	95.93 182	0.00 561	0.00 562	97.66 95	63.57 335	0.00 562	0.00 561	0.00 561	0.00 558

pcd_1.5k_mvsjas		5.92 519	7.89 514	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	71.04 265	0.00 562	0.00 561	0.00 561	0.00 558

sosnet-low-res		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

sosnet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

uncertanet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

Regformer		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

ab-mvs-re		8.11 510	10.81 511	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	97.30 119	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

uanet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

Meshroom													0.00 562
: In preparation.
AliceVision / Meshro													0.00 562
: In preparation.
AliceVision_Meshroom													0.00 562
: In preparation.
PatchmatchNet1														42.17 499	64.00 447	85.01 454
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													91.74 453
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						67.18 450								49.00 485

PC_three_1452									91.12 52	98.33 6	98.42 45	92.51 2	99.81 29	98.96 6	99.37 1	99.70 4

test_241102_TWO								96.78 68	88.72 86	97.70 15	98.91 3	87.86 25	99.82 25	98.15 23	99.00 15	99.47 10

test_0728_THIRD									88.38 94	96.69 32	98.76 19	89.64 14	99.76 47	97.47 42	98.84 23	99.38 15

GSMVS																97.54 154

sam_mvs1												77.59 132				97.54 154

sam_mvs												75.35 193

MTGPA								96.33 142

test_post1							85.88 464				30.24 531	73.77 218	95.07 394	73.89 365

test_post											33.80 528	76.17 167	95.97 333

patchmatchnet-post											77.09 478	77.78 130	95.39 367

MTMP							97.53 119	68.16 511

test9_res														96.00 60	99.03 13	98.31 78

agg_prior2														94.30 84	99.00 15	98.57 61

test_prior4						82.34 150	97.75 101

test_prior2							98.37 57		86.08 172	94.57 72	98.02 74	83.14 63		95.05 75	98.79 27

旧先验2							96.97 173		74.06 417	96.10 43			97.76 200	88.38 201

新几何2							96.42 224

无先验							96.87 182	96.78 68	77.39 383				99.52 88	79.95 290		98.43 70

原ACMM2							96.84 184

testdata2													99.48 92	76.45 336

segment_acmp												82.69 69

testdata1							95.57 297		87.44 127

plane_prior5								94.69 263					97.30 259	87.08 216	82.82 317	90.96 336

plane_prior4											94.15 256

plane_prior3						77.75 335			90.17 69	81.33 296

plane_prior2							97.18 148		89.89 72

plane_prior						77.96 322	97.52 122		90.36 67						82.96 315

n2								0.00 568

nn								0.00 568

door-mid								79.75 499

test11								96.50 118

door								80.13 498

HQP5-MVS						78.48 300

BP-MVS														87.67 211

HQP4-MVS										82.30 283			97.32 257			91.13 334

HQP3-MVS								94.80 254							83.01 313

HQP2-MVS												65.40 320

MDTV_nov1_ep13_2view						81.74 177	86.80 456		80.65 323	85.65 229		74.26 211		76.52 335		96.98 213

ACMMP++_ref															78.45 350

ACMMP++															79.05 342

Test By Simon												71.65 257

High-resolution multi-view benchmark