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.

RA-MVS			88.76 15		95.68 1	73.57 13	94.07 3	93.39 36	70.82 255	90.99 21	95.81 6	75.13 28	97.22 17	88.08 43	94.91 45

test_0728_SECOND				87.71 35	95.34 2	71.43 62	93.49 11	94.23 6					97.49 4	89.08 22	96.41 12	94.21 74

SED-MVS		90.08 2	90.85 2	87.77 28	95.30 3	70.98 75	93.57 9	94.06 15	77.24 65	93.10 1	95.72 12	82.99 1	97.44 7	89.07 25	96.63 4	94.88 19

IU-MVS					95.30 3	71.25 67		92.95 63	66.81 340	92.39 7				88.94 28	96.63 4	94.85 24

test_241102_ONE					95.30 3	70.98 75		94.06 15	77.17 68	93.10 1	95.39 20	82.99 1	97.27 14

DVP-MVS		89.60 4	90.35 4	87.33 45	95.27 6	71.25 67	93.49 11	92.73 73	77.33 60	92.12 12	95.78 8	80.98 10	97.40 9	89.08 22	96.41 12	93.33 130
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					95.27 6	71.25 67	93.60 8	94.11 11	77.33 60	92.81 4	95.79 7	80.98 10

test_one_0601					95.07 8	71.46 61		94.14 10	78.27 42	92.05 14	95.74 10	80.83 12

test_part2					95.06 9	72.65 33				91.80 16

HPM-MVS++		89.02 10	89.15 12	88.63 5	95.01 10	76.03 1	92.38 33	92.85 67	80.26 12	87.78 52	94.27 49	75.89 24	96.81 29	87.45 49	96.44 9	93.05 152

FOURS1					95.00 11	72.39 42	95.06 1	93.84 21	74.49 159	91.30 18

DPE-MVS		89.48 6	89.98 5	88.01 16	94.80 12	72.69 32	91.59 52	94.10 13	75.90 113	92.29 8	95.66 14	81.67 6	97.38 13	87.44 50	96.34 15	93.95 89
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CNVR-MVS		88.93 12	89.13 13	88.33 8	94.77 13	73.82 8	90.51 71	93.00 54	80.90 7	88.06 47	94.06 61	76.43 21	96.84 27	88.48 37	95.99 20	94.34 67

ACMMPR		87.44 29	87.23 37	88.08 15	94.64 14	73.59 12	93.04 18	93.20 42	76.78 82	84.66 94	94.52 34	68.81 117	96.65 37	84.53 75	94.90 46	94.00 86

region2R		87.42 31	87.20 38	88.09 14	94.63 15	73.55 14	93.03 20	93.12 48	76.73 85	84.45 99	94.52 34	69.09 111	96.70 33	84.37 77	94.83 50	94.03 84

OPU-MVS				89.06 3	94.62 16	75.42 4	93.57 9				94.02 63	82.45 3	96.87 26	83.77 85	96.48 8	94.88 19

test-260524					94.58 17	71.43 62		94.16 8		90.64 23		78.62 14	97.13 18	88.60 33	96.28 16

HFP-MVS		87.58 26	87.47 32	87.94 19	94.58 17	73.54 16	93.04 18	93.24 41	76.78 82	84.91 86	94.44 41	70.78 81	96.61 39	84.53 75	94.89 47	93.66 108

aaatest				87.86 27	94.57 19	71.43 62	93.28 13	94.36 3	75.24 132	92.25 10	95.03 24		97.39 11	88.15 40	95.96 21	94.75 35

MED-MVS		89.78 3	90.41 3	87.89 24	94.57 19	71.43 62	93.28 13	94.36 3	77.30 62	92.25 10	95.87 4	81.59 7	97.39 11	88.15 40	96.28 16	94.85 24

TestfortrainingZip a		88.83 13	89.21 11	87.68 37	94.57 19	71.25 67	93.28 13	93.91 20	77.30 62	91.13 19	95.87 4	77.62 17	96.95 24	86.12 60	93.07 77	94.85 24

aaEdge-Enhanced		88.98 11	89.39 8	87.75 30	94.54 22	71.43 62	91.61 50	94.25 5	76.30 105	90.62 24	95.03 24	78.06 16	97.07 21	88.15 40	95.96 21	94.75 35

MCST-MVS		87.37 34	87.25 36	87.73 31	94.53 23	72.46 41	89.82 89	93.82 22	73.07 206	84.86 89	92.89 98	76.22 22	96.33 48	84.89 69	95.13 40	94.40 63

APDe-MVS		89.15 8	89.63 7	87.73 31	94.49 24	71.69 56	93.83 5	93.96 18	75.70 120	91.06 20	96.03 2	76.84 19	97.03 22	89.09 21	95.65 31	94.47 60
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS Recon		83.11 137	82.09 151	86.15 72	94.44 25	70.92 80	88.79 137	92.20 108	70.53 265	79.17 210	91.03 168	64.12 180	96.03 58	68.39 281	90.14 132	91.50 219

XVS		87.18 37	86.91 45	88.00 17	94.42 26	73.33 20	92.78 24	92.99 57	79.14 27	83.67 119	94.17 55	67.45 134	96.60 40	83.06 90	94.50 58	94.07 82

X-MVStestdata		80.37 209	77.83 251	88.00 17	94.42 26	73.33 20	92.78 24	92.99 57	79.14 27	83.67 119	12.47 536	67.45 134	96.60 40	83.06 90	94.50 58	94.07 82

mPP-MVS		86.67 46	86.32 55	87.72 33	94.41 28	73.55 14	92.74 26	92.22 105	76.87 79	82.81 142	94.25 51	66.44 149	96.24 52	82.88 95	94.28 65	93.38 126

NCCC		88.06 18	88.01 23	88.24 11	94.41 28	73.62 11	91.22 63	92.83 68	81.50 5	85.79 76	93.47 83	73.02 49	97.00 23	84.90 67	94.94 44	94.10 80

ZNCC-MVS		87.94 22	87.85 25	88.20 12	94.39 30	73.33 20	93.03 20	93.81 23	76.81 80	85.24 81	94.32 46	71.76 66	96.93 25	85.53 64	95.79 26	94.32 69

ZD-MVS					94.38 31	72.22 47		92.67 76	70.98 250	87.75 54	94.07 60	74.01 40	96.70 33	84.66 73	94.84 49

MP-MVS		87.71 23	87.64 27	87.93 21	94.36 32	73.88 6	92.71 28	92.65 79	77.57 51	83.84 115	94.40 43	72.24 59	96.28 50	85.65 62	95.30 39	93.62 115
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DVP-MVS++		90.23 1	91.01 1	87.89 24	94.34 33	71.25 67	95.06 1	94.23 6	78.38 39	92.78 5	95.74 10	82.45 3	97.49 4	89.42 19	96.68 2	94.95 15

MSC_two_6792asdad				89.16 1	94.34 33	75.53 2		92.99 57					97.53 2	89.67 15	96.44 9	94.41 61

No_MVS				89.16 1	94.34 33	75.53 2		92.99 57					97.53 2	89.67 15	96.44 9	94.41 61

MSP-MVS		89.51 5	89.91 6	88.30 10	94.28 36	73.46 18	92.90 22	94.11 11	80.27 11	91.35 17	94.16 56	78.35 15	96.77 30	89.59 17	94.22 67	94.67 42
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
SMA-MVS		89.08 9	89.23 9	88.61 6	94.25 37	73.73 9	92.40 30	93.63 27	74.77 153	92.29 8	95.97 3	74.28 36	97.24 15	88.58 34	96.91 1	94.87 21
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
APD-MVS		87.44 29	87.52 31	87.19 48	94.24 38	72.39 42	91.86 46	92.83 68	73.01 208	88.58 38	94.52 34	73.36 42	96.49 45	84.26 78	95.01 41	92.70 167
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
PGM-MVS		86.68 45	86.27 57	87.90 22	94.22 39	73.38 19	90.22 82	93.04 49	75.53 123	83.86 114	94.42 42	67.87 131	96.64 38	82.70 102	94.57 57	93.66 108

CP-MVS		87.11 38	86.92 44	87.68 37	94.20 40	73.86 7	93.98 4	92.82 71	76.62 88	83.68 118	94.46 38	67.93 129	95.95 65	84.20 81	94.39 62	93.23 134

MTAPA		87.23 36	87.00 40	87.90 22	94.18 41	74.25 5	86.58 236	92.02 116	79.45 23	85.88 74	94.80 29	68.07 128	96.21 53	86.69 55	95.34 36	93.23 134

GST-MVS		87.42 31	87.26 35	87.89 24	94.12 42	72.97 25	92.39 32	93.43 34	76.89 78	84.68 91	93.99 67	70.67 83	96.82 28	84.18 82	95.01 41	93.90 92

SR-MVS		86.73 43	86.67 49	86.91 56	94.11 43	72.11 50	92.37 34	92.56 84	74.50 158	86.84 68	94.65 33	67.31 136	95.77 67	84.80 71	92.85 81	92.84 165

114514_t		80.68 196	79.51 209	84.20 158	94.09 44	67.27 181	89.64 97	91.11 159	58.75 447	74.08 333	90.72 176	58.10 265	95.04 103	69.70 266	89.42 147	90.30 268

HPM-MVS		87.11 38	86.98 42	87.50 43	93.88 45	72.16 48	92.19 39	93.33 38	76.07 110	83.81 116	93.95 70	69.77 98	96.01 61	85.15 65	94.66 52	94.32 69
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
save fliter					93.80 46	72.35 45	90.47 75	91.17 156	74.31 165

ACMMP_NAP		88.05 20	88.08 22	87.94 19	93.70 47	73.05 23	90.86 66	93.59 29	76.27 106	88.14 45	95.09 23	71.06 78	96.67 35	87.67 46	96.37 14	94.09 81

HPM-MVS_fast		85.35 81	84.95 89	86.57 64	93.69 48	70.58 87	92.15 41	91.62 141	73.89 179	82.67 145	94.09 59	62.60 202	95.54 73	80.93 116	92.93 79	93.57 118

TSAR-MVS + MP.		88.02 21	88.11 21	87.72 33	93.68 49	72.13 49	91.41 59	92.35 92	74.62 157	88.90 36	93.85 73	75.75 25	96.00 62	87.80 45	94.63 55	95.04 12
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MP-MVS-pluss		87.67 25	87.72 26	87.54 40	93.64 50	72.04 52	89.80 91	93.50 31	75.17 140	86.34 72	95.29 21	70.86 80	96.00 62	88.78 31	96.04 18	94.58 51
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP		85.89 66	85.39 79	87.38 44	93.59 51	72.63 34	92.74 26	93.18 47	76.78 82	80.73 182	93.82 74	64.33 178	96.29 49	82.67 103	90.69 122	93.23 134
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
DeepC-MVS_fast	79.65 3	86.91 41	86.62 51	87.76 29	93.52 52	72.37 44	91.26 60	93.04 49	76.62 88	84.22 106	93.36 87	71.44 72	96.76 31	80.82 118	95.33 37	94.16 76
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CDPH-MVS		85.76 69	85.29 84	87.17 49	93.49 53	71.08 73	88.58 150	92.42 89	68.32 326	84.61 96	93.48 81	72.32 57	96.15 56	79.00 149	95.43 34	94.28 72

DP-MVS		76.78 299	74.57 320	83.42 199	93.29 54	69.46 107	88.55 152	83.70 369	63.98 391	70.20 379	88.89 239	54.01 307	94.80 116	46.66 462	81.88 298	86.01 408

CPTT-MVS		83.73 114	83.33 123	84.92 115	93.28 55	70.86 81	92.09 42	90.38 182	68.75 318	79.57 202	92.83 100	60.60 246	93.04 220	80.92 117	91.56 106	90.86 241

reproduce-ours		87.47 27	87.61 28	87.07 51	93.27 56	71.60 57	91.56 55	93.19 43	74.98 144	88.96 33	95.54 16	71.20 76	96.54 43	86.28 57	93.49 72	93.06 150

our_new_method		87.47 27	87.61 28	87.07 51	93.27 56	71.60 57	91.56 55	93.19 43	74.98 144	88.96 33	95.54 16	71.20 76	96.54 43	86.28 57	93.49 72	93.06 150

NormalMVS		86.29 54	85.88 68	87.52 41	93.26 58	72.47 39	91.65 48	92.19 110	79.31 25	84.39 101	92.18 118	64.64 175	95.53 74	80.70 121	94.65 53	94.56 55

lecture		88.09 17	88.59 17	86.58 63	93.26 58	69.77 99	93.70 7	94.16 8	77.13 70	89.76 29	95.52 18	72.26 58	96.27 51	86.87 53	94.65 53	93.70 106

TEST9					93.26 58	72.96 26	88.75 140	91.89 124	68.44 324	85.00 84	93.10 91	74.36 35	95.41 83

train_agg		86.43 49	86.20 58	87.13 50	93.26 58	72.96 26	88.75 140	91.89 124	68.69 319	85.00 84	93.10 91	74.43 33	95.41 83	84.97 66	95.71 29	93.02 154

test_8					93.13 62	72.57 36	88.68 146	91.84 128	68.69 319	84.87 88	93.10 91	74.43 33	95.16 93

新几何1				83.42 199	93.13 62	70.71 83		85.48 343	57.43 459	81.80 157	91.98 125	63.28 187	92.27 255	64.60 313	92.99 78	87.27 376

reproduce_model		87.28 35	87.39 34	86.95 55	93.10 64	71.24 72	91.60 51	93.19 43	74.69 154	88.80 37	95.61 15	70.29 87	96.44 46	86.20 59	93.08 76	93.16 142

AdaColmap		80.58 203	79.42 211	84.06 170	93.09 65	68.91 118	89.36 112	88.97 250	69.27 300	75.70 292	89.69 209	57.20 277	95.77 67	63.06 327	88.41 169	87.50 366

SR-MVS-dyc-post		85.77 68	85.61 75	86.23 68	93.06 66	70.63 85	91.88 44	92.27 98	73.53 191	85.69 77	94.45 39	65.00 172	95.56 71	82.75 98	91.87 99	92.50 178

RE-MVS-def			85.48 78		93.06 66	70.63 85	91.88 44	92.27 98	73.53 191	85.69 77	94.45 39	63.87 183		82.75 98	91.87 99	92.50 178

原ACMM1				84.35 144	93.01 68	68.79 120		92.44 86	63.96 392	81.09 171	91.57 145	66.06 158	95.45 78	67.19 291	94.82 51	88.81 328

CSCG		86.41 51	86.19 60	87.07 51	92.91 69	72.48 38	90.81 67	93.56 30	73.95 175	83.16 133	91.07 165	75.94 23	95.19 92	79.94 132	94.38 63	93.55 120

TestfortrainingZip				87.28 46	92.85 70	72.05 51	93.28 13	93.32 39	76.52 90	88.91 35	93.52 79	77.30 18	96.67 35		91.98 97	93.13 146

agg_prior					92.85 70	71.94 54		91.78 132		84.41 100			94.93 105

9.14			88.26 20		92.84 72		91.52 57	94.75 1	73.93 178	88.57 39	94.67 32	75.57 27	95.79 66	86.77 54	95.76 27

SF-MVS		88.46 15	88.74 16	87.64 39	92.78 73	71.95 53	92.40 30	94.74 2	75.71 118	89.16 32	95.10 22	75.65 26	96.19 54	87.07 52	96.01 19	94.79 28

MG-MVS		83.41 126	83.45 119	83.28 204	92.74 74	62.28 323	88.17 169	89.50 216	75.22 134	81.49 163	92.74 107	66.75 143	95.11 97	72.85 227	91.58 105	92.45 182

APD-MVS_3200maxsize		85.97 62	85.88 68	86.22 69	92.69 75	69.53 102	91.93 43	92.99 57	73.54 190	85.94 73	94.51 37	65.80 163	95.61 70	83.04 92	92.51 86	93.53 122

test12				86.80 59	92.63 76	70.70 84		91.79 131		82.71 144		71.67 69	96.16 55		94.50 58	93.54 121

test_prior				86.33 65	92.61 77	69.59 101		92.97 62					95.48 77			93.91 90

SD-MVS		88.06 18	88.50 19	86.71 61	92.60 78	72.71 30	91.81 47	93.19 43	77.87 44	90.32 26	94.00 65	74.83 29	93.78 164	87.63 47	94.27 66	93.65 112
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
PAPM_NR		83.02 139	82.41 141	84.82 120	92.47 79	66.37 198	87.93 179	91.80 130	73.82 180	77.32 253	90.66 179	67.90 130	94.90 108	70.37 256	89.48 146	93.19 140

DeepPCF-MVS	80.84 1	88.10 16	88.56 18	86.73 60	92.24 80	69.03 113	89.57 100	93.39 36	77.53 55	89.79 28	94.12 58	78.98 13	96.58 42	85.66 61	95.72 28	94.58 51

SteuartSystems-ACMMP		88.72 14	88.86 14	88.32 9	92.14 81	72.96 26	93.73 6	93.67 26	80.19 13	88.10 46	94.80 29	73.76 41	97.11 19	87.51 48	95.82 25	94.90 18
Skip Steuart: Steuart Systems R&D Blog.
UA-Net		85.08 87	84.96 88	85.45 91	92.07 82	68.07 148	89.78 92	90.86 168	82.48 2	84.60 97	93.20 90	69.35 103	95.22 91	71.39 245	90.88 120	93.07 149

旧先验1					91.96 83	65.79 215		86.37 330			93.08 95	69.31 105			92.74 83	88.74 333

MSLP-MVS++		85.43 77	85.76 72	84.45 137	91.93 84	70.24 88	90.71 68	92.86 66	77.46 57	84.22 106	92.81 102	67.16 138	92.94 222	80.36 125	94.35 64	90.16 272

LFMVS		81.82 162	81.23 163	83.57 194	91.89 85	63.43 294	89.84 88	81.85 402	77.04 74	83.21 129	93.10 91	52.26 322	93.43 193	71.98 240	89.95 137	93.85 94

PLC	70.83 11	78.05 270	76.37 292	83.08 218	91.88 86	67.80 160	88.19 168	89.46 217	64.33 385	69.87 388	88.38 254	53.66 309	93.58 173	58.86 381	82.73 286	87.86 355
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
dcpmvs_2		85.63 71	86.15 62	84.06 170	91.71 87	64.94 246	86.47 240	91.87 126	73.63 185	86.60 71	93.02 96	76.57 20	91.87 274	83.36 87	92.15 93	95.35 4

MVS_111021_HR		85.14 84	84.75 91	86.32 66	91.65 88	72.70 31	85.98 258	90.33 186	76.11 109	82.08 152	91.61 144	71.36 74	94.17 144	81.02 115	92.58 85	92.08 201

test222					91.50 89	68.26 140	84.16 318	83.20 381	54.63 471	79.74 199	91.63 141	58.97 258			91.42 107	86.77 393

SymmetryMVS		85.38 80	84.81 90	87.07 51	91.47 90	72.47 39	91.65 48	88.06 280	79.31 25	84.39 101	92.18 118	64.64 175	95.53 74	80.70 121	90.91 119	93.21 137

TSAR-MVS + GP.		85.71 70	85.33 81	86.84 57	91.34 91	72.50 37	89.07 126	87.28 302	76.41 97	85.80 75	90.22 197	74.15 39	95.37 88	81.82 107	91.88 98	92.65 171

MAR-MVS		81.84 161	80.70 173	85.27 97	91.32 92	71.53 60	89.82 89	90.92 164	69.77 289	78.50 223	86.21 320	62.36 208	94.52 128	65.36 306	92.05 96	89.77 296
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
BridgeMVS		86.78 42	86.99 41	86.15 72	91.24 93	67.61 166	90.51 71	92.90 64	77.26 64	87.44 60	91.63 141	71.27 75	96.06 57	85.62 63	95.01 41	94.78 29

DeepC-MVS	79.81 2	87.08 40	86.88 46	87.69 36	91.16 94	72.32 46	90.31 80	93.94 19	77.12 71	82.82 141	94.23 52	72.13 62	97.09 20	84.83 70	95.37 35	93.65 112
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MVSMamba_PlusPlus		85.99 60	85.96 67	86.05 75	91.09 95	67.64 165	89.63 98	92.65 79	72.89 211	84.64 95	91.71 136	71.85 64	96.03 58	84.77 72	94.45 61	94.49 59

3Dnovator+	77.84 4	85.48 75	84.47 96	88.51 7	91.08 96	73.49 17	93.18 17	93.78 24	80.79 8	76.66 270	93.37 86	60.40 250	96.75 32	77.20 172	93.73 71	95.29 7

Anonymous202405211		78.25 262	77.01 273	81.99 261	91.03 97	60.67 355	84.77 293	83.90 367	70.65 264	80.00 197	91.20 159	41.08 443	91.43 299	65.21 307	85.26 239	93.85 94

SPE-MVS-test		86.29 54	86.48 52	85.71 82	91.02 98	67.21 185	92.36 35	93.78 24	78.97 34	83.51 126	91.20 159	70.65 84	95.15 94	81.96 106	94.89 47	94.77 30

VDD-MVS		83.01 140	82.36 143	84.96 111	91.02 98	66.40 197	88.91 130	88.11 276	77.57 51	84.39 101	93.29 88	52.19 323	93.91 157	77.05 175	88.70 163	94.57 53

API-MVS		81.99 158	81.23 163	84.26 155	90.94 100	70.18 94	91.10 64	89.32 226	71.51 235	78.66 219	88.28 257	65.26 166	95.10 100	64.74 312	91.23 112	87.51 365

testdata				79.97 316	90.90 101	64.21 268		84.71 353	59.27 440	85.40 79	92.91 97	62.02 215	89.08 366	68.95 274	91.37 109	86.63 398

PHI-MVS		86.43 49	86.17 61	87.24 47	90.88 102	70.96 77	92.27 38	94.07 14	72.45 215	85.22 82	91.90 127	69.47 101	96.42 47	83.28 89	95.94 23	94.35 66

VNet		82.21 153	82.41 141	81.62 268	90.82 103	60.93 348	84.47 304	89.78 203	76.36 103	84.07 110	91.88 128	64.71 174	90.26 341	70.68 253	88.89 156	93.66 108

PVSNet_Blended_VisFu		82.62 145	81.83 157	84.96 111	90.80 104	69.76 100	88.74 142	91.70 137	69.39 296	78.96 212	88.46 252	65.47 165	94.87 112	74.42 209	88.57 164	90.24 270

MM		89.16 7	89.23 9	88.97 4	90.79 105	73.65 10	92.66 29	91.17 156	86.57 1	87.39 61	94.97 27	71.70 68	97.68 1	92.19 1	95.63 32	95.57 2

CS-MVS		86.69 44	86.95 43	85.90 80	90.76 106	67.57 168	92.83 23	93.30 40	79.67 20	84.57 98	92.27 112	71.47 71	95.02 104	84.24 80	93.46 74	95.13 11

Anonymous20240529		80.19 215	78.89 227	84.10 161	90.60 107	64.75 254	88.95 129	90.90 165	65.97 359	80.59 186	91.17 161	49.97 362	93.73 170	69.16 272	82.70 288	93.81 99

h-mvs33		83.15 134	82.19 147	86.02 78	90.56 108	70.85 82	88.15 171	89.16 238	76.02 111	84.67 92	91.39 152	61.54 223	95.50 76	82.71 100	75.48 384	91.72 212

Anonymous20231211		78.97 246	77.69 259	82.81 233	90.54 109	64.29 266	90.11 84	91.51 146	65.01 376	76.16 287	88.13 266	50.56 354	93.03 221	69.68 267	77.56 353	91.11 230

LS3D		76.95 297	74.82 317	83.37 202	90.45 110	67.36 177	89.15 122	86.94 316	61.87 419	69.52 391	90.61 183	51.71 338	94.53 127	46.38 465	86.71 208	88.21 348

VDDNet		81.52 172	80.67 174	84.05 173	90.44 111	64.13 270	89.73 94	85.91 337	71.11 244	83.18 132	93.48 81	50.54 355	93.49 186	73.40 220	88.25 174	94.54 57

testing3-2		75.12 330	75.19 313	74.91 406	90.40 112	45.09 493	80.29 394	78.42 444	78.37 41	76.54 275	87.75 271	44.36 420	87.28 394	57.04 400	83.49 274	92.37 184

CNLPA		78.08 268	76.79 280	81.97 262	90.40 112	71.07 74	87.59 189	84.55 356	66.03 357	72.38 357	89.64 212	57.56 271	86.04 406	59.61 372	83.35 277	88.79 329

PAPR		81.66 167	80.89 171	83.99 180	90.27 114	64.00 271	86.76 229	91.77 133	68.84 317	77.13 263	89.50 216	67.63 132	94.88 111	67.55 286	88.52 166	93.09 148

Vis-MVSNet		83.46 125	82.80 133	85.43 92	90.25 115	68.74 124	90.30 81	90.13 194	76.33 104	80.87 179	92.89 98	61.00 237	94.20 141	72.45 237	90.97 116	93.35 129
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
DPM-MVS		84.93 89	84.29 97	86.84 57	90.20 116	73.04 24	87.12 210	93.04 49	69.80 287	82.85 140	91.22 158	73.06 48	96.02 60	76.72 184	94.63 55	91.46 223

EPP-MVSNet		83.40 127	83.02 127	84.57 128	90.13 117	64.47 262	92.32 36	90.73 172	74.45 161	79.35 208	91.10 162	69.05 114	95.12 95	72.78 228	87.22 196	94.13 78

CANet		86.45 48	86.10 63	87.51 42	90.09 118	70.94 79	89.70 95	92.59 83	81.78 4	81.32 166	91.43 151	70.34 85	97.23 16	84.26 78	93.36 75	94.37 65

test2506		77.30 291	76.49 287	79.74 326	90.08 119	52.02 456	87.86 183	63.10 501	74.88 149	80.16 195	92.79 103	38.29 461	92.35 252	68.74 277	92.50 87	94.86 22

ECVR-MVS		79.61 224	79.26 218	80.67 296	90.08 119	54.69 437	87.89 181	77.44 452	74.88 149	80.27 192	92.79 103	48.96 380	92.45 246	68.55 278	92.50 87	94.86 22

HQP_MVS		83.64 118	83.14 124	85.14 101	90.08 119	68.71 126	91.25 61	92.44 86	79.12 29	78.92 214	91.00 169	60.42 248	95.38 85	78.71 153	86.32 214	91.33 224

plane_prior7					90.08 119	68.51 134

patch_mono-2		83.65 117	84.54 93	80.99 288	90.06 123	65.83 212	84.21 315	88.74 263	71.60 233	85.01 83	92.44 110	74.51 32	83.50 432	82.15 105	92.15 93	93.64 114

test1111		79.43 231	79.18 221	80.15 311	89.99 124	53.31 450	87.33 205	77.05 456	75.04 142	80.23 194	92.77 106	48.97 379	92.33 254	68.87 275	92.40 89	94.81 27

CHOSEN 1792x2688		77.63 285	75.69 298	83.44 198	89.98 125	68.58 132	78.70 418	87.50 297	56.38 464	75.80 291	86.84 296	58.67 261	91.40 300	61.58 354	85.75 232	90.34 265

IS-MVSNet		83.15 134	82.81 132	84.18 159	89.94 126	63.30 296	91.59 52	88.46 273	79.04 31	79.49 203	92.16 120	65.10 169	94.28 135	67.71 284	91.86 101	94.95 15

plane_prior1					89.90 127

sasdasda		85.91 64	85.87 70	86.04 76	89.84 128	69.44 108	90.45 77	93.00 54	76.70 86	88.01 49	91.23 155	73.28 44	93.91 157	81.50 109	88.80 159	94.77 30

canonicalmvs		85.91 64	85.87 70	86.04 76	89.84 128	69.44 108	90.45 77	93.00 54	76.70 86	88.01 49	91.23 155	73.28 44	93.91 157	81.50 109	88.80 159	94.77 30

plane_prior6					89.84 128	68.70 128						60.42 248

balanced_ft_v1		83.98 106	83.64 115	85.03 107	89.76 131	65.86 211	88.31 164	91.71 136	74.41 162	80.41 191	90.82 174	62.90 200	94.90 108	83.04 92	91.37 109	94.32 69

mvsmamba		80.60 200	79.38 213	84.27 153	89.74 132	67.24 183	87.47 192	86.95 315	70.02 280	75.38 302	88.93 236	51.24 345	92.56 239	75.47 200	89.22 151	93.00 157

NP-MVS					89.62 133	68.32 138					90.24 195

EIA-MVS		83.31 132	82.80 133	84.82 120	89.59 134	65.59 220	88.21 167	92.68 75	74.66 156	78.96 212	86.42 315	69.06 113	95.26 90	75.54 198	90.09 133	93.62 115

HyFIR lowres test		77.53 286	75.40 306	83.94 183	89.59 134	66.62 194	80.36 392	88.64 270	56.29 465	76.45 276	85.17 346	57.64 270	93.28 197	61.34 358	83.10 282	91.91 204

TAPA-MVS	73.13 9	79.15 240	77.94 246	82.79 237	89.59 134	62.99 307	88.16 170	91.51 146	65.77 360	77.14 262	91.09 164	60.91 238	93.21 204	50.26 443	87.05 200	92.17 198
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
thres100view900		76.50 303	75.55 303	79.33 338	89.52 137	56.99 404	85.83 266	83.23 378	73.94 177	76.32 280	87.12 292	51.89 334	91.95 268	48.33 453	83.75 266	89.07 311

GeoE		81.71 164	81.01 169	83.80 188	89.51 138	64.45 263	88.97 128	88.73 265	71.27 241	78.63 220	89.76 208	66.32 151	93.20 207	69.89 264	86.02 224	93.74 104

alignmvs		85.48 75	85.32 82	85.96 79	89.51 138	69.47 105	89.74 93	92.47 85	76.17 108	87.73 56	91.46 150	70.32 86	93.78 164	81.51 108	88.95 155	94.63 48

PS-MVSNAJ		81.69 165	81.02 168	83.70 189	89.51 138	68.21 145	84.28 314	90.09 195	70.79 256	81.26 170	85.62 334	63.15 193	94.29 134	75.62 196	88.87 157	88.59 337

fmvsm_s_conf0.5_n_9		87.39 33	87.95 24	85.70 83	89.48 141	67.88 157	88.59 149	89.05 244	80.19 13	90.70 22	95.40 19	74.56 31	93.92 156	91.54 2	92.07 95	95.31 6

MGCNet		87.69 24	87.55 30	88.12 13	89.45 142	71.76 55	91.47 58	89.54 214	82.14 3	86.65 70	94.28 48	68.28 126	97.46 6	90.81 6	95.31 38	95.15 9

MGCFI-Net		85.06 88	85.51 77	83.70 189	89.42 143	63.01 303	89.43 106	92.62 82	76.43 96	87.53 57	91.34 153	72.82 54	93.42 194	81.28 113	88.74 162	94.66 45

ACMP	74.13 6	81.51 174	80.57 177	84.36 143	89.42 143	68.69 129	89.97 86	91.50 149	74.46 160	75.04 318	90.41 188	53.82 308	94.54 126	77.56 168	82.91 283	89.86 292
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
thres600view7		76.50 303	75.44 304	79.68 329	89.40 145	57.16 401	85.53 275	83.23 378	73.79 181	76.26 281	87.09 293	51.89 334	91.89 272	48.05 458	83.72 269	90.00 284

ETV-MVS		84.90 91	84.67 92	85.59 88	89.39 146	68.66 130	88.74 142	92.64 81	79.97 17	84.10 109	85.71 329	69.32 104	95.38 85	80.82 118	91.37 109	92.72 166

BH-RMVSNet		79.61 224	78.44 235	83.14 213	89.38 147	65.93 208	84.95 290	87.15 310	73.56 188	78.19 232	89.79 207	56.67 282	93.36 195	59.53 373	86.74 207	90.13 274

HQP-NCC					89.33 148		89.17 118		76.41 97	77.23 256

ACMP_Plane					89.33 148		89.17 118		76.41 97	77.23 256

HQP-MVS		82.61 146	82.02 153	84.37 142	89.33 148	66.98 188	89.17 118	92.19 110	76.41 97	77.23 256	90.23 196	60.17 251	95.11 97	77.47 169	85.99 225	91.03 234

EC-MVSNet		86.01 59	86.38 53	84.91 116	89.31 151	66.27 200	92.32 36	93.63 27	79.37 24	84.17 108	91.88 128	69.04 115	95.43 80	83.93 84	93.77 70	93.01 156

ACMM	73.20 8	80.78 195	79.84 199	83.58 193	89.31 151	68.37 137	89.99 85	91.60 143	70.28 275	77.25 254	89.66 211	53.37 313	93.53 181	74.24 212	82.85 284	88.85 326
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Test_1112_low_res		76.40 310	75.44 304	79.27 339	89.28 153	58.09 383	81.69 368	87.07 313	59.53 438	72.48 355	86.67 305	61.30 230	89.33 359	60.81 362	80.15 320	90.41 262

F-COLMAP		76.38 311	74.33 326	82.50 247	89.28 153	66.95 191	88.41 157	89.03 245	64.05 389	66.83 428	88.61 247	46.78 394	92.89 224	57.48 394	78.55 337	87.67 358

SSM_0404		81.91 159	80.84 172	85.13 104	89.24 155	68.26 140	87.84 184	89.25 232	71.06 247	80.62 185	90.39 190	59.57 253	94.65 124	72.45 237	87.19 197	92.47 181

LPG-MVS_test		82.08 155	81.27 162	84.50 134	89.23 156	68.76 122	90.22 82	91.94 122	75.37 129	76.64 271	91.51 147	54.29 302	94.91 106	78.44 155	83.78 263	89.83 293

LGP-MVS_train				84.50 134	89.23 156	68.76 122		91.94 122	75.37 129	76.64 271	91.51 147	54.29 302	94.91 106	78.44 155	83.78 263	89.83 293

BH-untuned		79.47 229	78.60 231	82.05 259	89.19 158	65.91 209	86.07 257	88.52 272	72.18 221	75.42 300	87.69 274	61.15 234	93.54 180	60.38 364	86.83 206	86.70 395

xiu_mvs_v2_base		81.69 165	81.05 167	83.60 191	89.15 159	68.03 151	84.46 306	90.02 196	70.67 260	81.30 169	86.53 313	63.17 192	94.19 143	75.60 197	88.54 165	88.57 338

test_yl		81.17 178	80.47 181	83.24 207	89.13 160	63.62 281	86.21 253	89.95 199	72.43 218	81.78 158	89.61 213	57.50 272	93.58 173	70.75 251	86.90 203	92.52 176

DCV-MVSNet		81.17 178	80.47 181	83.24 207	89.13 160	63.62 281	86.21 253	89.95 199	72.43 218	81.78 158	89.61 213	57.50 272	93.58 173	70.75 251	86.90 203	92.52 176

tfpn200view9		76.42 309	75.37 308	79.55 335	89.13 160	57.65 395	85.17 281	83.60 370	73.41 195	76.45 276	86.39 316	52.12 324	91.95 268	48.33 453	83.75 266	89.07 311

thres400		76.50 303	75.37 308	79.86 319	89.13 160	57.65 395	85.17 281	83.60 370	73.41 195	76.45 276	86.39 316	52.12 324	91.95 268	48.33 453	83.75 266	90.00 284

1112_ss		77.40 289	76.43 289	80.32 305	89.11 164	60.41 361	83.65 328	87.72 293	62.13 416	73.05 346	86.72 300	62.58 204	89.97 348	62.11 346	80.80 311	90.59 254

SDMVSNet		80.38 207	80.18 188	80.99 288	89.03 165	64.94 246	80.45 391	89.40 219	75.19 138	76.61 273	89.98 199	60.61 245	87.69 389	76.83 180	83.55 272	90.33 266

sd_testset		77.70 281	77.40 266	78.60 351	89.03 165	60.02 365	79.00 413	85.83 339	75.19 138	76.61 273	89.98 199	54.81 294	85.46 414	62.63 336	83.55 272	90.33 266

testing915		80.13 216	80.30 185	79.64 331	89.00 167	58.38 379	87.08 212	84.16 364	74.04 173	80.14 196	89.37 226	64.04 181	90.08 345	66.04 301	88.82 158	90.45 260

Fast-Effi-MVS+		80.81 188	79.92 195	83.47 195	88.85 168	64.51 259	85.53 275	89.39 220	70.79 256	78.49 224	85.06 349	67.54 133	93.58 173	67.03 294	86.58 209	92.32 187

PVSNet_BlendedMVS		80.60 200	80.02 193	82.36 252	88.85 168	65.40 224	86.16 255	92.00 118	69.34 298	78.11 234	86.09 324	66.02 159	94.27 136	71.52 242	82.06 294	87.39 368

PVSNet_Blended		80.98 183	80.34 183	82.90 228	88.85 168	65.40 224	84.43 309	92.00 118	67.62 332	78.11 234	85.05 350	66.02 159	94.27 136	71.52 242	89.50 145	89.01 318

MVS_111021_LR		82.61 146	82.11 148	84.11 160	88.82 171	71.58 59	85.15 283	86.16 334	74.69 154	80.47 190	91.04 166	62.29 209	90.55 336	80.33 127	90.08 134	90.20 271

mamba_0408		79.37 236	77.52 263	84.93 114	88.81 172	67.96 153	65.03 497	88.66 267	70.96 251	79.48 204	89.80 205	58.69 259	94.65 124	70.35 257	85.93 227	92.18 195

SSM_04072		77.67 283	77.52 263	78.12 363	88.81 172	67.96 153	65.03 497	88.66 267	70.96 251	79.48 204	89.80 205	58.69 259	74.23 490	70.35 257	85.93 227	92.18 195

SSM_0407		81.58 169	80.48 180	84.87 118	88.81 172	67.96 153	87.37 202	89.25 232	71.06 247	79.48 204	90.39 190	59.57 253	94.48 131	72.45 237	85.93 227	92.18 195

BH-w/o		78.21 264	77.33 269	80.84 292	88.81 172	65.13 236	84.87 291	87.85 289	69.75 290	74.52 328	84.74 356	61.34 229	93.11 214	58.24 389	85.84 230	84.27 437

FIs		82.07 156	82.42 140	81.04 287	88.80 176	58.34 381	88.26 166	93.49 32	76.93 77	78.47 226	91.04 166	69.92 95	92.34 253	69.87 265	84.97 241	92.44 183

OPM-MVS		83.50 124	82.95 130	85.14 101	88.79 177	70.95 78	89.13 123	91.52 145	77.55 54	80.96 176	91.75 134	60.71 240	94.50 129	79.67 140	86.51 211	89.97 288
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
WR-MVS		79.49 228	79.22 220	80.27 306	88.79 177	58.35 380	85.06 287	88.61 271	78.56 36	77.65 245	88.34 255	63.81 185	90.66 335	64.98 310	77.22 355	91.80 207

FBQ-MVS		77.66 284	76.04 295	82.50 247	88.78 179	63.76 280	86.60 235	84.86 351	70.85 253	77.63 246	82.83 400	47.83 385	92.10 261	60.18 367	84.82 245	91.65 213

OMC-MVS		82.69 144	81.97 155	84.85 119	88.75 180	67.42 173	87.98 175	90.87 167	74.92 147	79.72 200	91.65 139	62.19 212	93.96 149	75.26 202	86.42 212	93.16 142

hse-mvs2		81.72 163	80.94 170	84.07 167	88.72 181	67.68 164	85.87 263	87.26 307	76.02 111	84.67 92	88.22 260	61.54 223	93.48 189	82.71 100	73.44 412	91.06 232

AUN-MVS		79.21 239	77.60 261	84.05 173	88.71 182	67.61 166	85.84 265	87.26 307	69.08 308	77.23 256	88.14 265	53.20 315	93.47 190	75.50 199	73.45 411	91.06 232

ACMH	67.68 16	75.89 317	73.93 330	81.77 266	88.71 182	66.61 195	88.62 148	89.01 247	69.81 286	66.78 429	86.70 304	41.95 438	91.51 294	55.64 410	78.14 346	87.17 380
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Vis-MVSNet (Re-imp)		78.36 261	78.45 234	78.07 365	88.64 184	51.78 462	86.70 230	79.63 434	74.14 171	75.11 315	90.83 173	61.29 231	89.75 352	58.10 390	91.60 103	92.69 169

PatchMatch-RL		72.38 370	70.90 372	76.80 387	88.60 185	67.38 176	79.53 404	76.17 463	62.75 407	69.36 393	82.00 414	45.51 412	84.89 420	53.62 422	80.58 314	78.12 480

ACMH+	68.96 14	76.01 316	74.01 328	82.03 260	88.60 185	65.31 232	88.86 132	87.55 295	70.25 277	67.75 414	87.47 282	41.27 441	93.19 209	58.37 387	75.94 377	87.60 360

LTVRE_ROB	69.57 13	76.25 312	74.54 322	81.41 274	88.60 185	64.38 265	79.24 408	89.12 243	70.76 258	69.79 390	87.86 270	49.09 377	93.20 207	56.21 409	80.16 319	86.65 397
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
DELS-MVS		85.41 78	85.30 83	85.77 81	88.49 188	67.93 156	85.52 277	93.44 33	78.70 35	83.63 121	89.03 231	74.57 30	95.71 69	80.26 129	94.04 68	93.66 108
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
CLD-MVS		82.31 151	81.65 159	84.29 150	88.47 189	67.73 162	85.81 267	92.35 92	75.78 116	78.33 229	86.58 310	64.01 182	94.35 133	76.05 190	87.48 192	90.79 243
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_NR-MVSNet		81.88 160	81.54 160	82.92 227	88.46 190	63.46 292	87.13 209	92.37 91	80.19 13	78.38 227	89.14 227	71.66 70	93.05 218	70.05 261	76.46 367	92.25 190

ab-mvs		79.51 227	78.97 225	81.14 284	88.46 190	60.91 349	83.84 323	89.24 234	70.36 271	79.03 211	88.87 240	63.23 191	90.21 343	65.12 308	82.57 289	92.28 189

testing91		76.54 301	75.66 301	79.18 342	88.43 192	55.89 422	81.08 378	83.00 385	73.76 182	75.34 304	84.29 364	46.20 404	90.07 346	64.33 314	84.50 250	91.58 216

FC-MVSNet-test		81.52 172	82.02 153	80.03 313	88.42 193	55.97 421	87.95 177	93.42 35	77.10 72	77.38 251	90.98 171	69.96 94	91.79 275	68.46 280	84.50 250	92.33 186

Effi-MVS+		83.62 120	83.08 125	85.24 98	88.38 194	67.45 172	88.89 131	89.15 240	75.50 124	82.27 148	88.28 257	69.61 100	94.45 132	77.81 164	87.84 184	93.84 97

UniMVSNet (Re)		81.60 168	81.11 166	83.09 216	88.38 194	64.41 264	87.60 188	93.02 53	78.42 38	78.56 222	88.16 261	69.78 97	93.26 200	69.58 268	76.49 366	91.60 214

VPNet		78.69 253	78.66 230	78.76 348	88.31 196	55.72 425	84.45 307	86.63 325	76.79 81	78.26 230	90.55 185	59.30 256	89.70 354	66.63 295	77.05 357	90.88 240

FA-MVS(test-final)		80.96 184	79.91 196	84.10 161	88.30 197	65.01 240	84.55 303	90.01 197	73.25 201	79.61 201	87.57 277	58.35 264	94.72 120	71.29 246	86.25 217	92.56 173

TR-MVS		77.44 287	76.18 293	81.20 282	88.24 198	63.24 297	84.61 301	86.40 329	67.55 333	77.81 242	86.48 314	54.10 304	93.15 211	57.75 393	82.72 287	87.20 378

PRO-TEST		83.03 138	82.63 137	84.23 157	88.20 199	66.81 193	87.41 201	90.93 163	73.55 189	80.73 182	88.90 237	66.17 155	92.85 226	78.39 158	89.36 148	93.02 154

myMVS_eth3d28		73.62 345	73.53 336	73.90 420	88.20 199	47.41 483	78.06 428	79.37 436	74.29 167	73.98 334	84.29 364	44.67 416	83.54 431	51.47 433	87.39 193	90.74 247

EI-MVSNet-Vis-set		84.19 99	83.81 109	85.31 96	88.18 201	67.85 158	87.66 187	89.73 208	80.05 16	82.95 136	89.59 215	70.74 82	94.82 113	80.66 123	84.72 247	93.28 132

Casviewmamba		86.09 56	86.04 65	86.24 67	88.17 202	68.05 150	89.44 105	92.79 72	80.30 10	84.71 90	92.78 105	72.83 53	95.05 102	82.81 96	90.57 124	95.62 1

testing11		75.14 329	74.01 328	78.53 355	88.16 203	56.38 415	80.74 385	80.42 422	70.67 260	72.69 353	83.72 381	43.61 426	89.86 349	62.29 342	83.76 265	89.36 307

testing99		76.09 315	75.12 315	79.00 343	88.16 203	55.50 428	80.79 382	81.40 407	73.30 199	75.17 312	84.27 367	44.48 419	90.02 347	64.28 315	84.22 259	91.48 221

GDP-MVS		83.52 123	82.64 136	86.16 71	88.14 205	68.45 135	89.13 123	92.69 74	72.82 212	83.71 117	91.86 130	55.69 289	95.35 89	80.03 130	89.74 141	94.69 37

baseline1		76.98 296	76.75 283	77.66 373	88.13 206	55.66 426	85.12 284	81.89 400	73.04 207	76.79 266	88.90 237	62.43 207	87.78 388	63.30 322	71.18 428	89.55 302

test_0402		72.79 368	70.44 380	79.84 320	88.13 206	65.99 207	85.93 260	84.29 360	65.57 363	67.40 422	85.49 337	46.92 391	92.61 235	35.88 495	74.38 402	80.94 469

tttt0517		79.40 233	77.91 247	83.90 184	88.10 208	63.84 276	88.37 161	84.05 365	71.45 236	76.78 267	89.12 228	49.93 365	94.89 110	70.18 260	83.18 281	92.96 159

FE-MVS		77.78 277	75.68 299	84.08 166	88.09 209	66.00 206	83.13 345	87.79 290	68.42 325	78.01 237	85.23 344	45.50 413	95.12 95	59.11 378	85.83 231	91.11 230

VPA-MVSNet		80.60 200	80.55 178	80.76 294	88.07 210	60.80 351	86.86 223	91.58 144	75.67 121	80.24 193	89.45 222	63.34 186	90.25 342	70.51 255	79.22 334	91.23 227

UGNet		80.83 187	79.59 208	84.54 129	88.04 211	68.09 147	89.42 108	88.16 275	76.95 76	76.22 282	89.46 220	49.30 374	93.94 152	68.48 279	90.31 128	91.60 214
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
UBG		73.08 361	72.27 352	75.51 398	88.02 212	51.29 467	78.35 425	77.38 453	65.52 364	73.87 336	82.36 406	45.55 411	86.48 401	55.02 414	84.39 256	88.75 331

WR-MVS_H		78.51 258	78.49 233	78.56 353	88.02 212	56.38 415	88.43 155	92.67 76	77.14 69	73.89 335	87.55 279	66.25 152	89.24 362	58.92 380	73.55 410	90.06 282

QAPM		80.88 185	79.50 210	85.03 107	88.01 214	68.97 117	91.59 52	92.00 118	66.63 349	75.15 314	92.16 120	57.70 269	95.45 78	63.52 318	88.76 161	90.66 250

RRT-MVS		82.60 148	82.10 150	84.10 161	87.98 215	62.94 310	87.45 195	91.27 152	77.42 58	79.85 198	90.28 193	56.62 283	94.70 122	79.87 137	88.15 176	94.67 42

3Dnovator	76.31 5	83.38 128	82.31 144	86.59 62	87.94 216	72.94 29	90.64 69	92.14 115	77.21 67	75.47 296	92.83 100	58.56 262	94.72 120	73.24 223	92.71 84	92.13 200

WBMVS		73.43 348	72.81 345	75.28 402	87.91 217	50.99 469	78.59 421	81.31 409	65.51 366	74.47 329	84.83 353	46.39 398	86.68 398	58.41 386	77.86 347	88.17 349

testing222		74.04 340	72.66 347	78.19 361	87.89 218	55.36 429	81.06 379	79.20 439	71.30 240	74.65 326	83.57 386	39.11 456	88.67 375	51.43 435	85.75 232	90.53 256

EI-MVSNet-UG-set		83.81 109	83.38 121	85.09 106	87.87 219	67.53 170	87.44 200	89.66 209	79.74 19	82.23 149	89.41 224	70.24 88	94.74 119	79.95 131	83.92 262	92.99 158

TranMVSNet+NR-MVSNet		80.84 186	80.31 184	82.42 249	87.85 220	62.33 321	87.74 186	91.33 151	80.55 9	77.99 238	89.86 201	65.23 167	92.62 234	67.05 293	75.24 394	92.30 188

BP-MVS1		84.32 94	83.71 112	86.17 70	87.84 221	67.85 158	89.38 111	89.64 211	77.73 47	83.98 112	92.12 123	56.89 280	95.43 80	84.03 83	91.75 102	95.24 8

CP-MVSNet		78.22 263	78.34 238	77.84 369	87.83 222	54.54 439	87.94 178	91.17 156	77.65 48	73.48 341	88.49 251	62.24 211	88.43 379	62.19 343	74.07 403	90.55 255

DU-MVS		81.12 181	80.52 179	82.90 228	87.80 223	63.46 292	87.02 215	91.87 126	79.01 32	78.38 227	89.07 229	65.02 170	93.05 218	70.05 261	76.46 367	92.20 193

NR-MVSNet		80.23 213	79.38 213	82.78 238	87.80 223	63.34 295	86.31 248	91.09 160	79.01 32	72.17 360	89.07 229	67.20 137	92.81 231	66.08 300	75.65 380	92.20 193

TAMVS		78.89 249	77.51 265	83.03 221	87.80 223	67.79 161	84.72 294	85.05 349	67.63 331	76.75 268	87.70 273	62.25 210	90.82 327	58.53 385	87.13 199	90.49 258

fmvsm_s_conf0.5_n_11		86.06 57	86.75 48	84.00 178	87.78 226	66.09 202	89.96 87	90.80 170	77.37 59	86.72 69	94.20 54	72.51 56	92.78 232	89.08 22	92.33 90	93.13 146

thres200		75.55 321	74.47 323	78.82 347	87.78 226	57.85 390	83.07 349	83.51 373	72.44 217	75.84 290	84.42 359	52.08 327	91.75 277	47.41 460	83.64 271	86.86 390

ETVMVS		72.25 374	71.05 369	75.84 392	87.77 228	51.91 459	79.39 406	74.98 466	69.26 301	73.71 337	82.95 396	40.82 445	86.14 404	46.17 466	84.43 255	89.47 303

E3new		83.78 112	83.60 116	84.31 147	87.76 229	64.89 251	86.24 252	92.20 108	75.15 141	82.87 138	91.23 155	70.11 90	93.52 183	79.05 145	87.79 185	94.51 58

viewcassd2359sk11		83.89 107	83.74 111	84.34 145	87.76 229	64.91 250	86.30 249	92.22 105	75.47 125	83.04 135	91.52 146	70.15 89	93.53 181	79.26 144	87.96 182	94.57 53

fmvsm_s_conf0.5_n_8		86.56 47	87.17 39	84.73 125	87.76 229	65.62 219	89.20 116	92.21 107	79.94 18	89.74 30	94.86 28	68.63 120	94.20 141	90.83 5	91.39 108	94.38 64

PS-CasMVS		78.01 272	78.09 243	77.77 371	87.71 232	54.39 441	88.02 174	91.22 153	77.50 56	73.26 343	88.64 246	60.73 239	88.41 380	61.88 349	73.88 407	90.53 256

PCF-MVS	73.52 7	80.38 207	78.84 228	85.01 109	87.71 232	68.99 116	83.65 328	91.46 150	63.00 401	77.77 244	90.28 193	66.10 156	95.09 101	61.40 356	88.22 175	90.94 239
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
E2		84.00 104	83.87 106	84.39 140	87.70 234	64.95 243	86.40 245	92.23 102	75.85 114	83.21 129	91.78 132	70.09 91	93.55 178	79.52 142	88.05 179	94.66 45

E3		84.00 104	83.87 106	84.39 140	87.70 234	64.95 243	86.40 245	92.23 102	75.85 114	83.21 129	91.78 132	70.09 91	93.55 178	79.52 142	88.05 179	94.66 45

thisisatest0530		79.40 233	77.76 256	84.31 147	87.69 236	65.10 239	87.36 203	84.26 362	70.04 279	77.42 250	88.26 259	49.94 363	94.79 117	70.20 259	84.70 248	93.03 153

casdiffmvs_mvg		85.99 60	86.09 64	85.70 83	87.65 237	67.22 184	88.69 145	93.04 49	79.64 22	85.33 80	92.54 108	73.30 43	94.50 129	83.49 86	91.14 113	95.37 3
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt09		83.34 129	82.55 139	85.70 83	87.64 238	67.72 163	88.43 155	91.68 138	71.91 227	81.65 161	90.68 178	67.10 140	94.75 118	76.17 187	87.70 188	94.62 50

E5new		84.22 95	84.12 99	84.51 132	87.60 239	65.36 228	87.45 195	92.31 94	76.51 91	83.53 122	92.26 113	69.25 108	93.50 184	79.88 133	88.26 170	94.69 37

E6new		84.22 95	84.12 99	84.52 130	87.60 239	65.36 228	87.45 195	92.30 96	76.51 91	83.53 122	92.26 113	69.26 106	93.49 186	79.88 133	88.26 170	94.69 37

E6		84.22 95	84.12 99	84.52 130	87.60 239	65.36 228	87.45 195	92.30 96	76.51 91	83.53 122	92.26 113	69.26 106	93.49 186	79.88 133	88.26 170	94.69 37

E5		84.22 95	84.12 99	84.51 132	87.60 239	65.36 228	87.45 195	92.31 94	76.51 91	83.53 122	92.26 113	69.25 108	93.50 184	79.88 133	88.26 170	94.69 37

GBi-Net		78.40 259	77.40 266	81.40 275	87.60 239	63.01 303	88.39 158	89.28 228	71.63 230	75.34 304	87.28 284	54.80 295	91.11 310	62.72 332	79.57 325	90.09 278

test1		78.40 259	77.40 266	81.40 275	87.60 239	63.01 303	88.39 158	89.28 228	71.63 230	75.34 304	87.28 284	54.80 295	91.11 310	62.72 332	79.57 325	90.09 278

FMVSNet2		78.20 265	77.21 270	81.20 282	87.60 239	62.89 311	87.47 192	89.02 246	71.63 230	75.29 310	87.28 284	54.80 295	91.10 313	62.38 340	79.38 331	89.61 300

CDS-MVSNet		79.07 243	77.70 258	83.17 212	87.60 239	68.23 144	84.40 312	86.20 333	67.49 334	76.36 279	86.54 312	61.54 223	90.79 328	61.86 350	87.33 194	90.49 258
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
E4		84.10 101	83.99 105	84.45 137	87.58 247	64.99 242	86.54 238	92.25 101	76.38 101	83.37 127	92.09 124	69.88 96	93.58 173	79.78 138	88.03 181	94.77 30

HY-MVS	69.67 12	77.95 273	77.15 271	80.36 303	87.57 248	60.21 364	83.37 340	87.78 291	66.11 354	75.37 303	87.06 295	63.27 188	90.48 337	61.38 357	82.43 290	90.40 263

hybridcas		85.11 85	85.18 85	84.90 117	87.47 249	65.68 217	88.53 153	92.38 90	77.91 43	84.27 105	92.48 109	72.19 60	93.88 161	80.37 124	90.97 116	95.15 9

xiu_mvs_v1_base_debu		80.80 191	79.72 204	84.03 175	87.35 250	70.19 91	85.56 270	88.77 257	69.06 309	81.83 154	88.16 261	50.91 348	92.85 226	78.29 160	87.56 189	89.06 313

xiu_mvs_v1_base		80.80 191	79.72 204	84.03 175	87.35 250	70.19 91	85.56 270	88.77 257	69.06 309	81.83 154	88.16 261	50.91 348	92.85 226	78.29 160	87.56 189	89.06 313

xiu_mvs_v1_base_debi		80.80 191	79.72 204	84.03 175	87.35 250	70.19 91	85.56 270	88.77 257	69.06 309	81.83 154	88.16 261	50.91 348	92.85 226	78.29 160	87.56 189	89.06 313

MVSFormer		82.85 142	82.05 152	85.24 98	87.35 250	70.21 89	90.50 73	90.38 182	68.55 321	81.32 166	89.47 218	61.68 220	93.46 191	78.98 150	90.26 130	92.05 202

lupinMVS		81.39 176	80.27 187	84.76 124	87.35 250	70.21 89	85.55 273	86.41 328	62.85 404	81.32 166	88.61 247	61.68 220	92.24 257	78.41 157	90.26 130	91.83 205

fmvsm_s_conf0.5_n_10		86.38 52	86.76 47	85.24 98	87.33 255	67.30 179	89.50 102	90.98 161	76.25 107	90.56 25	94.75 31	68.38 123	94.24 140	90.80 7	92.32 92	94.19 75

testing3		68.56 414	67.67 412	71.22 445	87.33 255	42.87 498	83.06 350	71.54 478	70.36 271	69.08 397	84.38 361	30.33 484	85.69 410	37.50 493	75.45 387	85.09 428

fmvsm_s_conf0.5_n_6		85.55 73	86.20 58	83.60 191	87.32 257	65.13 236	88.86 132	91.63 140	75.41 127	88.23 44	93.45 84	68.56 121	92.47 244	89.52 18	92.78 82	93.20 139

casdiffseed414692147		83.62 120	83.02 127	85.40 93	87.31 258	67.50 171	88.70 144	91.72 135	76.97 75	82.77 143	91.72 135	66.85 142	93.71 171	73.06 225	88.12 177	94.98 14

baseline		84.93 89	84.98 87	84.80 122	87.30 259	65.39 226	87.30 206	92.88 65	77.62 49	84.04 111	92.26 113	71.81 65	93.96 149	81.31 112	90.30 129	95.03 13

PAPM		77.68 282	76.40 291	81.51 271	87.29 260	61.85 330	83.78 324	89.59 213	64.74 378	71.23 371	88.70 243	62.59 203	93.66 172	52.66 427	87.03 201	89.01 318

fmvsm_l_conf0.5_n_3		86.02 58	86.32 55	85.14 101	87.20 261	68.54 133	89.57 100	90.44 180	75.31 131	87.49 58	94.39 44	72.86 51	92.72 233	89.04 27	90.56 125	94.16 76

LCM-MVSNet-Re		77.05 294	76.94 276	77.36 379	87.20 261	51.60 463	80.06 397	80.46 420	75.20 137	67.69 415	86.72 300	62.48 205	88.98 368	63.44 320	89.25 149	91.51 218

casdiffmvs		85.11 85	85.14 86	85.01 109	87.20 261	65.77 216	87.75 185	92.83 68	77.84 45	84.36 104	92.38 111	72.15 61	93.93 155	81.27 114	90.48 126	95.33 5
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
icg_test_0407_2		78.92 248	78.93 226	78.90 346	87.13 264	63.59 285	76.58 441	89.33 222	70.51 266	77.82 240	89.03 231	61.84 216	81.38 449	72.56 233	85.56 234	91.74 208

IMVS_0407		80.61 198	79.90 197	82.75 241	87.13 264	63.59 285	85.33 279	89.33 222	70.51 266	77.82 240	89.03 231	61.84 216	92.91 223	72.56 233	85.56 234	91.74 208

IMVS_0404		77.16 293	76.42 290	79.37 337	87.13 264	63.59 285	77.12 438	89.33 222	70.51 266	66.22 439	89.03 231	50.36 357	82.78 437	72.56 233	85.56 234	91.74 208

IMVS_0403		80.80 191	80.12 192	82.87 230	87.13 264	63.59 285	85.19 280	89.33 222	70.51 266	78.49 224	89.03 231	63.26 189	93.27 199	72.56 233	85.56 234	91.74 208

COLMAP_ROB	66.92 17	73.01 362	70.41 381	80.81 293	87.13 264	65.63 218	88.30 165	84.19 363	62.96 402	63.80 459	87.69 274	38.04 462	92.56 239	46.66 462	74.91 397	84.24 438
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
fmvsm_l_conf0.5_n_9		85.84 67	86.63 50	83.46 196	87.12 269	66.01 205	88.56 151	89.43 218	75.59 122	89.32 31	94.32 46	72.89 50	91.21 309	90.11 11	92.33 90	93.16 142

KinetiMVS		83.31 132	82.61 138	85.39 94	87.08 270	67.56 169	88.06 173	91.65 139	77.80 46	82.21 150	91.79 131	57.27 275	94.07 147	77.77 165	89.89 139	94.56 55

fmvsm_s_conf0.5_n_3		86.36 53	87.46 33	83.09 216	87.08 270	65.21 233	89.09 125	90.21 191	79.67 20	89.98 27	95.02 26	73.17 46	91.71 280	91.30 3	91.60 103	92.34 185

PEN-MVS		77.73 278	77.69 259	77.84 369	87.07 272	53.91 444	87.91 180	91.18 155	77.56 53	73.14 345	88.82 241	61.23 232	89.17 364	59.95 368	72.37 418	90.43 261

viewdifsd2359ckpt13		82.91 141	82.29 145	84.77 123	86.96 273	66.90 192	87.47 192	91.62 141	72.19 220	81.68 160	90.71 177	66.92 141	93.28 197	75.90 192	87.15 198	94.12 79

MVS_Test		83.15 134	83.06 126	83.41 201	86.86 274	63.21 298	86.11 256	92.00 118	74.31 165	82.87 138	89.44 223	70.03 93	93.21 204	77.39 171	88.50 167	93.81 99

UniMVSNet_ETH3D		79.10 242	78.24 241	81.70 267	86.85 275	60.24 363	87.28 207	88.79 256	74.25 168	76.84 264	90.53 186	49.48 369	91.56 287	67.98 282	82.15 292	93.29 131

FMVSNet3		77.88 275	76.85 278	80.97 290	86.84 276	62.36 320	86.52 239	88.77 257	71.13 243	75.34 304	86.66 306	54.07 305	91.10 313	62.72 332	79.57 325	89.45 304

viewmanbaseed2359cas		83.66 116	83.55 117	84.00 178	86.81 277	64.53 257	86.65 232	91.75 134	74.89 148	83.15 134	91.68 137	68.74 119	92.83 230	79.02 147	89.24 150	94.63 48

FMVSNet1		77.44 287	76.12 294	81.40 275	86.81 277	63.01 303	88.39 158	89.28 228	70.49 270	74.39 330	87.28 284	49.06 378	91.11 310	60.91 360	78.52 338	90.09 278

nrg030		83.88 108	83.53 118	84.96 111	86.77 279	69.28 112	90.46 76	92.67 76	74.79 152	82.95 136	91.33 154	72.70 55	93.09 215	80.79 120	79.28 333	92.50 178

ET-MVSNet_ETH3D		78.63 254	76.63 286	84.64 127	86.73 280	69.47 105	85.01 288	84.61 355	69.54 294	66.51 436	86.59 308	50.16 359	91.75 277	76.26 186	84.24 258	92.69 169

fmvsm_s_conf0.5_n_4		85.39 79	85.75 73	84.30 149	86.70 281	65.83 212	88.77 138	89.78 203	75.46 126	88.35 40	93.73 76	69.19 110	93.06 217	91.30 3	88.44 168	94.02 85

fmvsm_s_conf0.5_n		83.80 110	83.71 112	84.07 167	86.69 282	67.31 178	89.46 104	83.07 383	71.09 245	86.96 67	93.70 77	69.02 116	91.47 297	88.79 30	84.62 249	93.44 125

UWE-MVS		72.13 376	71.49 359	74.03 418	86.66 283	47.70 480	81.40 374	76.89 458	63.60 395	75.59 293	84.22 368	39.94 449	85.62 411	48.98 450	86.13 220	88.77 330

jason		81.39 176	80.29 186	84.70 126	86.63 284	69.90 97	85.95 259	86.77 320	63.24 397	81.07 172	89.47 218	61.08 236	92.15 259	78.33 159	90.07 135	92.05 202
jason: jason.
viewmacassd2359aftdt		83.76 113	83.66 114	84.07 167	86.59 285	64.56 256	86.88 222	91.82 129	75.72 117	83.34 128	92.15 122	68.24 127	92.88 225	79.05 145	89.15 153	94.77 30

guyue		81.13 180	80.64 176	82.60 245	86.52 286	63.92 275	86.69 231	87.73 292	73.97 174	80.83 181	89.69 209	56.70 281	91.33 303	78.26 163	85.40 238	92.54 174

viewdifsd2359ckpt07		82.83 143	82.78 135	82.99 223	86.51 287	62.58 314	85.09 286	90.83 169	75.22 134	82.28 147	91.63 141	69.43 102	92.03 263	77.71 166	86.32 214	94.34 67

PS-MVSNAJss		82.07 156	81.31 161	84.34 145	86.51 287	67.27 181	89.27 114	91.51 146	71.75 228	79.37 207	90.22 197	63.15 193	94.27 136	77.69 167	82.36 291	91.49 220

fmvsm_l_mol_unc0.5_1		85.55 73	86.37 54	83.10 215	86.42 289	62.98 309	85.89 262	84.85 352	76.48 95	92.88 3	96.67 1	74.16 38	92.46 245	87.11 51	92.90 80	93.85 94

WTY-MVS		75.65 320	75.68 299	75.57 396	86.40 290	56.82 406	77.92 431	82.40 393	65.10 373	76.18 284	87.72 272	63.13 196	80.90 452	60.31 365	81.96 295	89.00 320

fmvsm_s_conf0.5_n_5		85.22 83	85.55 76	84.25 156	86.26 291	67.40 175	89.18 117	89.31 227	72.50 214	88.31 41	93.86 72	69.66 99	91.96 267	89.81 13	91.05 114	93.38 126

DTE-MVSNet		76.99 295	76.80 279	77.54 378	86.24 292	53.06 454	87.52 190	90.66 173	77.08 73	72.50 354	88.67 245	60.48 247	89.52 356	57.33 397	70.74 430	90.05 283

PVSNet	64.34 18	72.08 377	70.87 373	75.69 394	86.21 293	56.44 413	74.37 460	80.73 414	62.06 417	70.17 381	82.23 410	42.86 430	83.31 434	54.77 416	84.45 254	87.32 374

SD_0403		74.65 333	74.77 318	74.29 414	86.20 294	47.42 482	83.71 326	85.12 346	69.30 299	68.50 405	87.95 269	59.40 255	86.05 405	49.38 447	83.35 277	89.40 305

fmvsm_s_conf0.5_n_2		84.04 102	84.11 103	83.81 187	86.17 295	65.00 241	86.96 217	87.28 302	74.35 163	88.25 43	94.23 52	61.82 218	92.60 236	89.85 12	88.09 178	93.84 97

fmvsm_s_conf0.5_n_a		83.63 119	83.41 120	84.28 151	86.14 296	68.12 146	89.43 106	82.87 388	70.27 276	87.27 63	93.80 75	69.09 111	91.58 284	88.21 39	83.65 270	93.14 145

test_fmvsm_n_1920		85.29 82	85.34 80	85.13 104	86.12 297	69.93 95	88.65 147	90.78 171	69.97 283	88.27 42	93.98 68	71.39 73	91.54 291	88.49 36	90.45 127	93.91 90

tfpnnormal		74.39 334	73.16 341	78.08 364	86.10 298	58.05 384	84.65 298	87.53 296	70.32 274	71.22 372	85.63 333	54.97 293	89.86 349	43.03 479	75.02 396	86.32 400

AstraMVS		80.81 188	80.14 191	82.80 234	86.05 299	63.96 272	86.46 241	85.90 338	73.71 183	80.85 180	90.56 184	54.06 306	91.57 286	79.72 139	83.97 261	92.86 163

VortexMVS		78.57 257	77.89 249	80.59 297	85.89 300	62.76 312	85.61 268	89.62 212	72.06 224	74.99 319	85.38 340	55.94 288	90.77 331	74.99 203	76.58 364	88.23 346

IterMVS-LS		80.06 217	79.38 213	82.11 258	85.89 300	63.20 299	86.79 226	89.34 221	74.19 169	75.45 299	86.72 300	66.62 145	92.39 249	72.58 230	76.86 360	90.75 246
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Baseline_NR-MVSNet		78.15 267	78.33 239	77.61 375	85.79 302	56.21 419	86.78 227	85.76 340	73.60 187	77.93 239	87.57 277	65.02 170	88.99 367	67.14 292	75.33 391	87.63 359

cascas		76.72 300	74.64 319	82.99 223	85.78 303	65.88 210	82.33 357	89.21 235	60.85 425	72.74 350	81.02 421	47.28 388	93.75 168	67.48 287	85.02 240	89.34 308

fmvsm_s_conf0.5_n_7		83.34 129	84.03 104	81.28 279	85.73 304	65.13 236	85.40 278	89.90 201	74.96 146	82.13 151	93.89 71	66.65 144	87.92 385	86.56 56	91.05 114	90.80 242

MVS		78.19 266	76.99 275	81.78 265	85.66 305	66.99 187	84.66 296	90.47 179	55.08 470	72.02 363	85.27 342	63.83 184	94.11 146	66.10 299	89.80 140	84.24 438

XVG-OURS		80.41 205	79.23 219	83.97 181	85.64 306	69.02 115	83.03 351	90.39 181	71.09 245	77.63 246	91.49 149	54.62 301	91.35 301	75.71 194	83.47 275	91.54 217

fmvsm_s_conf0.1_n_2		83.80 110	83.79 110	83.83 185	85.62 307	64.94 246	87.03 214	86.62 326	74.32 164	87.97 51	94.33 45	60.67 242	92.60 236	89.72 14	87.79 185	93.96 87

CANet_DTU		80.61 198	79.87 198	82.83 231	85.60 308	63.17 301	87.36 203	88.65 269	76.37 102	75.88 289	88.44 253	53.51 311	93.07 216	73.30 221	89.74 141	92.25 190

XVG-OURS-SEG-HR		80.81 188	79.76 201	83.96 182	85.60 308	68.78 121	83.54 335	90.50 178	70.66 263	76.71 269	91.66 138	60.69 241	91.26 304	76.94 176	81.58 301	91.83 205

Elysia		81.53 170	80.16 189	85.62 86	85.51 310	68.25 142	88.84 135	92.19 110	71.31 238	80.50 188	89.83 203	46.89 392	94.82 113	76.85 177	89.57 143	93.80 101

StellarMVS		81.53 170	80.16 189	85.62 86	85.51 310	68.25 142	88.84 135	92.19 110	71.31 238	80.50 188	89.83 203	46.89 392	94.82 113	76.85 177	89.57 143	93.80 101

TransMVSNet (Re)		75.39 327	74.56 321	77.86 368	85.50 312	57.10 403	86.78 227	86.09 336	72.17 222	71.53 368	87.34 283	63.01 197	89.31 360	56.84 403	61.83 473	87.17 380

fmvsm_l_conf0.5_n		84.47 93	84.54 93	84.27 153	85.42 313	68.81 119	88.49 154	87.26 307	68.08 328	88.03 48	93.49 80	72.04 63	91.77 276	88.90 29	89.14 154	92.24 192

fmvsm_l_conf0.5_n_a		84.13 100	84.16 98	84.06 170	85.38 314	68.40 136	88.34 162	86.85 319	67.48 335	87.48 59	93.40 85	70.89 79	91.61 282	88.38 38	89.22 151	92.16 199

MVP-Stereo		76.12 313	74.46 324	81.13 285	85.37 315	69.79 98	84.42 311	87.95 285	65.03 375	67.46 419	85.33 341	53.28 314	91.73 279	58.01 391	83.27 279	81.85 464
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
tt0320-xc		70.11 397	67.45 416	78.07 365	85.33 316	59.51 372	83.28 341	78.96 441	58.77 445	67.10 425	80.28 431	36.73 467	87.42 392	56.83 404	59.77 481	87.29 375

SSC-MVS3.2		73.35 354	73.39 337	73.23 424	85.30 317	49.01 478	74.58 458	81.57 404	75.21 136	73.68 338	85.58 335	52.53 316	82.05 443	54.33 419	77.69 351	88.63 336

thisisatest0515		77.33 290	75.38 307	83.18 211	85.27 318	63.80 277	82.11 361	83.27 377	65.06 374	75.91 288	83.84 376	49.54 368	94.27 136	67.24 290	86.19 218	91.48 221

tt0805		78.73 251	77.83 251	81.43 273	85.17 319	60.30 362	89.41 109	90.90 165	71.21 242	77.17 261	88.73 242	46.38 399	93.21 204	72.57 231	78.96 335	90.79 243

OpenMVS	72.83 10	79.77 222	78.33 239	84.09 165	85.17 319	69.91 96	90.57 70	90.97 162	66.70 343	72.17 360	91.91 126	54.70 299	93.96 149	61.81 351	90.95 118	88.41 342

AllTest		70.96 384	68.09 401	79.58 333	85.15 321	63.62 281	84.58 302	79.83 430	62.31 413	60.32 473	86.73 298	32.02 478	88.96 370	50.28 441	71.57 426	86.15 404

TestCases				79.58 333	85.15 321	63.62 281		79.83 430	62.31 413	60.32 473	86.73 298	32.02 478	88.96 370	50.28 441	71.57 426	86.15 404

Effi-MVS+-dtu		80.03 219	78.57 232	84.42 139	85.13 323	68.74 124	88.77 138	88.10 277	74.99 143	74.97 320	83.49 387	57.27 275	93.36 195	73.53 217	80.88 309	91.18 228

SixPastTwentyTwo		73.37 351	71.26 366	79.70 328	85.08 324	57.89 389	85.57 269	83.56 372	71.03 249	65.66 442	85.88 326	42.10 436	92.57 238	59.11 378	63.34 467	88.65 335

LuminaMVS		80.68 196	79.62 207	83.83 185	85.07 325	68.01 152	86.99 216	88.83 254	70.36 271	81.38 165	87.99 268	50.11 360	92.51 243	79.02 147	86.89 205	90.97 237

test_fmvsmconf_n		85.92 63	86.04 65	85.57 89	85.03 326	69.51 103	89.62 99	90.58 175	73.42 194	87.75 54	94.02 63	72.85 52	93.24 201	90.37 8	90.75 121	93.96 87

EG-PatchMatch MVS		74.04 340	71.82 355	80.71 295	84.92 327	67.42 173	85.86 264	88.08 278	66.04 356	64.22 454	83.85 375	35.10 473	92.56 239	57.44 395	80.83 310	82.16 462

fmvsm_s_conf0.1_n		83.56 122	83.38 121	84.10 161	84.86 328	67.28 180	89.40 110	83.01 384	70.67 260	87.08 64	93.96 69	68.38 123	91.45 298	88.56 35	84.50 250	93.56 119

sc_t1		72.19 375	69.51 388	80.23 308	84.81 329	61.09 343	84.68 295	80.22 427	60.70 426	71.27 370	83.58 385	36.59 468	89.24 362	60.41 363	63.31 468	90.37 264

tt0320		70.49 393	68.03 402	77.89 367	84.78 330	59.12 374	83.55 333	80.44 421	58.13 451	67.43 421	80.41 429	39.26 454	87.54 391	55.12 412	63.18 469	86.99 387

IB-MVS	68.01 15	75.85 318	73.36 339	83.31 203	84.76 331	66.03 203	83.38 339	85.06 348	70.21 278	69.40 392	81.05 420	45.76 409	94.66 123	65.10 309	75.49 383	89.25 310
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
mvs_tets		79.13 241	77.77 255	83.22 209	84.70 332	66.37 198	89.17 118	90.19 192	69.38 297	75.40 301	89.46 220	44.17 422	93.15 211	76.78 183	80.70 313	90.14 273

Syy-MVS		68.05 419	67.85 406	68.67 459	84.68 333	40.97 504	78.62 419	73.08 475	66.65 347	66.74 430	79.46 440	52.11 326	82.30 441	32.89 498	76.38 372	82.75 456

myMVS_eth3d		67.02 426	66.29 427	69.21 454	84.68 333	42.58 499	78.62 419	73.08 475	66.65 347	66.74 430	79.46 440	31.53 481	82.30 441	39.43 489	76.38 372	82.75 456

jajsoiax		79.29 237	77.96 245	83.27 205	84.68 333	66.57 196	89.25 115	90.16 193	69.20 305	75.46 298	89.49 217	45.75 410	93.13 213	76.84 179	80.80 311	90.11 276

WB-MVSnew		71.96 378	71.65 358	72.89 430	84.67 336	51.88 460	82.29 358	77.57 449	62.31 413	73.67 339	83.00 395	53.49 312	81.10 451	45.75 470	82.13 293	85.70 415

MIMVSNet		70.69 389	69.30 389	74.88 407	84.52 337	56.35 417	75.87 447	79.42 435	64.59 379	67.76 413	82.41 405	41.10 442	81.54 446	46.64 464	81.34 302	86.75 394

MSDG		73.36 353	70.99 370	80.49 300	84.51 338	65.80 214	80.71 386	86.13 335	65.70 361	65.46 444	83.74 379	44.60 417	90.91 324	51.13 436	76.89 359	84.74 432

mvs_anonymous		79.42 232	79.11 222	80.34 304	84.45 339	57.97 387	82.59 353	87.62 294	67.40 337	76.17 286	88.56 250	68.47 122	89.59 355	70.65 254	86.05 223	93.47 124

EI-MVSNet		80.52 204	79.98 194	82.12 256	84.28 340	63.19 300	86.41 242	88.95 251	74.18 170	78.69 217	87.54 280	66.62 145	92.43 247	72.57 231	80.57 315	90.74 247

CVMVSNet		72.99 363	72.58 348	74.25 415	84.28 340	50.85 470	86.41 242	83.45 375	44.56 491	73.23 344	87.54 280	49.38 371	85.70 409	65.90 302	78.44 340	86.19 403

pm-mvs1		77.25 292	76.68 285	78.93 345	84.22 342	58.62 377	86.41 242	88.36 274	71.37 237	73.31 342	88.01 267	61.22 233	89.15 365	64.24 316	73.01 415	89.03 317

EPNet		83.72 115	82.92 131	86.14 74	84.22 342	69.48 104	91.05 65	85.27 344	81.30 6	76.83 265	91.65 139	66.09 157	95.56 71	76.00 191	93.85 69	93.38 126
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvsmvis_n_1920		84.02 103	83.87 106	84.49 136	84.12 344	69.37 111	88.15 171	87.96 284	70.01 281	83.95 113	93.23 89	68.80 118	91.51 294	88.61 32	89.96 136	92.57 172

v8		79.97 221	79.02 224	82.80 234	84.09 345	64.50 261	87.96 176	90.29 189	74.13 172	75.24 311	86.81 297	62.88 201	93.89 160	74.39 210	75.40 389	90.00 284

v10		79.74 223	78.67 229	82.97 226	84.06 346	64.95 243	87.88 182	90.62 174	73.11 205	75.11 315	86.56 311	61.46 226	94.05 148	73.68 215	75.55 382	89.90 290

SCA		74.22 337	72.33 351	79.91 317	84.05 347	62.17 324	79.96 400	79.29 438	66.30 352	72.38 357	80.13 433	51.95 330	88.60 376	59.25 376	77.67 352	88.96 322

test_djsdf		80.30 212	79.32 216	83.27 205	83.98 348	65.37 227	90.50 73	90.38 182	68.55 321	76.19 283	88.70 243	56.44 284	93.46 191	78.98 150	80.14 321	90.97 237

1314		76.53 302	75.30 312	80.21 309	83.93 349	62.32 322	84.66 296	88.81 255	60.23 430	70.16 382	84.07 373	55.30 292	90.73 334	67.37 288	83.21 280	87.59 362

reproduce_monomvs		75.40 326	74.38 325	78.46 358	83.92 350	57.80 392	83.78 324	86.94 316	73.47 193	72.25 359	84.47 358	38.74 457	89.27 361	75.32 201	70.53 431	88.31 343

MS-PatchMatch		73.83 343	72.67 346	77.30 381	83.87 351	66.02 204	81.82 363	84.66 354	61.37 423	68.61 401	82.82 401	47.29 387	88.21 381	59.27 375	84.32 257	77.68 481

fmvsm_s_conf0.1_n_a		83.32 131	82.99 129	84.28 151	83.79 352	68.07 148	89.34 113	82.85 389	69.80 287	87.36 62	94.06 61	68.34 125	91.56 287	87.95 44	83.46 276	93.21 137

v1144		80.03 219	79.03 223	83.01 222	83.78 353	64.51 259	87.11 211	90.57 177	71.96 226	78.08 236	86.20 321	61.41 227	93.94 152	74.93 204	77.23 354	90.60 253

OurMVSNet-221017-0		74.26 336	72.42 350	79.80 321	83.76 354	59.59 370	85.92 261	86.64 324	66.39 351	66.96 426	87.58 276	39.46 452	91.60 283	65.76 304	69.27 436	88.22 347

mmtdpeth		74.16 338	73.01 343	77.60 377	83.72 355	61.13 341	85.10 285	85.10 347	72.06 224	77.21 260	80.33 430	43.84 424	85.75 408	77.14 174	52.61 493	85.91 411

viewdifsd2359ckpt11		80.37 209	79.73 202	82.30 253	83.70 356	62.39 318	84.20 316	86.67 322	73.22 203	80.90 177	90.62 181	63.00 198	91.56 287	76.81 181	78.44 340	92.95 160

viewmsd2359difaftdt		80.37 209	79.73 202	82.30 253	83.70 356	62.39 318	84.20 316	86.67 322	73.22 203	80.90 177	90.62 181	63.00 198	91.56 287	76.81 181	78.44 340	92.95 160

v2v482		80.23 213	79.29 217	83.05 220	83.62 358	64.14 269	87.04 213	89.97 198	73.61 186	78.18 233	87.22 288	61.10 235	93.82 162	76.11 188	76.78 363	91.18 228

XXY-MVS		75.41 325	75.56 302	74.96 405	83.59 359	57.82 391	80.59 388	83.87 368	66.54 350	74.93 321	88.31 256	63.24 190	80.09 455	62.16 344	76.85 361	86.97 388

v1192		79.59 226	78.43 236	83.07 219	83.55 360	64.52 258	86.93 220	90.58 175	70.83 254	77.78 243	85.90 325	59.15 257	93.94 152	73.96 214	77.19 356	90.76 245

EGC-MVSNET		52.07 463	47.05 468	67.14 465	83.51 361	60.71 354	80.50 390	67.75 489	0.07 559	0.43 561	75.85 474	24.26 494	81.54 446	28.82 502	62.25 472	59.16 501

v7n		78.97 246	77.58 262	83.14 213	83.45 362	65.51 221	88.32 163	91.21 154	73.69 184	72.41 356	86.32 318	57.93 266	93.81 163	69.18 271	75.65 380	90.11 276

v144192		79.47 229	78.37 237	82.78 238	83.35 363	63.96 272	86.96 217	90.36 185	69.99 282	77.50 248	85.67 332	60.66 243	93.77 166	74.27 211	76.58 364	90.62 251

tpm2		73.26 356	71.46 360	78.63 349	83.34 364	56.71 409	80.65 387	80.40 423	56.63 463	73.55 340	82.02 413	51.80 336	91.24 305	56.35 408	78.42 343	87.95 352

viewmamba		82.38 149	82.11 148	83.19 210	83.30 365	64.26 267	84.62 300	89.16 238	75.24 132	80.97 175	91.10 162	67.12 139	91.63 281	81.36 111	86.13 220	93.67 107

v1921920		79.22 238	78.03 244	82.80 234	83.30 365	63.94 274	86.80 225	90.33 186	69.91 285	77.48 249	85.53 336	58.44 263	93.75 168	73.60 216	76.85 361	90.71 249

diffmvs_AUTHOR		82.38 149	82.27 146	82.73 242	83.26 367	63.80 277	83.89 322	89.76 205	73.35 197	82.37 146	90.84 172	66.25 152	90.79 328	82.77 97	87.93 183	93.59 117

baseline2		75.70 319	73.83 333	81.30 278	83.26 367	61.79 332	82.57 354	80.65 415	66.81 340	66.88 427	83.42 388	57.86 268	92.19 258	63.47 319	79.57 325	89.91 289

v1240		78.99 245	77.78 254	82.64 243	83.21 369	63.54 289	86.62 234	90.30 188	69.74 292	77.33 252	85.68 331	57.04 278	93.76 167	73.13 224	76.92 358	90.62 251

XVG-ACMP-BASELINE		76.11 314	74.27 327	81.62 268	83.20 370	64.67 255	83.60 332	89.75 207	69.75 290	71.85 364	87.09 293	32.78 477	92.11 260	69.99 263	80.43 317	88.09 350

MDTV_nov1_ep13			69.97 386		83.18 371	53.48 447	77.10 439	80.18 429	60.45 427	69.33 394	80.44 427	48.89 381	86.90 396	51.60 432	78.51 339

PatchmatchNet		73.12 359	71.33 363	78.49 357	83.18 371	60.85 350	79.63 403	78.57 443	64.13 386	71.73 365	79.81 438	51.20 346	85.97 407	57.40 396	76.36 374	88.66 334
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
onestephybrid01		82.22 152	81.81 158	83.46 196	83.16 373	64.93 249	84.64 299	89.19 237	73.95 175	81.48 164	90.63 180	66.00 161	91.92 271	80.33 127	86.93 202	93.53 122

Fast-Effi-MVS+-dtu		78.02 271	76.49 287	82.62 244	83.16 373	66.96 190	86.94 219	87.45 299	72.45 215	71.49 369	84.17 371	54.79 298	91.58 284	67.61 285	80.31 318	89.30 309

dtuplus		80.04 218	79.40 212	81.97 262	83.08 375	62.61 313	83.63 331	87.98 282	67.47 336	81.02 173	90.50 187	64.86 173	90.77 331	71.28 247	84.76 246	92.53 175

gg-mvs-nofinetune		69.95 401	67.96 403	75.94 391	83.07 376	54.51 440	77.23 437	70.29 481	63.11 399	70.32 378	62.33 496	43.62 425	88.69 374	53.88 421	87.76 187	84.62 434

MVSTER		79.01 244	77.88 250	82.38 250	83.07 376	64.80 253	84.08 321	88.95 251	69.01 312	78.69 217	87.17 291	54.70 299	92.43 247	74.69 205	80.57 315	89.89 291

K. test v3		71.19 381	68.51 395	79.21 341	83.04 378	57.78 393	84.35 313	76.91 457	72.90 210	62.99 462	82.86 399	39.27 453	91.09 315	61.65 353	52.66 492	88.75 331

usedtu_dtu_shiyan1		76.43 307	75.32 310	79.76 324	83.00 379	60.72 352	81.74 365	88.76 261	68.99 313	72.98 347	84.19 369	56.41 285	90.27 339	62.39 338	79.40 329	88.31 343

FE-MVSNET3		76.43 307	75.32 310	79.76 324	83.00 379	60.72 352	81.74 365	88.76 261	68.99 313	72.98 347	84.19 369	56.41 285	90.27 339	62.39 338	79.40 329	88.31 343

eth_miper_zixun_eth		77.92 274	76.69 284	81.61 270	83.00 379	61.98 328	83.15 344	89.20 236	69.52 295	74.86 322	84.35 363	61.76 219	92.56 239	71.50 244	72.89 416	90.28 269

diffmvs		82.10 154	81.88 156	82.76 240	83.00 379	63.78 279	83.68 327	89.76 205	72.94 209	82.02 153	89.85 202	65.96 162	90.79 328	82.38 104	87.30 195	93.71 105
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_fmvsmconf0.1_n		85.61 72	85.65 74	85.50 90	82.99 383	69.39 110	89.65 96	90.29 189	73.31 198	87.77 53	94.15 57	71.72 67	93.23 202	90.31 9	90.67 123	93.89 93

FMVSNet5		69.50 405	67.96 403	74.15 416	82.97 384	55.35 430	80.01 399	82.12 399	62.56 410	63.02 460	81.53 416	36.92 466	81.92 444	48.42 452	74.06 404	85.17 426

viewmambaseed2359dif		80.41 205	79.84 199	82.12 256	82.95 385	62.50 317	83.39 338	88.06 280	67.11 338	80.98 174	90.31 192	66.20 154	91.01 318	74.62 206	84.90 242	92.86 163

c3_l		78.75 250	77.91 247	81.26 280	82.89 386	61.56 335	84.09 320	89.13 242	69.97 283	75.56 294	84.29 364	66.36 150	92.09 262	73.47 219	75.48 384	90.12 275

sss		73.60 346	73.64 335	73.51 423	82.80 387	55.01 434	76.12 443	81.69 403	62.47 411	74.68 325	85.85 328	57.32 274	78.11 463	60.86 361	80.93 307	87.39 368

GA-MVS		76.87 298	75.17 314	81.97 262	82.75 388	62.58 314	81.44 373	86.35 331	72.16 223	74.74 323	82.89 398	46.20 404	92.02 265	68.85 276	81.09 306	91.30 226

v148		78.72 252	77.80 253	81.47 272	82.73 389	61.96 329	86.30 249	88.08 278	73.26 200	76.18 284	85.47 338	62.46 206	92.36 251	71.92 241	73.82 408	90.09 278

IterMVS-SCA-FT		75.43 324	73.87 332	80.11 312	82.69 390	64.85 252	81.57 370	83.47 374	69.16 306	70.49 376	84.15 372	51.95 330	88.15 382	69.23 270	72.14 422	87.34 373

miper_ehance_all_eth		78.59 256	77.76 256	81.08 286	82.66 391	61.56 335	83.65 328	89.15 240	68.87 316	75.55 295	83.79 378	66.49 148	92.03 263	73.25 222	76.39 369	89.64 299

CostFormer		75.24 328	73.90 331	79.27 339	82.65 392	58.27 382	80.80 381	82.73 391	61.57 420	75.33 308	83.13 393	55.52 290	91.07 316	64.98 310	78.34 345	88.45 340

nomal-1		73.10 360	71.76 356	77.13 383	82.58 393	65.50 222	73.53 464	79.64 433	66.14 353	72.17 360	81.27 417	46.45 397	81.47 448	62.08 347	81.93 297	84.42 436

EPNet_dtu		75.46 323	74.86 316	77.23 382	82.57 394	54.60 438	86.89 221	83.09 382	71.64 229	66.25 438	85.86 327	55.99 287	88.04 384	54.92 415	86.55 210	89.05 316
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
RPSCF		73.23 358	71.46 360	78.54 354	82.50 395	59.85 366	82.18 360	82.84 390	58.96 443	71.15 373	89.41 224	45.48 414	84.77 421	58.82 382	71.83 424	91.02 236

cl____		77.72 279	76.76 281	80.58 298	82.49 396	60.48 359	83.09 347	87.87 287	69.22 303	74.38 331	85.22 345	62.10 213	91.53 292	71.09 248	75.41 388	89.73 298

DIV-MVS_self_test		77.72 279	76.76 281	80.58 298	82.48 397	60.48 359	83.09 347	87.86 288	69.22 303	74.38 331	85.24 343	62.10 213	91.53 292	71.09 248	75.40 389	89.74 297

tpm cat1		70.57 390	68.31 397	77.35 380	82.41 398	57.95 388	78.08 427	80.22 427	52.04 477	68.54 404	77.66 456	52.00 329	87.84 387	51.77 430	72.07 423	86.25 401

cl22		78.07 269	77.01 273	81.23 281	82.37 399	61.83 331	83.55 333	87.98 282	68.96 315	75.06 317	83.87 374	61.40 228	91.88 273	73.53 217	76.39 369	89.98 287

tpm		72.37 371	71.71 357	74.35 413	82.19 400	52.00 457	79.22 409	77.29 454	64.56 380	72.95 349	83.68 383	51.35 340	83.26 435	58.33 388	75.80 378	87.81 356

hybridnocas07		81.44 175	81.13 165	82.37 251	82.13 401	63.11 302	83.45 336	88.74 263	72.54 213	80.71 184	90.73 175	65.14 168	90.74 333	80.35 126	86.41 213	93.27 133

tpmvs		71.09 383	69.29 390	76.49 388	82.04 402	56.04 420	78.92 416	81.37 408	64.05 389	67.18 424	78.28 451	49.74 367	89.77 351	49.67 446	72.37 418	83.67 445

hybrid		81.05 182	80.66 175	82.22 255	81.97 403	62.99 307	83.42 337	88.68 266	70.76 258	80.56 187	90.40 189	64.49 177	90.48 337	79.57 141	86.06 222	93.19 140

dmvs_re		71.14 382	70.58 377	72.80 431	81.96 404	59.68 368	75.60 449	79.34 437	68.55 321	69.27 396	80.72 426	49.42 370	76.54 471	52.56 428	77.79 348	82.19 461

pmmvs4		74.03 342	71.91 354	80.39 301	81.96 404	68.32 138	81.45 372	82.14 398	59.32 439	69.87 388	85.13 347	52.40 320	88.13 383	60.21 366	74.74 399	84.73 433

TinyColmap		67.30 424	64.81 432	74.76 409	81.92 406	56.68 410	80.29 394	81.49 406	60.33 428	56.27 488	83.22 390	24.77 493	87.66 390	45.52 471	69.47 435	79.95 475

ITE_SJBPF				78.22 360	81.77 407	60.57 357		83.30 376	69.25 302	67.54 416	87.20 289	36.33 470	87.28 394	54.34 418	74.62 400	86.80 392

miper_enhance_ethall		77.87 276	76.86 277	80.92 291	81.65 408	61.38 339	82.68 352	88.98 248	65.52 364	75.47 296	82.30 408	65.76 164	92.00 266	72.95 226	76.39 369	89.39 306

MVS-HIRNet		59.14 451	57.67 454	63.57 471	81.65 408	43.50 497	71.73 468	65.06 497	39.59 498	51.43 493	57.73 504	38.34 460	82.58 439	39.53 487	73.95 405	64.62 498

GG-mvs-BLEND				75.38 401	81.59 410	55.80 424	79.32 407	69.63 483		67.19 423	73.67 480	43.24 427	88.90 372	50.41 438	84.50 250	81.45 466

MonoMVSNet		76.49 306	75.80 296	78.58 352	81.55 411	58.45 378	86.36 247	86.22 332	74.87 151	74.73 324	83.73 380	51.79 337	88.73 373	70.78 250	72.15 421	88.55 339

IterMVS		74.29 335	72.94 344	78.35 359	81.53 412	63.49 291	81.58 369	82.49 392	68.06 329	69.99 385	83.69 382	51.66 339	85.54 412	65.85 303	71.64 425	86.01 408
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CHOSEN 280x420		66.51 430	64.71 433	71.90 437	81.45 413	63.52 290	57.98 506	68.95 487	53.57 473	62.59 464	76.70 461	46.22 403	75.29 486	55.25 411	79.68 324	76.88 483

gm-plane-assit					81.40 414	53.83 445			62.72 408		80.94 423		92.39 249	63.40 321

pmmvs6		74.69 332	73.39 337	78.61 350	81.38 415	57.48 398	86.64 233	87.95 285	64.99 377	70.18 380	86.61 307	50.43 356	89.52 356	62.12 345	70.18 433	88.83 327

test-LLR		72.94 364	72.43 349	74.48 411	81.35 416	58.04 385	78.38 422	77.46 450	66.66 344	69.95 386	79.00 445	48.06 383	79.24 457	66.13 297	84.83 243	86.15 404

test-mter		71.41 380	70.39 382	74.48 411	81.35 416	58.04 385	78.38 422	77.46 450	60.32 429	69.95 386	79.00 445	36.08 471	79.24 457	66.13 297	84.83 243	86.15 404

CR-MVSNet		73.37 351	71.27 365	79.67 330	81.32 418	65.19 234	75.92 445	80.30 425	59.92 434	72.73 351	81.19 418	52.50 318	86.69 397	59.84 369	77.71 349	87.11 384

RPMNet		73.51 347	70.49 379	82.58 246	81.32 418	65.19 234	75.92 445	92.27 98	57.60 456	72.73 351	76.45 463	52.30 321	95.43 80	48.14 457	77.71 349	87.11 384

V42		79.38 235	78.24 241	82.83 231	81.10 420	65.50 222	85.55 273	89.82 202	71.57 234	78.21 231	86.12 323	60.66 243	93.18 210	75.64 195	75.46 386	89.81 295

lessismore_v0				78.97 344	81.01 421	57.15 402		65.99 494		61.16 469	82.82 401	39.12 455	91.34 302	59.67 371	46.92 499	88.43 341

Patchmtry		70.74 388	69.16 392	75.49 399	80.72 422	54.07 443	74.94 456	80.30 425	58.34 448	70.01 383	81.19 418	52.50 318	86.54 399	53.37 424	71.09 429	85.87 413

PatchT		68.46 416	67.85 406	70.29 449	80.70 423	43.93 496	72.47 466	74.88 467	60.15 431	70.55 374	76.57 462	49.94 363	81.59 445	50.58 437	74.83 398	85.34 421

USDC		70.33 394	68.37 396	76.21 390	80.60 424	56.23 418	79.19 410	86.49 327	60.89 424	61.29 468	85.47 338	31.78 480	89.47 358	53.37 424	76.21 375	82.94 455

tpmrst		72.39 369	72.13 353	73.18 428	80.54 425	49.91 474	79.91 401	79.08 440	63.11 399	71.69 366	79.95 435	55.32 291	82.77 438	65.66 305	73.89 406	86.87 389

anonymousdsp		78.60 255	77.15 271	82.98 225	80.51 426	67.08 186	87.24 208	89.53 215	65.66 362	75.16 313	87.19 290	52.52 317	92.25 256	77.17 173	79.34 332	89.61 300

OpenMVS_ROB	64.09 19	70.56 391	68.19 398	77.65 374	80.26 427	59.41 373	85.01 288	82.96 387	58.76 446	65.43 445	82.33 407	37.63 464	91.23 306	45.34 474	76.03 376	82.32 459

test_fmvsmconf0.01_n		84.73 92	84.52 95	85.34 95	80.25 428	69.03 113	89.47 103	89.65 210	73.24 202	86.98 66	94.27 49	66.62 145	93.23 202	90.26 10	89.95 137	93.78 103

Anonymous20231206		68.60 412	67.80 409	71.02 446	80.23 429	50.75 471	78.30 426	80.47 419	56.79 462	66.11 440	82.63 404	46.35 401	78.95 459	43.62 477	75.70 379	83.36 448

dtuonlycased		68.45 417	67.29 419	71.92 436	80.18 430	54.90 435	79.76 402	80.38 424	60.11 432	62.57 465	76.44 465	49.34 372	82.31 440	55.05 413	61.77 474	78.53 479

miper_lstm_enhance		74.11 339	73.11 342	77.13 383	80.11 431	59.62 369	72.23 467	86.92 318	66.76 342	70.40 377	82.92 397	56.93 279	82.92 436	69.06 273	72.63 417	88.87 325

MIMVSNet1		68.58 413	66.78 425	73.98 419	80.07 432	51.82 461	80.77 383	84.37 357	64.40 383	59.75 476	82.16 411	36.47 469	83.63 429	42.73 480	70.33 432	86.48 399

ADS-MVSNet2		66.20 435	63.33 440	74.82 408	79.92 433	58.75 376	67.55 486	75.19 465	53.37 474	65.25 447	75.86 472	42.32 433	80.53 454	41.57 484	68.91 438	85.18 424

ADS-MVSNet		64.36 441	62.88 444	68.78 458	79.92 433	47.17 484	67.55 486	71.18 479	53.37 474	65.25 447	75.86 472	42.32 433	73.99 492	41.57 484	68.91 438	85.18 424

test_vis1_n_1920		75.52 322	75.78 297	74.75 410	79.84 435	57.44 399	83.26 342	85.52 342	62.83 405	79.34 209	86.17 322	45.10 415	79.71 456	78.75 152	81.21 305	87.10 386

D2MVS		74.82 331	73.21 340	79.64 331	79.81 436	62.56 316	80.34 393	87.35 301	64.37 384	68.86 398	82.66 403	46.37 400	90.10 344	67.91 283	81.24 304	86.25 401

our_test_3		69.14 408	67.00 421	75.57 396	79.80 437	58.80 375	77.96 429	77.81 447	59.55 437	62.90 463	78.25 452	47.43 386	83.97 426	51.71 431	67.58 447	83.93 443

ppachtmachnet_test		70.04 398	67.34 418	78.14 362	79.80 437	61.13 341	79.19 410	80.59 416	59.16 441	65.27 446	79.29 442	46.75 395	87.29 393	49.33 448	66.72 448	86.00 410

dp		66.80 427	65.43 429	70.90 448	79.74 439	48.82 479	75.12 454	74.77 468	59.61 436	64.08 456	77.23 459	42.89 429	80.72 453	48.86 451	66.58 450	83.16 450

EPMVS		69.02 409	68.16 399	71.59 439	79.61 440	49.80 476	77.40 435	66.93 492	62.82 406	70.01 383	79.05 443	45.79 408	77.86 465	56.58 406	75.26 393	87.13 383

PVSNet_0	57.27 20	61.67 448	59.27 452	68.85 457	79.61 440	57.44 399	68.01 484	73.44 474	55.93 467	58.54 479	70.41 488	44.58 418	77.55 466	47.01 461	35.91 504	71.55 492

CL-MVSNet_self_test		72.37 371	71.46 360	75.09 404	79.49 442	53.53 446	80.76 384	85.01 350	69.12 307	70.51 375	82.05 412	57.92 267	84.13 425	52.27 429	66.00 453	87.60 360

Patchmatch-test		64.82 439	63.24 441	69.57 452	79.42 443	49.82 475	63.49 501	69.05 486	51.98 479	59.95 475	80.13 433	50.91 348	70.98 496	40.66 486	73.57 409	87.90 354

0.4-1-1-0.1		70.93 385	67.94 405	79.91 317	79.35 444	61.27 340	78.95 415	82.19 397	63.36 396	67.50 417	69.40 491	39.83 451	91.04 317	62.44 337	68.40 442	87.40 367

MDA-MVSNet-bldmvs		66.68 428	63.66 439	75.75 393	79.28 445	60.56 358	73.92 462	78.35 445	64.43 381	50.13 496	79.87 437	44.02 423	83.67 428	46.10 467	56.86 483	83.03 453

TESTMET0.1,1		69.89 403	69.00 393	72.55 433	79.27 446	56.85 405	78.38 422	74.71 470	57.64 455	68.09 408	77.19 460	37.75 463	76.70 470	63.92 317	84.09 260	84.10 441

N_pmnet		52.79 461	53.26 460	51.40 489	78.99 447	7.68 538	69.52 478	3.89 538	51.63 480	57.01 484	74.98 476	40.83 444	65.96 504	37.78 491	64.67 464	80.56 474

UWE-MVS-28		65.32 436	64.93 431	66.49 467	78.70 448	38.55 506	77.86 432	64.39 499	62.00 418	64.13 455	83.60 384	41.44 439	76.00 478	31.39 500	80.89 308	84.92 429

dmvs_testset		62.63 445	64.11 436	58.19 477	78.55 449	24.76 521	75.28 450	65.94 495	67.91 330	60.34 472	76.01 471	53.56 310	73.94 493	31.79 499	67.65 446	75.88 485

EU-MVSNet		68.53 415	67.61 413	71.31 444	78.51 450	47.01 485	84.47 304	84.27 361	42.27 494	66.44 437	84.79 355	40.44 446	83.76 427	58.76 383	68.54 441	83.17 449

blended_shiyan8		73.38 349	71.17 367	80.02 314	78.36 451	61.51 337	82.43 355	87.28 302	65.40 368	68.61 401	77.53 458	51.91 333	91.00 321	63.28 323	65.76 455	87.53 364

blended_shiyan6		73.38 349	71.17 367	80.01 315	78.36 451	61.48 338	82.43 355	87.27 305	65.40 368	68.56 403	77.55 457	51.94 332	91.01 318	63.27 324	65.76 455	87.55 363

FE-MVSNET2		72.88 367	71.28 364	77.67 372	78.30 453	57.78 393	84.43 309	88.92 253	69.56 293	64.61 451	81.67 415	46.73 396	88.54 378	59.33 374	67.99 445	86.69 396

blend_shiyan4		72.29 373	69.65 387	80.21 309	78.24 454	62.16 325	82.29 358	87.27 305	65.41 367	68.43 407	76.42 466	39.91 450	91.23 306	63.21 325	65.66 460	87.22 377

0.3-1-1-0.015		70.03 399	66.80 424	79.72 327	78.18 455	61.07 344	77.63 433	82.32 396	62.65 409	65.50 443	67.29 492	37.62 465	90.91 324	61.99 348	68.04 444	87.19 379

gbinet_0.2-2-1-0.02		73.24 357	70.86 374	80.39 301	78.03 456	61.62 334	83.10 346	86.69 321	65.98 358	69.29 395	76.15 470	49.77 366	91.51 294	62.75 331	66.00 453	88.03 351

pmmvs5		71.55 379	70.20 384	75.61 395	77.83 457	56.39 414	81.74 365	80.89 411	57.76 454	67.46 419	84.49 357	49.26 375	85.32 416	57.08 399	75.29 392	85.11 427

wanda-best-256-512		72.94 364	70.66 375	79.79 322	77.80 458	61.03 346	81.31 375	87.15 310	65.18 371	68.09 408	76.28 467	51.32 341	90.97 322	63.06 327	65.76 455	87.35 370

FE-blended-shiyan7		72.94 364	70.66 375	79.79 322	77.80 458	61.03 346	81.31 375	87.15 310	65.18 371	68.09 408	76.28 467	51.32 341	90.97 322	63.06 327	65.76 455	87.35 370

usedtu_blend_shiyan5		73.29 355	70.96 371	80.25 307	77.80 458	62.16 325	84.44 308	87.38 300	64.41 382	68.09 408	76.28 467	51.32 341	91.23 306	63.21 325	65.76 455	87.35 370

0.4-1-1-0.2		70.01 400	66.86 423	79.44 336	77.61 461	60.64 356	76.77 440	82.34 395	62.40 412	65.91 441	66.65 493	40.05 448	90.83 326	61.77 352	68.24 443	86.86 390

test0.0.03 1		68.00 420	67.69 411	68.90 456	77.55 462	47.43 481	75.70 448	72.95 477	66.66 344	66.56 432	82.29 409	48.06 383	75.87 480	44.97 475	74.51 401	83.41 447

Patchmatch-RL test		70.24 395	67.78 410	77.61 375	77.43 463	59.57 371	71.16 471	70.33 480	62.94 403	68.65 400	72.77 482	50.62 353	85.49 413	69.58 268	66.58 450	87.77 357

pmmvs-eth3d		70.50 392	67.83 408	78.52 356	77.37 464	66.18 201	81.82 363	81.51 405	58.90 444	63.90 458	80.42 428	42.69 431	86.28 403	58.56 384	65.30 462	83.11 451

JIA-IIPM		66.32 432	62.82 445	76.82 386	77.09 465	61.72 333	65.34 495	75.38 464	58.04 453	64.51 452	62.32 497	42.05 437	86.51 400	51.45 434	69.22 437	82.21 460

Gipuma		45.18 470	41.86 474	55.16 485	77.03 466	51.52 464	32.50 516	80.52 418	32.46 508	27.12 512	35.02 524	9.52 512	75.50 482	22.31 513	60.21 480	38.45 517
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MDA-MVSNet_test_wron		65.03 437	62.92 442	71.37 441	75.93 467	56.73 407	69.09 483	74.73 469	57.28 460	54.03 491	77.89 453	45.88 406	74.39 489	49.89 445	61.55 475	82.99 454

test_cas_vis1_n_1920		73.76 344	73.74 334	73.81 421	75.90 468	59.77 367	80.51 389	82.40 393	58.30 449	81.62 162	85.69 330	44.35 421	76.41 474	76.29 185	78.61 336	85.23 423

FE-MVSNET		67.25 425	65.33 430	73.02 429	75.86 469	52.54 455	80.26 396	80.56 417	63.80 394	60.39 471	79.70 439	41.41 440	84.66 423	43.34 478	62.62 471	81.86 463

YYNet1		65.03 437	62.91 443	71.38 440	75.85 470	56.60 411	69.12 482	74.66 471	57.28 460	54.12 490	77.87 454	45.85 407	74.48 488	49.95 444	61.52 476	83.05 452

PMMVS		69.34 407	68.67 394	71.35 443	75.67 471	62.03 327	75.17 451	73.46 473	50.00 484	68.68 399	79.05 443	52.07 328	78.13 462	61.16 359	82.77 285	73.90 488

testgi		66.67 429	66.53 426	67.08 466	75.62 472	41.69 503	75.93 444	76.50 459	66.11 354	65.20 449	86.59 308	35.72 472	74.71 487	43.71 476	73.38 413	84.84 431

test20.03		67.45 422	66.95 422	68.94 455	75.48 473	44.84 494	77.50 434	77.67 448	66.66 344	63.01 461	83.80 377	47.02 390	78.40 461	42.53 483	68.86 440	83.58 446

KD-MVS_2432*1600		66.22 433	63.89 437	73.21 425	75.47 474	53.42 448	70.76 474	84.35 358	64.10 387	66.52 434	78.52 449	34.55 474	84.98 418	50.40 439	50.33 496	81.23 467

miper_refine_blended		66.22 433	63.89 437	73.21 425	75.47 474	53.42 448	70.76 474	84.35 358	64.10 387	66.52 434	78.52 449	34.55 474	84.98 418	50.40 439	50.33 496	81.23 467

Anonymous20240521		68.80 411	67.22 420	73.55 422	74.33 476	54.11 442	83.18 343	85.61 341	58.15 450	61.68 467	80.94 423	30.71 483	81.27 450	57.00 401	73.34 414	85.28 422

KD-MVS_self_test		68.81 410	67.59 414	72.46 434	74.29 477	45.45 488	77.93 430	87.00 314	63.12 398	63.99 457	78.99 447	42.32 433	84.77 421	56.55 407	64.09 466	87.16 382

mvs5depth		69.45 406	67.45 416	75.46 400	73.93 478	55.83 423	79.19 410	83.23 378	66.89 339	71.63 367	83.32 389	33.69 476	85.09 417	59.81 370	55.34 489	85.46 419

PM-MVS		66.41 431	64.14 435	73.20 427	73.92 479	56.45 412	78.97 414	64.96 498	63.88 393	64.72 450	80.24 432	19.84 501	83.44 433	66.24 296	64.52 465	79.71 476

test_fmvs1		70.93 385	70.52 378	72.16 435	73.71 480	55.05 433	80.82 380	78.77 442	51.21 482	78.58 221	84.41 360	31.20 482	76.94 469	75.88 193	80.12 322	84.47 435

UnsupCasMVSNet_bld		63.70 443	61.53 450	70.21 450	73.69 481	51.39 466	72.82 465	81.89 400	55.63 468	57.81 482	71.80 484	38.67 458	78.61 460	49.26 449	52.21 494	80.63 471

WB-MVS		54.94 455	54.72 457	55.60 484	73.50 482	20.90 524	74.27 461	61.19 503	59.16 441	50.61 494	74.15 478	47.19 389	75.78 481	17.31 518	35.07 505	70.12 493

UnsupCasMVSNet_eth		67.33 423	65.99 428	71.37 441	73.48 483	51.47 465	75.16 452	85.19 345	65.20 370	60.78 470	80.93 425	42.35 432	77.20 467	57.12 398	53.69 491	85.44 420

TDRefinement		67.49 421	64.34 434	76.92 385	73.47 484	61.07 344	84.86 292	82.98 386	59.77 435	58.30 480	85.13 347	26.06 489	87.89 386	47.92 459	60.59 479	81.81 465

dongtai		45.42 469	45.38 471	45.55 491	73.36 485	26.85 519	67.72 485	34.19 518	54.15 472	49.65 497	56.41 508	25.43 490	62.94 508	19.45 516	28.09 509	46.86 512

ambc				75.24 403	73.16 486	50.51 472	63.05 502	87.47 298		64.28 453	77.81 455	17.80 503	89.73 353	57.88 392	60.64 478	85.49 418

CMPMVS	51.72 21	70.19 396	68.16 399	76.28 389	73.15 487	57.55 397	79.47 405	83.92 366	48.02 487	56.48 486	84.81 354	43.13 428	86.42 402	62.67 335	81.81 299	84.89 430
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
dtuonly		69.95 401	69.98 385	69.85 451	73.09 488	49.46 477	74.55 459	76.40 460	57.56 458	67.82 412	86.31 319	50.89 352	74.23 490	61.46 355	81.71 300	85.86 414

SSC-MVS		53.88 458	53.59 459	54.75 487	72.87 489	19.59 525	73.84 463	60.53 505	57.58 457	49.18 498	73.45 481	46.34 402	75.47 484	16.20 521	32.28 507	69.20 494

new-patchmatchnet		61.73 447	61.73 448	61.70 473	72.74 490	24.50 522	69.16 481	78.03 446	61.40 421	56.72 485	75.53 475	38.42 459	76.48 473	45.95 468	57.67 482	84.13 440

test_vis1_n		69.85 404	69.21 391	71.77 438	72.66 491	55.27 432	81.48 371	76.21 462	52.03 478	75.30 309	83.20 392	28.97 485	76.22 476	74.60 207	78.41 344	83.81 444

test_fmvs1_n		70.86 387	70.24 383	72.73 432	72.51 492	55.28 431	81.27 377	79.71 432	51.49 481	78.73 216	84.87 352	27.54 488	77.02 468	76.06 189	79.97 323	85.88 412

LF4IMVS		64.02 442	62.19 446	69.50 453	70.90 493	53.29 451	76.13 442	77.18 455	52.65 476	58.59 478	80.98 422	23.55 496	76.52 472	53.06 426	66.66 449	78.68 478

usedtu_dtu_shiyan2		64.75 440	61.63 449	74.10 417	70.64 494	53.18 453	82.10 362	81.27 410	56.22 466	56.39 487	74.67 477	27.94 487	83.56 430	42.71 481	62.73 470	85.57 417

mvsany_test1		62.30 446	61.26 451	65.41 469	69.52 495	54.86 436	66.86 489	49.78 512	46.65 488	68.50 405	83.21 391	49.15 376	66.28 503	56.93 402	60.77 477	75.11 486

test_fmvs2		68.35 418	67.48 415	70.98 447	69.50 496	51.95 458	80.05 398	76.38 461	49.33 485	74.65 326	84.38 361	23.30 497	75.40 485	74.51 208	75.17 395	85.60 416

new_pmnet		50.91 464	50.29 465	52.78 488	68.58 497	34.94 512	63.71 499	56.63 509	39.73 497	44.95 499	65.47 495	21.93 498	58.48 510	34.98 496	56.62 484	64.92 497

DSMNet-mixed		57.77 453	56.90 456	60.38 475	67.70 498	35.61 510	69.18 480	53.97 510	32.30 509	57.49 483	79.88 436	40.39 447	68.57 502	38.78 490	72.37 418	76.97 482

test_vis1_rt		60.28 449	58.42 453	65.84 468	67.25 499	55.60 427	70.44 476	60.94 504	44.33 492	59.00 477	66.64 494	24.91 492	68.67 501	62.80 330	69.48 434	73.25 489

ttmdpeth		59.91 450	57.10 455	68.34 461	67.13 500	46.65 487	74.64 457	67.41 491	48.30 486	62.52 466	85.04 351	20.40 499	75.93 479	42.55 482	45.90 502	82.44 458

APD_test1		53.31 460	49.93 466	63.42 472	65.68 501	50.13 473	71.59 470	66.90 493	34.43 505	40.58 505	71.56 485	8.65 514	76.27 475	34.64 497	55.36 488	63.86 499

FPMVS		53.68 459	51.64 462	59.81 476	65.08 502	51.03 468	69.48 479	69.58 484	41.46 495	40.67 504	72.32 483	16.46 505	70.00 500	24.24 511	65.42 461	58.40 503

kuosan		39.70 475	40.40 475	37.58 496	64.52 503	26.98 517	65.62 494	33.02 519	46.12 489	42.79 502	48.99 515	24.10 495	46.56 518	12.16 526	26.30 510	39.20 516

pmmvs3		57.79 452	54.26 458	68.37 460	64.02 504	56.72 408	75.12 454	65.17 496	40.20 496	52.93 492	69.86 490	20.36 500	75.48 483	45.45 472	55.25 490	72.90 490

test_fmvs3		63.36 444	61.82 447	67.98 463	62.51 505	46.96 486	77.37 436	74.03 472	45.24 490	67.50 417	78.79 448	12.16 509	72.98 495	72.77 229	66.02 452	83.99 442

MVStest1		56.63 454	52.76 461	68.25 462	61.67 506	53.25 452	71.67 469	68.90 488	38.59 499	50.59 495	83.05 394	25.08 491	70.66 497	36.76 494	38.56 503	80.83 470

wuyk23d		16.82 490	15.94 495	19.46 508	58.74 507	31.45 513	39.22 512	3.74 540	6.84 524	6.04 536	2.70 559	1.27 527	24.29 528	10.54 531	14.40 523	2.63 542

testf1		45.72 467	41.96 472	57.00 478	56.90 508	45.32 489	66.14 492	59.26 506	26.19 510	30.89 509	60.96 500	4.14 519	70.64 498	26.39 509	46.73 500	55.04 505

APD_test2		45.72 467	41.96 472	57.00 478	56.90 508	45.32 489	66.14 492	59.26 506	26.19 510	30.89 509	60.96 500	4.14 519	70.64 498	26.39 509	46.73 500	55.04 505

mvsany_test3		53.99 457	51.45 463	61.61 474	55.51 510	44.74 495	63.52 500	45.41 516	43.69 493	58.11 481	76.45 463	17.99 502	63.76 507	54.77 416	47.59 498	76.34 484

test_vis3_rt		49.26 466	47.02 469	56.00 481	54.30 511	45.27 492	66.76 491	48.08 513	36.83 501	44.38 500	53.20 511	7.17 516	64.07 506	56.77 405	55.66 486	58.65 502

PMMVS2		40.82 474	38.86 479	46.69 490	53.84 512	16.45 529	48.61 509	49.92 511	37.49 500	31.67 507	60.97 499	8.14 515	56.42 512	28.42 503	30.72 508	67.19 496

test_f		52.09 462	50.82 464	55.90 482	53.82 513	42.31 502	59.42 505	58.31 508	36.45 502	56.12 489	70.96 487	12.18 508	57.79 511	53.51 423	56.57 485	67.60 495

LCM-MVSNet		54.25 456	49.68 467	67.97 464	53.73 514	45.28 491	66.85 490	80.78 413	35.96 503	39.45 506	62.23 498	8.70 513	78.06 464	48.24 456	51.20 495	80.57 473

E-PMN		31.77 477	30.64 480	35.15 498	52.87 515	27.67 515	57.09 507	47.86 514	24.64 513	16.40 528	33.05 525	11.23 510	54.90 514	14.46 522	18.15 518	22.87 524

ArgMatch-Sym		43.72 473	39.92 477	55.10 486	52.36 516	37.56 508	61.93 503	23.00 524	35.80 504	43.62 501	70.22 489	3.22 522	55.93 513	45.35 473	23.80 513	71.81 491

EMVS		30.81 479	29.65 481	34.27 499	50.96 517	25.95 520	56.58 508	46.80 515	24.01 514	15.53 529	30.68 528	12.47 507	54.43 515	12.81 525	17.05 519	22.43 525

ArgMatch-SfM		44.04 472	39.87 478	56.58 480	50.92 518	36.22 509	59.86 504	27.68 522	33.67 507	42.15 503	71.07 486	3.10 524	59.10 509	45.79 469	24.54 511	74.41 487

ANet_high		50.57 465	46.10 470	63.99 470	48.67 519	39.13 505	70.99 473	80.85 412	61.39 422	31.18 508	57.70 505	17.02 504	73.65 494	31.22 501	15.89 520	79.18 477

MVE	26.22 23	30.37 480	25.89 485	43.81 492	44.55 520	35.46 511	28.87 521	39.07 517	18.20 518	18.58 525	40.18 520	2.68 525	47.37 517	17.07 520	23.78 514	48.60 510
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DenseAffine		31.97 476	28.22 483	43.21 493	43.10 521	27.10 516	46.21 510	11.36 528	24.92 512	27.70 511	58.81 503	1.09 528	46.50 519	26.95 506	13.85 524	56.02 504

PMVS	37.38 22	44.16 471	40.28 476	55.82 483	40.82 522	42.54 501	65.12 496	63.99 500	34.43 505	24.48 514	57.12 506	3.92 521	76.17 477	17.10 519	55.52 487	48.75 509
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
DeepMVS_CX				27.40 504	40.17 523	26.90 518		24.59 523	17.44 519	23.95 515	48.61 517	9.77 511	26.48 526	18.06 517	24.47 512	28.83 522

PDCNetPlus		24.75 484	22.46 489	31.64 501	35.53 524	17.00 528	32.00 517	9.46 529	18.43 517	18.56 526	51.31 513	1.65 526	33.00 524	26.51 507	8.70 529	44.91 513

LoFTR		27.52 482	24.27 487	37.29 497	34.75 525	19.27 526	33.78 515	21.60 525	12.42 522	21.61 520	56.59 507	0.91 530	40.37 521	13.94 523	22.80 515	52.22 507

RoMa-SfM		28.67 481	25.38 486	38.54 494	32.61 526	22.48 523	40.24 511	7.23 532	21.81 515	26.66 513	60.46 502	0.96 529	41.72 520	26.47 508	11.95 525	51.40 508

DKM		25.67 483	23.01 488	33.64 500	32.08 527	19.25 527	37.50 513	5.52 534	18.67 516	23.58 517	55.44 509	0.64 535	34.02 522	23.95 512	9.73 527	47.66 511

MatchFormer		22.13 485	19.86 491	28.93 502	28.66 528	15.74 530	31.91 518	17.10 527	7.75 523	18.87 524	47.50 518	0.62 537	33.92 523	7.49 533	18.87 517	37.14 518

test_method		31.52 478	29.28 482	38.23 495	27.03 529	6.50 543	20.94 522	62.21 502	4.05 530	22.35 518	52.50 512	13.33 506	47.58 516	27.04 505	34.04 506	60.62 500

DKM-HiRes		20.87 487	19.15 493	26.02 505	25.34 530	14.13 532	29.63 520	3.62 541	14.53 521	20.13 522	50.55 514	0.47 543	24.22 529	20.96 515	7.15 534	39.70 514

RoMa-HiRes		21.63 486	19.64 492	27.59 503	22.40 531	14.25 531	29.71 519	4.10 536	15.42 520	21.09 521	54.77 510	0.72 533	28.87 525	21.01 514	7.52 533	39.65 515

ALIKED-LG		8.61 498	8.70 503	8.33 514	20.63 532	8.70 535	15.50 526	4.61 535	2.19 532	5.84 537	18.70 530	0.80 531	8.06 536	1.03 544	8.97 528	8.25 529

ALIKED-MNN		7.86 499	7.83 506	7.97 515	19.40 533	8.86 534	14.48 527	3.90 537	1.59 534	4.74 542	16.49 531	0.59 538	7.65 537	0.91 545	8.34 531	7.39 532

ALIKED-NN		7.51 500	7.61 507	7.21 516	18.26 534	8.10 537	13.45 529	3.88 539	1.50 535	4.87 540	16.47 532	0.64 535	7.00 538	0.88 546	8.50 530	6.52 537

MVS_clip		11.37 496	13.03 497	6.40 517	15.78 535	6.79 541	11.98 531	1.47 551	1.89 533	19.38 523	35.95 523	3.13 523	3.09 541	12.10 527	15.54 521	9.34 527

GLUNet-SfM		12.90 495	10.00 500	21.62 507	13.58 536	8.30 536	10.19 532	9.30 530	4.31 529	12.18 531	30.90 527	0.50 541	22.76 530	4.89 534	4.14 545	33.79 520

PMatch-SfM		14.15 493	12.67 498	18.59 509	12.84 537	7.03 540	17.41 523	2.28 543	6.63 525	12.96 530	43.56 519	0.09 560	16.11 532	13.90 524	4.38 544	32.63 521

VLMVS_CLIP		15.14 491	16.11 494	12.23 512	12.32 538	7.35 539	15.53 525	20.73 526	4.02 531	22.32 519	31.59 526	4.37 518	21.02 531	11.59 528	22.52 516	8.32 528

ELoFTR		14.23 492	11.56 499	22.24 506	11.02 539	6.56 542	13.59 528	7.57 531	5.55 526	11.96 532	39.09 521	0.21 548	24.93 527	9.43 532	5.66 538	35.22 519

SP-LightGlue		4.27 508	4.41 512	3.86 519	10.99 540	1.99 556	8.19 533	2.06 546	0.98 540	2.37 544	8.29 539	0.56 539	2.10 544	1.27 540	4.99 540	7.48 531

SP-SuperGlue		4.24 509	4.38 513	3.81 521	10.75 541	2.00 555	8.18 534	2.09 545	1.00 539	2.41 543	8.29 539	0.56 539	2.05 546	1.27 540	4.91 541	7.39 532

MASt3R-SfM		13.55 494	13.93 496	12.41 511	10.54 542	5.97 544	16.61 524	6.07 533	4.50 528	16.53 527	48.67 516	0.73 532	9.44 535	11.56 529	10.18 526	21.81 526

SP-MNN		4.14 510	4.24 514	3.82 520	10.32 543	1.83 560	8.11 535	1.99 547	0.82 542	2.23 545	8.27 541	0.47 543	2.14 543	1.20 542	4.77 542	7.49 530

SP-NN		4.00 511	4.12 515	3.63 523	9.92 544	1.81 561	7.94 536	1.90 549	0.86 541	2.15 546	8.00 542	0.50 541	2.09 545	1.20 542	4.63 543	6.98 536

PMatch-Up-SfM		10.76 497	9.99 501	13.09 510	9.50 545	4.83 545	12.94 530	1.40 552	4.65 527	10.16 533	37.54 522	0.07 563	10.94 534	10.71 530	2.92 555	23.50 523

SIFT-NN		2.77 514	2.92 518	2.34 526	8.70 546	3.08 546	4.46 540	1.01 554	0.68 544	1.46 547	5.49 543	0.16 549	1.65 548	0.26 547	4.04 546	2.27 543

SIFT-MNN		2.63 515	2.75 519	2.25 527	8.10 547	2.84 547	4.08 541	1.02 553	0.68 544	1.28 548	5.34 546	0.15 550	1.64 549	0.26 547	3.88 548	2.27 543

SIFT-NCM-Cal		2.40 517	2.52 521	2.05 529	7.74 548	2.54 549	3.75 544	0.84 556	0.65 547	0.89 555	4.78 552	0.13 554	1.60 550	0.19 558	3.71 549	2.01 549

SIFT-NN-NCMNet		2.52 516	2.64 520	2.14 528	7.53 549	2.74 548	4.00 542	0.98 555	0.65 547	1.24 550	5.08 549	0.14 551	1.60 550	0.23 550	3.94 547	2.07 547

SIFT-ConvMatch		2.25 520	2.37 524	1.90 531	7.29 550	2.37 550	3.21 549	0.75 559	0.65 547	1.03 553	4.91 550	0.12 557	1.51 554	0.22 553	3.13 553	1.81 550

SIFT-UMatch		2.16 521	2.30 525	1.72 534	6.99 551	1.97 558	3.32 547	0.70 561	0.64 551	0.91 554	4.86 551	0.12 557	1.49 555	0.22 553	2.97 554	1.72 552

SIFT-CM-Cal		2.02 523	2.13 527	1.67 535	6.79 552	1.99 556	2.79 551	0.64 562	0.63 552	0.87 556	4.48 555	0.13 554	1.41 557	0.19 558	2.70 556	1.61 554

SIFT-NN-CMatch		2.31 518	2.41 522	2.00 530	6.59 553	2.34 551	3.48 545	0.83 557	0.65 547	1.28 548	5.09 547	0.14 551	1.52 552	0.23 550	3.41 551	2.14 545

SIFT-UM-Cal		1.97 524	2.12 528	1.52 536	6.57 554	1.67 562	2.93 550	0.57 564	0.62 553	0.83 557	4.55 554	0.11 559	1.37 558	0.20 557	2.69 557	1.53 555

SIFT-NN-UMatch		2.26 519	2.39 523	1.89 532	6.21 555	2.08 554	3.76 543	0.83 557	0.66 546	1.04 552	5.09 547	0.14 551	1.52 552	0.23 550	3.51 550	2.07 547

SIFT-NN-PointCN		2.07 522	2.18 526	1.74 533	5.75 556	1.65 563	3.27 548	0.73 560	0.60 554	1.07 551	4.62 553	0.13 554	1.43 556	0.21 555	3.22 552	2.12 546

SIFT-PCN-Cal		1.72 525	1.82 530	1.39 537	5.64 557	1.19 566	2.39 553	0.53 565	0.55 556	0.72 558	3.90 556	0.09 560	1.22 560	0.17 560	2.42 559	1.76 551

SIFT-PointCN		1.72 525	1.83 529	1.36 538	5.55 558	1.22 565	2.59 552	0.59 563	0.55 556	0.71 559	3.77 557	0.08 562	1.24 559	0.17 560	2.48 558	1.63 553

SIFT-NCMNet		1.44 527	1.56 531	1.08 540	5.14 559	1.07 567	1.97 554	0.32 566	0.56 555	0.64 560	3.23 558	0.07 563	1.01 561	0.14 562	1.95 560	1.15 556

VLMVS		4.54 505	4.93 509	3.37 524	4.86 560	2.23 552	3.38 546	1.77 550	0.23 558	7.94 534	11.34 538	4.62 517	2.44 542	2.43 536	7.76 532	5.44 539

tmp_tt		18.61 489	21.40 490	10.23 513	4.82 561	10.11 533	34.70 514	30.74 521	1.48 536	23.91 516	26.07 529	28.42 486	13.41 533	27.12 504	15.35 522	7.17 535

SP-DiffGlue		4.29 507	4.46 511	3.77 522	3.68 562	2.12 553	5.97 537	2.22 544	1.10 537	4.89 539	13.93 535	0.66 534	1.95 547	2.47 535	5.24 539	7.22 534

MVS_baseline		3.29 513	4.00 516	1.16 539	3.08 563	0.09 568	1.26 555	0.24 567	0.04 561	6.52 535	16.19 533	0.30 547	0.00 564	1.53 539	6.83 535	3.39 541

XFeat-MNN		4.39 506	4.49 510	4.10 518	2.88 564	1.91 559	5.86 538	2.57 542	1.06 538	5.04 538	13.99 534	0.43 545	4.47 539	2.00 537	6.55 536	5.92 538

XFeat-NN		3.78 512	3.96 517	3.23 525	2.65 565	1.53 564	4.99 539	1.92 548	0.81 543	4.77 541	12.37 537	0.38 546	3.39 540	1.64 538	6.13 537	4.77 540

testmvs		6.04 503	8.02 505	0.10 542	0.08 566	0.03 570	69.74 477	0.04 568	0.05 560	0.31 562	1.68 560	0.02 566	0.04 562	0.24 549	0.02 561	0.25 558

test123		6.12 502	8.11 504	0.14 541	0.06 567	0.09 568	71.05 472	0.03 569	0.04 561	0.25 563	1.30 561	0.05 565	0.03 563	0.21 555	0.01 562	0.29 557

PatchmatchNet2					0.00 568	30.51 514	67.30 488	67.46 490	50.92 483
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
mmdepth		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

monomultidepth		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

test_blank		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

eth-test2					0.00 568

eth-test					0.00 568

uanet_test		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

DCPMVS		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

cdsmvs_eth3d_5k		19.96 488	26.61 484	0.00 543	0.00 568	0.00 571	0.00 556	89.26 231	0.00 563	0.00 564	88.61 247	61.62 222	0.00 564	0.00 563	0.00 563	0.00 559

pcd_1.5k_mvsjas		5.26 504	7.02 508	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	63.15 193	0.00 564	0.00 563	0.00 563	0.00 559

sosnet-low-res		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

sosnet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

uncertanet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

Regformer		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

ab-mvs-re		7.23 501	9.64 502	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	86.72 300	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

uanet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

Meshroom													0.00 564
: In preparation.
AliceVision / Meshro													0.00 564
: In preparation.
AliceVision_Meshroom													0.00 564
: In preparation.
PatchmatchNet1														37.67 492	64.79 463	80.58 472
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													65.90 505
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						42.58 499								39.46 488

PC_three_1452									68.21 327	92.02 15	94.00 65	82.09 5	95.98 64	84.58 74	96.68 2	94.95 15

test_241102_TWO								94.06 15	77.24 65	92.78 5	95.72 12	81.26 9	97.44 7	89.07 25	96.58 6	94.26 73

test_0728_THIRD									78.38 39	92.12 12	95.78 8	81.46 8	97.40 9	89.42 19	96.57 7	94.67 42

GSMVS																88.96 322

sam_mvs1												51.32 341				88.96 322

sam_mvs												50.01 361

MTGPA								92.02 116

test_post1							78.90 417				5.43 545	48.81 382	85.44 415	59.25 376

test_post											5.46 544	50.36 357	84.24 424

patchmatchnet-post											74.00 479	51.12 347	88.60 376

MTMP							92.18 40	32.83 520

test9_res														84.90 67	95.70 30	92.87 162

agg_prior2														82.91 94	95.45 33	92.70 167

test_prior4						72.60 35	89.01 127

test_prior2							88.85 134		75.41 127	84.91 86	93.54 78	74.28 36		83.31 88	95.86 24

旧先验2							86.56 237		58.10 452	87.04 65			88.98 368	74.07 213

新几何2							86.29 251

无先验							87.48 191	88.98 248	60.00 433				94.12 145	67.28 289		88.97 321

原ACMM2							86.86 223

testdata2													91.01 318	62.37 341

segment_acmp												73.08 47

testdata1							84.14 319		75.71 118

plane_prior5								92.44 86					95.38 85	78.71 153	86.32 214	91.33 224

plane_prior4											91.00 169

plane_prior3						68.60 131			78.44 37	78.92 214

plane_prior2							91.25 61		79.12 29

plane_prior						68.71 126	90.38 79		77.62 49						86.16 219

n2								0.00 570

nn								0.00 570

door-mid								69.98 482

test11								92.23 102

door								69.44 485

HQP5-MVS						66.98 188

BP-MVS														77.47 169

HQP4-MVS										77.24 255			95.11 97			91.03 234

HQP3-MVS								92.19 110							85.99 225

HQP2-MVS												60.17 251

MDTV_nov1_ep13_2view						37.79 507	75.16 452		55.10 469	66.53 433		49.34 372		53.98 420		87.94 353

ACMMP++_ref															81.95 296

ACMMP++															81.25 303

Test By Simon												64.33 178

High-resolution multi-view benchmark