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.

MVS_0304		78.73 15	78.75 14	78.66 29	80.82 100	57.62 82	85.31 29	81.31 111	70.51 1	74.17 52	91.24 14	54.99 44	89.56 16	82.29 1	88.13 34	88.80 6

CANet		76.46 36	75.93 39	78.06 38	81.29 92	57.53 84	82.35 68	83.31 73	67.78 2	70.09 99	86.34 94	54.92 46	88.90 24	72.68 47	84.55 64	87.76 31

UA-Net		73.13 67	72.93 67	73.76 113	83.58 64	51.66 177	78.75 117	77.66 183	67.75 3	72.61 77	89.42 46	49.82 98	83.29 142	53.61 189	83.14 74	86.32 76

CNVR-MVS		79.84 9	79.97 9	79.45 10	87.90 2	62.17 17	84.37 35	85.03 34	66.96 4	77.58 27	90.06 35	59.47 20	89.13 21	78.67 13	89.73 16	87.03 52

TranMVSNet+NR-MVSNet		70.36 110	70.10 106	71.17 178	78.64 148	42.97 279	76.53 163	81.16 118	66.95 5	68.53 128	85.42 118	51.61 83	83.07 146	52.32 197	69.70 244	87.46 40

3Dnovator+	66.72 4	75.84 44	74.57 52	79.66 8	82.40 76	59.92 47	85.83 21	86.32 16	66.92 6	67.80 147	89.24 50	42.03 187	89.38 18	64.07 106	86.50 54	89.69 2

NCCC		78.58 16	78.31 18	79.39 11	87.51 12	62.61 13	85.20 30	84.42 42	66.73 7	74.67 47	89.38 48	55.30 41	89.18 20	74.19 36	87.34 42	86.38 68

SteuartSystems-ACMMP		79.48 10	79.31 10	79.98 2	83.01 72	62.18 16	87.60 9	85.83 19	66.69 8	78.03 26	90.98 15	54.26 51	90.06 12	78.42 18	89.02 23	87.69 32
Skip Steuart: Steuart Systems R&D Blog.
EPNet		73.09 68	72.16 72	75.90 64	75.95 215	56.28 103	83.05 55	72.39 252	66.53 9	65.27 196	87.00 77	50.40 95	85.47 101	62.48 123	86.32 55	85.94 86
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
UniMVSNet_NR-MVSNet		71.11 96	71.00 91	71.44 168	79.20 133	44.13 267	76.02 176	82.60 86	66.48 10	68.20 132	84.60 130	56.82 32	82.82 157	54.62 180	70.43 226	87.36 47

MSP-MVS		81.06 3	81.40 4	80.02 1	86.21 31	62.73 9	86.09 17	86.83 8	65.51 11	83.81 10	90.51 22	63.71 12	89.23 19	81.51 2	88.44 27	88.09 20
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
HPM-MVS++		79.88 8	80.14 8	79.10 20	88.17 1	64.80 1	86.59 12	83.70 60	65.37 12	78.78 22	90.64 18	58.63 24	87.24 50	79.00 11	90.37 14	85.26 120

NR-MVSNet		69.54 131	68.85 124	71.59 166	78.05 166	43.81 271	74.20 210	80.86 124	65.18 13	62.76 231	84.52 131	52.35 74	83.59 138	50.96 212	70.78 221	87.37 45

MTAPA		76.90 33	76.42 34	78.35 34	86.08 37	63.57 2	74.92 198	80.97 122	65.13 14	75.77 34	90.88 16	48.63 112	86.66 69	77.23 20	88.17 33	84.81 132

DVP-MVS++		81.67 1	82.40 1	79.47 9	87.24 14	59.15 59	88.18 1	87.15 3	65.04 15	84.26 5	91.86 6	67.01 1	90.84 3	79.48 5	91.38 2	88.42 10

test_0728_THIRD									65.04 15	83.82 8	92.00 3	64.69 10	90.75 8	79.48 5	90.63 10	88.09 20

EI-MVSNet-Vis-set		72.42 77	71.59 77	74.91 83	78.47 152	54.02 135	77.05 153	79.33 146	65.03 17	71.68 87	79.35 241	52.75 67	84.89 113	66.46 86	74.23 173	85.83 92

casdiffmvs_mvg		76.14 40	76.30 35	75.66 70	76.46 209	51.83 176	79.67 108	85.08 31	65.02 18	75.84 33	88.58 59	59.42 21	85.08 107	72.75 46	83.93 71	90.08 1
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_one_0601					87.58 9	59.30 56		86.84 7	65.01 19	83.80 11	91.86 6	64.03 11

ETV-MVS		74.46 57	73.84 60	76.33 59	79.27 131	55.24 125	79.22 114	85.00 36	64.97 20	72.65 76	79.46 238	53.65 62	87.87 41	67.45 80	82.91 80	85.89 90

WR-MVS		68.47 154	68.47 132	68.44 224	80.20 112	39.84 301	73.75 222	76.07 206	64.68 21	68.11 137	83.63 150	50.39 96	79.14 228	49.78 217	69.66 245	86.34 72

XVS		77.17 30	76.56 33	79.00 22	86.32 29	62.62 11	85.83 21	83.92 51	64.55 22	72.17 82	90.01 39	47.95 119	88.01 37	71.55 55	86.74 51	86.37 70

X-MVStestdata		70.21 113	67.28 161	79.00 22	86.32 29	62.62 11	85.83 21	83.92 51	64.55 22	72.17 82	6.49 381	47.95 119	88.01 37	71.55 55	86.74 51	86.37 70

HQP_MVS		74.31 58	73.73 61	76.06 61	81.41 89	56.31 101	84.22 39	84.01 49	64.52 24	69.27 117	86.10 99	45.26 160	87.21 52	68.16 71	80.58 102	84.65 136

plane_prior2							84.22 39		64.52 24

EI-MVSNet-UG-set		71.92 84	71.06 90	74.52 98	77.98 169	53.56 141	76.62 161	79.16 147	64.40 26	71.18 90	78.95 246	52.19 75	84.66 119	65.47 97	73.57 183	85.32 117

DU-MVS		70.01 116	69.53 113	71.44 168	78.05 166	44.13 267	75.01 195	81.51 101	64.37 27	68.20 132	84.52 131	49.12 109	82.82 157	54.62 180	70.43 226	87.37 45

DVP-MVS		80.84 4	81.64 3	78.42 33	87.75 7	59.07 63	87.85 5	85.03 34	64.26 28	83.82 8	92.00 3	64.82 8	90.75 8	78.66 14	90.61 11	85.45 110
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					87.75 7	59.07 63	87.86 4	86.83 8	64.26 28	84.19 7	91.92 5	64.82 8

test_241102_ONE					87.77 4	58.90 68		86.78 10	64.20 30	85.97 1	91.34 12	66.87 3	90.78 7

SED-MVS		81.56 2	82.30 2	79.32 12	87.77 4	58.90 68	87.82 7	86.78 10	64.18 31	85.97 1	91.84 8	66.87 3	90.83 5	78.63 16	90.87 5	88.23 15

test_241102_TWO								86.73 12	64.18 31	84.26 5	91.84 8	65.19 6	90.83 5	78.63 16	90.70 7	87.65 34

LFMVS		71.78 86	71.59 77	72.32 154	83.40 67	46.38 244	79.75 106	71.08 261	64.18 31	72.80 73	88.64 58	42.58 182	83.72 134	57.41 158	84.49 65	86.86 57

IS-MVSNet		71.57 90	71.00 91	73.27 135	78.86 141	45.63 255	80.22 96	78.69 158	64.14 34	66.46 172	87.36 72	49.30 103	85.60 94	50.26 216	83.71 73	88.59 8

plane_prior3						56.09 107			63.92 35	69.27 117

MP-MVS		78.35 19	78.26 20	78.64 30	86.54 25	63.47 4	86.02 19	83.55 64	63.89 36	73.60 59	90.60 19	54.85 47	86.72 67	77.20 21	88.06 36	85.74 99
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DELS-MVS		74.76 51	74.46 53	75.65 71	77.84 172	52.25 168	75.59 182	84.17 46	63.76 37	73.15 66	82.79 164	59.58 19	86.80 65	67.24 81	86.04 56	87.89 23
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
OPM-MVS		74.73 52	74.25 55	76.19 60	80.81 101	59.01 66	82.60 65	83.64 61	63.74 38	72.52 78	87.49 70	47.18 134	85.88 89	69.47 64	80.78 98	83.66 171
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
UniMVSNet (Re)		70.63 105	70.20 102	71.89 157	78.55 149	45.29 258	75.94 177	82.92 81	63.68 39	68.16 135	83.59 151	53.89 56	83.49 140	53.97 185	71.12 219	86.89 56

GST-MVS		78.14 21	77.85 23	78.99 24	86.05 38	61.82 22	85.84 20	85.21 29	63.56 40	74.29 51	90.03 37	52.56 68	88.53 28	74.79 32	88.34 29	86.63 64

EC-MVSNet		75.84 44	75.87 41	75.74 68	78.86 141	52.65 158	83.73 49	86.08 17	63.47 41	72.77 74	87.25 76	53.13 65	87.93 39	71.97 51	85.57 59	86.66 63

ZNCC-MVS		78.82 12	78.67 16	79.30 13	86.43 28	62.05 18	86.62 11	86.01 18	63.32 42	75.08 38	90.47 25	53.96 55	88.68 26	76.48 24	89.63 20	87.16 50

DPE-MVS		80.56 5	80.98 5	79.29 14	87.27 13	60.56 41	85.71 25	86.42 14	63.28 43	83.27 13	91.83 10	64.96 7	90.47 10	76.41 25	89.67 18	86.84 58
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CS-MVS		76.25 39	75.98 38	77.06 49	80.15 115	55.63 117	84.51 34	83.90 53	63.24 44	73.30 62	87.27 75	55.06 43	86.30 82	71.78 52	84.58 63	89.25 4

DeepC-MVS	69.38 2	78.56 17	78.14 21	79.83 6	83.60 63	61.62 23	84.17 41	86.85 6	63.23 45	73.84 57	90.25 31	57.68 27	89.96 13	74.62 33	89.03 22	87.89 23
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
VDD-MVS		72.50 74	72.09 73	73.75 115	81.58 85	49.69 207	77.76 135	77.63 184	63.21 46	73.21 65	89.02 52	42.14 186	83.32 141	61.72 130	82.50 86	88.25 14

plane_prior						56.31 101	83.58 52		63.19 47						80.48 105

ACMMP		76.02 42	75.33 45	78.07 37	85.20 49	61.91 20	85.49 28	84.44 41	63.04 48	69.80 109	89.74 45	45.43 156	87.16 54	72.01 50	82.87 82	85.14 121
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
PEN-MVS		66.60 194	66.45 174	67.04 238	77.11 195	36.56 332	77.03 154	80.42 130	62.95 49	62.51 239	84.03 141	46.69 142	79.07 229	44.22 264	63.08 301	85.51 107

APDe-MVS		80.16 7	80.59 6	78.86 27	86.64 21	60.02 45	88.12 3	86.42 14	62.94 50	82.40 14	92.12 2	59.64 18	89.76 14	78.70 12	88.32 31	86.79 60

mPP-MVS		76.54 35	75.93 39	78.34 35	86.47 26	63.50 3	85.74 24	82.28 89	62.90 51	71.77 85	90.26 30	46.61 143	86.55 73	71.71 53	85.66 58	84.97 128

ACMMP_NAP		78.77 14	78.78 13	78.74 28	85.44 45	61.04 31	83.84 48	85.16 30	62.88 52	78.10 24	91.26 13	52.51 69	88.39 29	79.34 7	90.52 13	86.78 61

DeepPCF-MVS	69.58 1	79.03 11	79.00 12	79.13 18	84.92 56	60.32 44	83.03 56	85.33 27	62.86 53	80.17 17	90.03 37	61.76 14	88.95 23	74.21 35	88.67 26	88.12 19

HFP-MVS		78.01 23	77.65 24	79.10 20	86.71 19	62.81 8	86.29 14	84.32 44	62.82 54	73.96 55	90.50 23	53.20 64	88.35 30	74.02 38	87.05 43	86.13 82

ACMMPR		77.71 24	77.23 27	79.16 16	86.75 18	62.93 7	86.29 14	84.24 45	62.82 54	73.55 60	90.56 21	49.80 99	88.24 32	74.02 38	87.03 44	86.32 76

region2R		77.67 26	77.18 28	79.15 17	86.76 17	62.95 6	86.29 14	84.16 47	62.81 56	73.30 62	90.58 20	49.90 97	88.21 33	73.78 40	87.03 44	86.29 79

casdiffmvs		74.80 50	74.89 50	74.53 97	75.59 221	50.37 194	78.17 127	85.06 33	62.80 57	74.40 49	87.86 67	57.88 26	83.61 137	69.46 65	82.79 84	89.59 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
baseline		74.61 54	74.70 51	74.34 101	75.70 217	49.99 202	77.54 140	84.63 40	62.73 58	73.98 54	87.79 69	57.67 28	83.82 133	69.49 63	82.74 85	89.20 5

HPM-MVS		77.28 28	76.85 29	78.54 31	85.00 51	60.81 38	82.91 59	85.08 31	62.57 59	73.09 69	89.97 40	50.90 93	87.48 48	75.30 28	86.85 49	87.33 48
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
DTE-MVSNet		65.58 206	65.34 197	66.31 245	76.06 214	34.79 341	76.43 165	79.38 145	62.55 60	61.66 248	83.83 146	45.60 150	79.15 227	41.64 291	60.88 315	85.00 126

SMA-MVS		80.28 6	80.39 7	79.95 3	86.60 23	61.95 19	86.33 13	85.75 21	62.49 61	82.20 15	92.28 1	56.53 33	89.70 15	79.85 4	91.48 1	88.19 17
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
CP-MVSNet		66.49 197	66.41 178	66.72 240	77.67 177	36.33 335	76.83 160	79.52 142	62.45 62	62.54 237	83.47 157	46.32 144	78.37 237	45.47 259	63.43 298	85.45 110

CP-MVS		77.12 31	76.68 31	78.43 32	86.05 38	63.18 5	87.55 10	83.45 67	62.44 63	72.68 75	90.50 23	48.18 117	87.34 49	73.59 42	85.71 57	84.76 135

PS-CasMVS		66.42 198	66.32 182	66.70 242	77.60 185	36.30 337	76.94 156	79.61 140	62.36 64	62.43 241	83.66 149	45.69 148	78.37 237	45.35 261	63.26 299	85.42 113

3Dnovator	64.47 5	72.49 75	71.39 82	75.79 65	77.70 175	58.99 67	80.66 93	83.15 78	62.24 65	65.46 192	86.59 88	42.38 185	85.52 97	59.59 148	84.72 62	82.85 191

MP-MVS-pluss		78.35 19	78.46 17	78.03 39	84.96 52	59.52 52	82.93 58	85.39 26	62.15 66	76.41 32	91.51 11	52.47 71	86.78 66	80.66 3	89.64 19	87.80 29
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HQP-NCC					80.66 102		82.31 70		62.10 67	67.85 142

ACMP_Plane					80.66 102		82.31 70		62.10 67	67.85 142

HQP-MVS		73.45 64	72.80 68	75.40 75	80.66 102	54.94 127	82.31 70	83.90 53	62.10 67	67.85 142	85.54 116	45.46 154	86.93 61	67.04 83	80.35 106	84.32 143

CS-MVS-test		75.62 46	75.31 46	76.56 56	80.63 105	55.13 126	83.88 47	85.22 28	62.05 70	71.49 89	86.03 102	53.83 57	86.36 80	67.74 75	86.91 48	88.19 17

VPNet		67.52 173	68.11 138	65.74 258	79.18 134	36.80 330	72.17 243	72.83 249	62.04 71	67.79 148	85.83 109	48.88 111	76.60 262	51.30 208	72.97 196	83.81 161

WR-MVS_H		67.02 185	66.92 170	67.33 237	77.95 170	37.75 319	77.57 138	82.11 92	62.03 72	62.65 234	82.48 175	50.57 94	79.46 218	42.91 280	64.01 291	84.79 133

DeepC-MVS_fast	68.24 3	77.25 29	76.63 32	79.12 19	86.15 34	60.86 36	84.71 32	84.85 38	61.98 73	73.06 70	88.88 54	53.72 58	89.06 22	68.27 68	88.04 37	87.42 42
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SF-MVS		78.82 12	79.22 11	77.60 43	82.88 74	57.83 79	84.99 31	88.13 2	61.86 74	79.16 20	90.75 17	57.96 25	87.09 59	77.08 22	90.18 15	87.87 25

PGM-MVS		76.77 34	76.06 37	78.88 26	86.14 35	62.73 9	82.55 66	83.74 59	61.71 75	72.45 81	90.34 28	48.48 115	88.13 34	72.32 48	86.85 49	85.78 93

Effi-MVS+		73.31 66	72.54 70	75.62 72	77.87 171	53.64 139	79.62 110	79.61 140	61.63 76	72.02 84	82.61 169	56.44 34	85.97 87	63.99 109	79.07 126	87.25 49

MG-MVS		73.96 61	73.89 59	74.16 104	85.65 42	49.69 207	81.59 83	81.29 113	61.45 77	71.05 91	88.11 61	51.77 81	87.73 44	61.05 136	83.09 75	85.05 125

LPG-MVS_test		72.74 71	71.74 76	75.76 66	80.22 110	57.51 85	82.55 66	83.40 69	61.32 78	66.67 169	87.33 73	39.15 217	86.59 70	67.70 76	77.30 148	83.19 183

LGP-MVS_train				75.76 66	80.22 110	57.51 85		83.40 69	61.32 78	66.67 169	87.33 73	39.15 217	86.59 70	67.70 76	77.30 148	83.19 183

CLD-MVS		73.33 65	72.68 69	75.29 79	78.82 143	53.33 148	78.23 126	84.79 39	61.30 80	70.41 96	81.04 206	52.41 72	87.12 57	64.61 105	82.49 87	85.41 114
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MVS_111021_HR		74.02 60	73.46 64	75.69 69	83.01 72	60.63 40	77.29 148	78.40 172	61.18 81	70.58 94	85.97 104	54.18 53	84.00 130	67.52 79	82.98 79	82.45 197

FIs		70.82 102	71.43 80	68.98 217	78.33 157	38.14 315	76.96 155	83.59 63	61.02 82	67.33 155	86.73 82	55.07 42	81.64 178	54.61 182	79.22 122	87.14 51

FOURS1					86.12 36	60.82 37	88.18 1	83.61 62	60.87 83	81.50 16

FC-MVSNet-test		69.80 123	70.58 97	67.46 233	77.61 183	34.73 344	76.05 174	83.19 77	60.84 84	65.88 185	86.46 91	54.52 50	80.76 202	52.52 196	78.12 137	86.91 55

v8		70.33 111	69.28 118	73.49 127	73.15 253	50.22 196	78.62 121	80.78 125	60.79 85	66.45 173	82.11 187	49.35 102	84.98 110	63.58 114	68.71 258	85.28 118

CSCG		76.92 32	76.75 30	77.41 45	83.96 62	59.60 50	82.95 57	86.50 13	60.78 86	75.27 36	84.83 123	60.76 15	86.56 72	67.86 74	87.87 40	86.06 84

Vis-MVSNet		72.18 80	71.37 83	74.61 93	81.29 92	55.41 122	80.90 89	78.28 174	60.73 87	69.23 120	88.09 62	44.36 168	82.65 161	57.68 155	81.75 95	85.77 96
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
APD-MVS		78.02 22	78.04 22	77.98 40	86.44 27	60.81 38	85.52 26	84.36 43	60.61 88	79.05 21	90.30 29	55.54 40	88.32 31	73.48 43	87.03 44	84.83 131
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ACMP	63.53 6	72.30 78	71.20 87	75.59 74	80.28 108	57.54 83	82.74 62	82.84 84	60.58 89	65.24 200	86.18 96	39.25 215	86.03 85	66.95 85	76.79 155	83.22 181
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
testdata1							72.65 233		60.50 90

UGNet		68.81 144	67.39 156	73.06 138	78.33 157	54.47 133	79.77 105	75.40 215	60.45 91	63.22 226	84.40 134	32.71 285	80.91 198	51.71 206	80.56 104	83.81 161
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
h-mvs33		72.71 72	71.49 79	76.40 57	81.99 81	59.58 51	76.92 157	76.74 199	60.40 92	74.81 43	85.95 106	45.54 152	85.76 92	70.41 60	70.61 224	83.86 160

hse-mvs2		71.04 97	69.86 107	74.60 94	79.58 123	57.12 95	73.96 214	75.25 217	60.40 92	74.81 43	81.95 189	45.54 152	82.90 150	70.41 60	66.83 272	83.77 165

EPP-MVSNet		72.16 82	71.31 85	74.71 87	78.68 147	49.70 205	82.10 75	81.65 98	60.40 92	65.94 181	85.84 108	51.74 82	86.37 79	55.93 166	79.55 117	88.07 22

UniMVSNet_ETH3D		67.60 172	67.07 169	69.18 216	77.39 188	42.29 283	74.18 211	75.59 212	60.37 95	66.77 166	86.06 101	37.64 231	78.93 235	52.16 199	73.49 185	86.32 76

test_prior2							81.75 79		60.37 95	75.01 39	89.06 51	56.22 36		72.19 49	88.96 24

SD-MVS		77.70 25	77.62 25	77.93 41	84.47 59	61.88 21	84.55 33	83.87 56	60.37 95	79.89 18	89.38 48	54.97 45	85.58 96	76.12 26	84.94 61	86.33 74
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
VNet		69.68 127	70.19 103	68.16 227	79.73 121	41.63 292	70.53 265	77.38 189	60.37 95	70.69 93	86.63 86	51.08 89	77.09 257	53.61 189	81.69 97	85.75 98

canonicalmvs		74.67 53	74.98 49	73.71 117	78.94 140	50.56 192	80.23 95	83.87 56	60.30 99	77.15 29	86.56 90	59.65 17	82.00 173	66.01 91	82.12 88	88.58 9

v7n		69.01 142	67.36 158	73.98 106	72.51 267	52.65 158	78.54 124	81.30 112	60.26 100	62.67 233	81.62 195	43.61 173	84.49 120	57.01 159	68.70 259	84.79 133

HPM-MVS_fast		74.30 59	73.46 64	76.80 51	84.45 60	59.04 65	83.65 51	81.05 119	60.15 101	70.43 95	89.84 42	41.09 203	85.59 95	67.61 78	82.90 81	85.77 96

VPA-MVSNet		69.02 141	69.47 115	67.69 231	77.42 187	41.00 297	74.04 212	79.68 138	60.06 102	69.26 119	84.81 124	51.06 90	77.58 249	54.44 183	74.43 171	84.48 140

v10		70.21 113	69.02 122	73.81 110	73.51 250	50.92 184	78.74 118	81.39 104	60.05 103	66.39 174	81.83 192	47.58 126	85.41 104	62.80 120	68.86 257	85.09 124

SR-MVS		76.13 41	75.70 42	77.40 47	85.87 40	61.20 29	85.52 26	82.19 90	59.99 104	75.10 37	90.35 27	47.66 124	86.52 74	71.64 54	82.99 77	84.47 141

9.14			78.75 14		83.10 69		84.15 42	88.26 1	59.90 105	78.57 23	90.36 26	57.51 30	86.86 63	77.39 19	89.52 21

v2v482		70.50 108	69.45 116	73.66 119	72.62 263	50.03 201	77.58 137	80.51 129	59.90 105	69.52 111	82.14 185	47.53 127	84.88 115	65.07 101	70.17 232	86.09 83

Baseline_NR-MVSNet		67.05 184	67.56 147	65.50 260	75.65 218	37.70 321	75.42 185	74.65 229	59.90 105	68.14 136	83.15 161	49.12 109	77.20 255	52.23 198	69.78 241	81.60 209

API-MVS		72.17 81	71.41 81	74.45 99	81.95 82	57.22 88	84.03 44	80.38 131	59.89 108	68.40 129	82.33 178	49.64 100	87.83 43	51.87 203	84.16 70	78.30 256

Effi-MVS+-dtu		69.64 129	67.53 150	75.95 63	76.10 213	62.29 15	80.20 97	76.06 207	59.83 109	65.26 199	77.09 268	41.56 195	84.02 129	60.60 139	71.09 220	81.53 210

CANet_DTU		68.18 160	67.71 145	69.59 207	74.83 231	46.24 246	78.66 120	76.85 196	59.60 110	63.45 225	82.09 188	35.25 255	77.41 252	59.88 145	78.76 131	85.14 121

EI-MVSNet		69.27 138	68.44 134	71.73 161	74.47 239	49.39 212	75.20 190	78.45 168	59.60 110	69.16 121	76.51 278	51.29 85	82.50 165	59.86 147	71.45 217	83.30 178

IterMVS-LS		69.22 140	68.48 130	71.43 170	74.44 241	49.40 211	76.23 169	77.55 185	59.60 110	65.85 186	81.59 198	51.28 86	81.58 181	59.87 146	69.90 239	83.30 178
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
VDDNet		71.81 85	71.33 84	73.26 136	82.80 75	47.60 235	78.74 118	75.27 216	59.59 113	72.94 71	89.40 47	41.51 197	83.91 131	58.75 152	82.99 77	88.26 13

alignmvs		73.86 62	73.99 57	73.45 129	78.20 160	50.50 193	78.57 122	82.43 87	59.40 114	76.57 30	86.71 84	56.42 35	81.23 189	65.84 93	81.79 92	88.62 7

MVS_Test		72.45 76	72.46 71	72.42 153	74.88 229	48.50 223	76.28 168	83.14 79	59.40 114	72.46 79	84.68 125	55.66 39	81.12 190	65.98 92	79.66 114	87.63 35

TSAR-MVS + MP.		78.44 18	78.28 19	78.90 25	84.96 52	61.41 26	84.03 44	83.82 58	59.34 116	79.37 19	89.76 44	59.84 16	87.62 46	76.69 23	86.74 51	87.68 33
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MSLP-MVS++		73.77 63	73.47 63	74.66 90	83.02 71	59.29 57	82.30 73	81.88 94	59.34 116	71.59 88	86.83 78	45.94 147	83.65 136	65.09 100	85.22 60	81.06 224

PAPM_NR		72.63 73	71.80 75	75.13 82	81.72 84	53.42 146	79.91 103	83.28 75	59.14 118	66.31 176	85.90 107	51.86 79	86.06 83	57.45 157	80.62 100	85.91 88

save fliter					86.17 33	61.30 28	83.98 46	79.66 139	59.00 119

v148		68.24 159	67.19 167	71.40 171	70.43 292	47.77 232	75.76 180	77.03 194	58.91 120	67.36 154	80.10 225	48.60 114	81.89 174	60.01 143	66.52 275	84.53 138

TransMVSNet (Re)		64.72 217	64.33 206	65.87 257	75.22 226	38.56 312	74.66 204	75.08 226	58.90 121	61.79 247	82.63 168	51.18 87	78.07 242	43.63 273	55.87 336	80.99 225

Anonymous202405211		66.84 189	65.99 188	69.40 211	80.19 113	42.21 285	71.11 259	71.31 260	58.80 122	67.90 140	86.39 93	29.83 305	79.65 215	49.60 223	78.78 130	86.33 74

test2506		65.33 211	64.61 204	67.50 232	79.46 126	34.19 348	74.43 208	51.92 351	58.72 123	66.75 167	88.05 64	25.99 333	80.92 197	51.94 202	84.25 67	87.39 43

ECVR-MVS		67.72 170	67.51 151	68.35 225	79.46 126	36.29 338	74.79 201	66.93 290	58.72 123	67.19 157	88.05 64	36.10 248	81.38 184	52.07 200	84.25 67	87.39 43

test1111		67.21 177	67.14 168	67.42 234	79.24 132	34.76 343	73.89 219	65.65 297	58.71 125	66.96 162	87.95 66	36.09 249	80.53 204	52.03 201	83.79 72	86.97 53

LCM-MVSNet-Re		61.88 247	61.35 241	63.46 274	74.58 237	31.48 360	61.42 319	58.14 333	58.71 125	53.02 325	79.55 236	43.07 177	76.80 260	45.69 253	77.96 139	82.11 203

v1144		70.42 109	69.31 117	73.76 113	73.22 251	50.64 189	77.83 133	81.43 103	58.58 127	69.40 115	81.16 203	47.53 127	85.29 106	64.01 108	70.64 222	85.34 116

TSAR-MVS + GP.		74.90 49	74.15 56	77.17 48	82.00 80	58.77 71	81.80 78	78.57 161	58.58 127	74.32 50	84.51 133	55.94 38	87.22 51	67.11 82	84.48 66	85.52 106

BH-RMVSNet		68.81 144	67.42 155	72.97 139	80.11 116	52.53 163	74.26 209	76.29 202	58.48 129	68.38 130	84.20 136	42.59 181	83.83 132	46.53 245	75.91 161	82.56 192

APD-MVS_3200maxsize		74.96 48	74.39 54	76.67 53	82.20 78	58.24 76	83.67 50	83.29 74	58.41 130	73.71 58	90.14 32	45.62 149	85.99 86	69.64 62	82.85 83	85.78 93

OMC-MVS		71.40 94	70.60 95	73.78 111	76.60 205	53.15 151	79.74 107	79.78 136	58.37 131	68.75 124	86.45 92	45.43 156	80.60 203	62.58 121	77.73 141	87.58 38

nrg030		72.96 69	73.01 66	72.84 142	75.41 224	50.24 195	80.02 99	82.89 83	58.36 132	74.44 48	86.73 82	58.90 23	80.83 199	65.84 93	74.46 170	87.44 41

K. test v3		60.47 257	57.11 269	70.56 189	73.74 249	48.22 226	75.10 194	62.55 317	58.27 133	53.62 321	76.31 281	27.81 320	81.59 180	47.42 236	39.18 366	81.88 207

FA-MVS(test-final)		69.82 121	68.48 130	73.84 109	78.44 153	50.04 200	75.58 184	78.99 151	58.16 134	67.59 151	82.14 185	42.66 180	85.63 93	56.60 161	76.19 159	85.84 91

MVS_111021_LR		69.50 132	68.78 126	71.65 164	78.38 154	59.33 55	74.82 200	70.11 268	58.08 135	67.83 146	84.68 125	41.96 188	76.34 265	65.62 96	77.54 143	79.30 250

SR-MVS-dyc-post		74.57 55	73.90 58	76.58 55	83.49 65	59.87 48	84.29 36	81.36 106	58.07 136	73.14 67	90.07 33	44.74 163	85.84 90	68.20 69	81.76 93	84.03 151

RE-MVS-def			73.71 62		83.49 65	59.87 48	84.29 36	81.36 106	58.07 136	73.14 67	90.07 33	43.06 178		68.20 69	81.76 93	84.03 151

SDMVSNet		68.03 162	68.10 139	67.84 229	77.13 193	48.72 221	65.32 299	79.10 148	58.02 138	65.08 203	82.55 171	47.83 121	73.40 277	63.92 110	73.92 176	81.41 212

sd_testset		64.46 222	64.45 205	64.51 269	77.13 193	42.25 284	62.67 312	72.11 255	58.02 138	65.08 203	82.55 171	41.22 202	69.88 295	47.32 238	73.92 176	81.41 212

GeoE		71.01 98	70.15 104	73.60 124	79.57 124	52.17 169	78.93 116	78.12 176	58.02 138	67.76 150	83.87 145	52.36 73	82.72 159	56.90 160	75.79 162	85.92 87

ZD-MVS					86.64 21	60.38 43		82.70 85	57.95 141	78.10 24	90.06 35	56.12 37	88.84 25	74.05 37	87.00 47

EIA-MVS		71.78 86	70.60 95	75.30 78	79.85 119	53.54 142	77.27 149	83.26 76	57.92 142	66.49 171	79.39 239	52.07 77	86.69 68	60.05 142	79.14 125	85.66 101

test_yl		69.69 125	69.13 119	71.36 172	78.37 155	45.74 251	74.71 202	80.20 133	57.91 143	70.01 104	83.83 146	42.44 183	82.87 153	54.97 176	79.72 112	85.48 108

DCV-MVSNet		69.69 125	69.13 119	71.36 172	78.37 155	45.74 251	74.71 202	80.20 133	57.91 143	70.01 104	83.83 146	42.44 183	82.87 153	54.97 176	79.72 112	85.48 108

dcpmvs_2		74.55 56	75.23 47	72.48 149	82.34 77	53.34 147	77.87 131	81.46 102	57.80 145	75.49 35	86.81 79	62.22 13	77.75 247	71.09 57	82.02 90	86.34 72

mvsmamba		71.15 95	69.54 112	75.99 62	77.61 183	53.46 144	81.95 77	75.11 222	57.73 146	66.95 163	85.96 105	37.14 240	87.56 47	67.94 73	75.49 166	86.97 53

Fast-Effi-MVS+-dtu		67.37 175	65.33 198	73.48 128	72.94 258	57.78 81	77.47 142	76.88 195	57.60 147	61.97 244	76.85 272	39.31 213	80.49 207	54.72 179	70.28 231	82.17 202

v1192		69.97 118	68.68 127	73.85 108	73.19 252	50.94 182	77.68 136	81.36 106	57.51 148	68.95 123	80.85 213	45.28 159	85.33 105	62.97 119	70.37 228	85.27 119

ACMH+	57.40 11	66.12 200	64.06 207	72.30 155	77.79 174	52.83 156	80.39 94	78.03 177	57.30 149	57.47 286	82.55 171	27.68 321	84.17 124	45.54 256	69.78 241	79.90 241

diffmvs		70.69 104	70.43 98	71.46 167	69.45 306	48.95 217	72.93 230	78.46 167	57.27 150	71.69 86	83.97 144	51.48 84	77.92 244	70.70 59	77.95 140	87.53 39
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
BH-untuned		68.27 157	67.29 160	71.21 176	79.74 120	53.22 150	76.06 173	77.46 188	57.19 151	66.10 178	81.61 196	45.37 158	83.50 139	45.42 260	76.68 157	76.91 277

thres100view900		63.28 232	62.41 230	65.89 256	77.31 190	38.66 311	72.65 233	69.11 278	57.07 152	62.45 240	81.03 207	37.01 244	79.17 224	31.84 339	73.25 191	79.83 243

DP-MVS Recon		72.15 83	70.73 94	76.40 57	86.57 24	57.99 78	81.15 88	82.96 80	57.03 153	66.78 165	85.56 113	44.50 166	88.11 35	51.77 205	80.23 109	83.10 186

thres600view7		63.30 231	62.27 231	66.41 244	77.18 192	38.87 309	72.35 240	69.11 278	56.98 154	62.37 242	80.96 209	37.01 244	79.00 233	31.43 346	73.05 195	81.36 215

V42		68.65 148	67.35 159	72.56 147	68.93 312	50.18 197	72.90 231	79.47 143	56.92 155	69.45 114	80.26 222	46.29 145	82.99 147	64.07 106	67.82 264	84.53 138

MCST-MVS		77.48 27	77.45 26	77.54 44	86.67 20	58.36 75	83.22 54	86.93 5	56.91 156	74.91 42	88.19 60	59.15 22	87.68 45	73.67 41	87.45 41	86.57 65

GA-MVS		65.53 207	63.70 213	71.02 182	70.87 287	48.10 227	70.48 266	74.40 231	56.69 157	64.70 211	76.77 273	33.66 272	81.10 191	55.42 175	70.32 230	83.87 159

v144192		69.71 124	68.51 129	73.33 134	73.10 254	50.13 198	77.54 140	80.64 126	56.65 158	68.57 127	80.55 216	46.87 141	84.96 112	62.98 118	69.66 245	84.89 130

tfpn200view9		63.18 234	62.18 233	66.21 248	76.85 200	39.62 303	71.96 247	69.44 274	56.63 159	62.61 235	79.83 228	37.18 237	79.17 224	31.84 339	73.25 191	79.83 243

thres400		63.31 230	62.18 233	66.72 240	76.85 200	39.62 303	71.96 247	69.44 274	56.63 159	62.61 235	79.83 228	37.18 237	79.17 224	31.84 339	73.25 191	81.36 215

GBi-Net		67.21 177	66.55 172	69.19 213	77.63 178	43.33 274	77.31 145	77.83 180	56.62 161	65.04 205	82.70 165	41.85 190	80.33 209	47.18 240	72.76 198	83.92 156

test1		67.21 177	66.55 172	69.19 213	77.63 178	43.33 274	77.31 145	77.83 180	56.62 161	65.04 205	82.70 165	41.85 190	80.33 209	47.18 240	72.76 198	83.92 156

FMVSNet2		66.93 187	66.31 183	68.79 220	77.63 178	42.98 278	76.11 171	77.47 186	56.62 161	65.22 202	82.17 183	41.85 190	80.18 212	47.05 243	72.72 201	83.20 182

DPM-MVS		75.47 47	75.00 48	76.88 50	81.38 91	59.16 58	79.94 101	85.71 22	56.59 164	72.46 79	86.76 80	56.89 31	87.86 42	66.36 87	88.91 25	83.64 173

v1921920		69.47 133	68.17 137	73.36 133	73.06 255	50.10 199	77.39 143	80.56 127	56.58 165	68.59 125	80.37 218	44.72 164	84.98 110	62.47 124	69.82 240	85.00 126

FMVSNet1		66.70 192	65.87 189	69.19 213	77.49 186	43.33 274	77.31 145	77.83 180	56.45 166	64.60 213	82.70 165	38.08 229	80.33 209	46.08 249	72.31 207	83.92 156

v1240		69.24 139	67.91 141	73.25 137	73.02 257	49.82 203	77.21 150	80.54 128	56.43 167	68.34 131	80.51 217	43.33 176	84.99 108	62.03 128	69.77 243	84.95 129

CDPH-MVS		76.31 37	75.67 43	78.22 36	85.35 48	59.14 61	81.31 86	84.02 48	56.32 168	74.05 53	88.98 53	53.34 63	87.92 40	69.23 66	88.42 28	87.59 37

Vis-MVSNet (Re-imp)		63.69 227	63.88 210	63.14 278	74.75 234	31.04 361	71.16 257	63.64 310	56.32 168	59.80 264	84.99 121	44.51 165	75.46 268	39.12 301	80.62 100	82.92 188

AdaColmap		69.99 117	68.66 128	73.97 107	84.94 54	57.83 79	82.63 64	78.71 157	56.28 170	64.34 214	84.14 138	41.57 194	87.06 60	46.45 246	78.88 127	77.02 273

PS-MVSNAJss		72.24 79	71.21 86	75.31 77	78.50 150	55.93 111	81.63 80	82.12 91	56.24 171	70.02 103	85.68 112	47.05 136	84.34 123	65.27 99	74.41 172	85.67 100

c3_l		68.33 156	67.56 147	70.62 188	70.87 287	46.21 247	74.47 207	78.80 155	56.22 172	66.19 177	78.53 253	51.88 78	81.40 183	62.08 125	69.04 254	84.25 145

Fast-Effi-MVS+		70.28 112	69.12 121	73.73 116	78.50 150	51.50 178	75.01 195	79.46 144	56.16 173	68.59 125	79.55 236	53.97 54	84.05 126	53.34 191	77.53 144	85.65 102

PHI-MVS		75.87 43	75.36 44	77.41 45	80.62 106	55.91 112	84.28 38	85.78 20	56.08 174	73.41 61	86.58 89	50.94 92	88.54 27	70.79 58	89.71 17	87.79 30

baseline1		63.81 226	63.87 211	63.62 273	76.29 210	36.36 333	71.78 249	67.29 287	56.05 175	64.23 218	82.95 163	47.11 135	74.41 273	47.30 239	61.85 309	80.10 239

train_agg		76.27 38	76.15 36	76.64 54	85.58 43	61.59 24	81.62 81	81.26 114	55.86 176	74.93 40	88.81 55	53.70 59	84.68 117	75.24 30	88.33 30	83.65 172

test_8					85.40 46	60.96 34	81.54 84	81.18 117	55.86 176	74.81 43	88.80 57	53.70 59	84.45 121

RRT_MVS		69.42 135	67.49 153	75.21 81	78.01 168	52.56 162	82.23 74	78.15 175	55.84 178	65.65 188	85.07 120	30.86 296	86.83 64	61.56 134	70.00 235	86.24 81

FMVSNet3		66.32 199	65.61 194	68.46 223	76.48 208	42.34 282	74.98 197	77.15 193	55.83 179	65.04 205	81.16 203	39.91 207	80.14 213	47.18 240	72.76 198	82.90 190

PAPR		71.72 89	70.82 93	74.41 100	81.20 96	51.17 179	79.55 111	83.33 72	55.81 180	66.93 164	84.61 129	50.95 91	86.06 83	55.79 169	79.20 123	86.00 85

eth_miper_zixun_eth		67.63 171	66.28 184	71.67 163	71.60 278	48.33 225	73.68 223	77.88 178	55.80 181	65.91 182	78.62 251	47.35 133	82.88 152	59.45 149	66.25 276	83.81 161

ACMH	55.70 15	65.20 213	63.57 215	70.07 197	78.07 165	52.01 174	79.48 112	79.69 137	55.75 182	56.59 292	80.98 208	27.12 325	80.94 195	42.90 281	71.58 215	77.25 271
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IB-MVS	56.42 12	65.40 210	62.73 227	73.40 132	74.89 228	52.78 157	73.09 229	75.13 221	55.69 183	58.48 280	73.73 303	32.86 280	86.32 81	50.63 213	70.11 233	81.10 223
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
CL-MVSNet_self_test		61.53 250	60.94 247	63.30 276	68.95 311	36.93 329	67.60 284	72.80 250	55.67 184	59.95 261	76.63 274	45.01 162	72.22 284	39.74 299	62.09 308	80.74 229

TEST9					85.58 43	61.59 24	81.62 81	81.26 114	55.65 185	74.93 40	88.81 55	53.70 59	84.68 117

thres200		62.20 243	61.16 245	65.34 263	75.38 225	39.99 300	69.60 274	69.29 276	55.64 186	61.87 246	76.99 269	37.07 243	78.96 234	31.28 347	73.28 190	77.06 272

pm-mvs1		65.24 212	64.97 202	66.04 253	72.38 268	39.40 306	72.62 235	75.63 211	55.53 187	62.35 243	83.18 160	47.45 129	76.47 263	49.06 227	66.54 274	82.24 199

ACMM	61.98 7	70.80 103	69.73 109	74.02 105	80.59 107	58.59 73	82.68 63	82.02 93	55.46 188	67.18 158	84.39 135	38.51 222	83.17 145	60.65 138	76.10 160	80.30 235
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240529		69.91 119	69.02 122	72.56 147	80.19 113	47.65 233	77.56 139	80.99 121	55.45 189	69.88 107	86.76 80	39.24 216	82.18 171	54.04 184	77.10 151	87.85 26

tt0805		67.77 169	67.24 165	69.34 212	74.87 230	40.08 299	77.36 144	81.37 105	55.31 190	66.33 175	84.65 127	37.35 235	82.55 164	55.65 172	72.28 208	85.39 115

CPTT-MVS		72.78 70	72.08 74	74.87 85	84.88 57	61.41 26	84.15 42	77.86 179	55.27 191	67.51 153	88.08 63	41.93 189	81.85 175	69.04 67	80.01 110	81.35 217

XVG-OURS		68.76 147	67.37 157	72.90 141	74.32 244	57.22 88	70.09 271	78.81 154	55.24 192	67.79 148	85.81 111	36.54 247	78.28 239	62.04 127	75.74 163	83.19 183

tfpnnormal		62.47 239	61.63 238	64.99 266	74.81 232	39.01 308	71.22 255	73.72 241	55.22 193	60.21 256	80.09 226	41.26 201	76.98 259	30.02 352	68.09 262	78.97 253

cl____		67.18 180	66.26 185	69.94 199	70.20 295	45.74 251	73.30 225	76.83 197	55.10 194	65.27 196	79.57 235	47.39 131	80.53 204	59.41 151	69.22 252	83.53 175

DIV-MVS_self_test		67.18 180	66.26 185	69.94 199	70.20 295	45.74 251	73.29 226	76.83 197	55.10 194	65.27 196	79.58 234	47.38 132	80.53 204	59.43 150	69.22 252	83.54 174

PC_three_1452									55.09 196	84.46 4	89.84 42	66.68 5	89.41 17	74.24 34	91.38 2	88.42 10

EPNet_dtu		61.90 246	61.97 235	61.68 286	72.89 259	39.78 302	75.85 179	65.62 298	55.09 196	54.56 311	79.36 240	37.59 232	67.02 307	39.80 298	76.95 152	78.25 257
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_Blended_VisFu		71.45 93	70.39 99	74.65 91	82.01 79	58.82 70	79.93 102	80.35 132	55.09 196	65.82 187	82.16 184	49.17 106	82.64 162	60.34 140	78.62 134	82.50 196

cl22		67.47 174	66.45 174	70.54 190	69.85 302	46.49 243	73.85 220	77.35 190	55.07 199	65.51 191	77.92 258	47.64 125	81.10 191	61.58 133	69.32 248	84.01 153

miper_ehance_all_eth		68.03 162	67.24 165	70.40 192	70.54 290	46.21 247	73.98 213	78.68 159	55.07 199	66.05 179	77.80 262	52.16 76	81.31 186	61.53 135	69.32 248	83.67 169

PS-MVSNAJ		70.51 107	69.70 110	72.93 140	81.52 86	55.79 113	74.92 198	79.00 150	55.04 201	69.88 107	78.66 248	47.05 136	82.19 170	61.61 131	79.58 115	80.83 227

iter_conf_final		69.82 121	68.02 140	75.23 80	79.38 128	52.91 155	80.11 98	73.96 239	54.99 202	68.04 139	83.59 151	29.05 310	87.16 54	65.41 98	77.62 142	85.63 103

xiu_mvs_v2_base		70.52 106	69.75 108	72.84 142	81.21 95	55.63 117	75.11 192	78.92 152	54.92 203	69.96 106	79.68 233	47.00 140	82.09 172	61.60 132	79.37 118	80.81 228

MAR-MVS		71.51 91	70.15 104	75.60 73	81.84 83	59.39 54	81.38 85	82.90 82	54.90 204	68.08 138	78.70 247	47.73 122	85.51 98	51.68 207	84.17 69	81.88 207
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
XVG-OURS-SEG-HR		68.81 144	67.47 154	72.82 144	74.40 242	56.87 98	70.59 264	79.04 149	54.77 205	66.99 161	86.01 103	39.57 211	78.21 240	62.54 122	73.33 189	83.37 177

iter_conf05		69.40 136	67.62 146	74.73 86	77.84 172	51.13 180	79.28 113	73.71 242	54.62 206	68.17 134	83.59 151	28.68 315	87.16 54	65.74 95	76.95 152	85.91 88

Anonymous20231211		69.28 137	68.47 132	71.73 161	80.28 108	47.18 239	79.98 100	82.37 88	54.61 207	67.24 156	84.01 142	39.43 212	82.41 168	55.45 174	72.83 197	85.62 104

SixPastTwentyTwo		61.65 249	58.80 258	70.20 195	75.80 216	47.22 238	75.59 182	69.68 270	54.61 207	54.11 315	79.26 242	27.07 326	82.96 148	43.27 275	49.79 353	80.41 233

test_0402		63.25 233	61.01 246	69.96 198	80.00 117	54.37 134	76.86 159	72.02 256	54.58 209	58.71 276	80.79 215	35.00 258	84.36 122	26.41 363	64.71 287	71.15 332

tttt0517		67.83 168	65.66 193	74.33 102	76.69 202	50.82 186	77.86 132	73.99 238	54.54 210	64.64 212	82.53 174	35.06 257	85.50 99	55.71 170	69.91 238	86.67 62

BH-w/o		66.85 188	65.83 190	69.90 202	79.29 129	52.46 165	74.66 204	76.65 200	54.51 211	64.85 209	78.12 254	45.59 151	82.95 149	43.26 276	75.54 165	74.27 302

AUN-MVS		68.45 155	66.41 178	74.57 96	79.53 125	57.08 96	73.93 217	75.23 218	54.44 212	66.69 168	81.85 191	37.10 242	82.89 151	62.07 126	66.84 271	83.75 166

LTVRE_ROB	55.42 16	63.15 235	61.23 244	68.92 218	76.57 206	47.80 230	59.92 328	76.39 201	54.35 213	58.67 277	82.46 176	29.44 308	81.49 182	42.12 285	71.14 218	77.46 266
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
ab-mvs		66.65 193	66.42 177	67.37 235	76.17 212	41.73 289	70.41 268	76.14 205	53.99 214	65.98 180	83.51 155	49.48 101	76.24 266	48.60 230	73.46 187	84.14 149

IU-MVS					87.77 4	59.15 59		85.53 25	53.93 215	84.64 3				79.07 10	90.87 5	88.37 12

XVG-ACMP-BASELINE		64.36 223	62.23 232	70.74 186	72.35 269	52.45 166	70.80 263	78.45 168	53.84 216	59.87 262	81.10 205	16.24 356	79.32 221	55.64 173	71.76 212	80.47 231

FE-MVS		65.91 202	63.33 219	73.63 122	77.36 189	51.95 175	72.62 235	75.81 208	53.70 217	65.31 194	78.96 245	28.81 314	86.39 78	43.93 269	73.48 186	82.55 193

thisisatest0530		67.92 166	65.78 191	74.33 102	76.29 210	51.03 181	76.89 158	74.25 235	53.67 218	65.59 190	81.76 193	35.15 256	85.50 99	55.94 165	72.47 202	86.47 67

PVSNet_BlendedMVS		68.56 153	67.72 143	71.07 181	77.03 197	50.57 190	74.50 206	81.52 99	53.66 219	64.22 219	79.72 232	49.13 107	82.87 153	55.82 167	73.92 176	79.77 245

patch_mono-2		69.85 120	71.09 89	66.16 249	79.11 137	54.80 131	71.97 246	74.31 233	53.50 220	70.90 92	84.17 137	57.63 29	63.31 320	66.17 88	82.02 90	80.38 234

EG-PatchMatch MVS		64.71 218	62.87 224	70.22 193	77.68 176	53.48 143	77.99 130	78.82 153	53.37 221	56.03 295	77.41 267	24.75 340	84.04 127	46.37 247	73.42 188	73.14 308

DP-MVS		65.68 204	63.66 214	71.75 160	84.93 55	56.87 98	80.74 92	73.16 247	53.06 222	59.09 273	82.35 177	36.79 246	85.94 88	32.82 335	69.96 237	72.45 316

TR-MVS		66.59 196	65.07 201	71.17 178	79.18 134	49.63 209	73.48 224	75.20 220	52.95 223	67.90 140	80.33 221	39.81 209	83.68 135	43.20 277	73.56 184	80.20 236

ET-MVSNet_ETH3D		67.96 165	65.72 192	74.68 89	76.67 203	55.62 119	75.11 192	74.74 227	52.91 224	60.03 259	80.12 224	33.68 271	82.64 162	61.86 129	76.34 158	85.78 93

QAPM		70.05 115	68.81 125	73.78 111	76.54 207	53.43 145	83.23 53	83.48 65	52.89 225	65.90 183	86.29 95	41.55 196	86.49 76	51.01 210	78.40 136	81.42 211

OpenMVS	61.03 9	68.85 143	67.56 147	72.70 146	74.26 245	53.99 136	81.21 87	81.34 110	52.70 226	62.75 232	85.55 115	38.86 220	84.14 125	48.41 232	83.01 76	79.97 240

pmmvs6		63.69 227	62.82 226	66.27 247	70.63 289	39.27 307	73.13 228	75.47 214	52.69 227	59.75 266	82.30 179	39.71 210	77.03 258	47.40 237	64.35 290	82.53 194

IterMVS		62.79 237	61.27 242	67.35 236	69.37 307	52.04 173	71.17 256	68.24 283	52.63 228	59.82 263	76.91 271	37.32 236	72.36 281	52.80 195	63.19 300	77.66 264
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
mvs_tets		68.18 160	66.36 180	73.63 122	75.61 220	55.35 124	80.77 91	78.56 162	52.48 229	64.27 217	84.10 140	27.45 323	81.84 176	63.45 116	70.56 225	83.69 168

jajsoiax		68.25 158	66.45 174	73.66 119	75.62 219	55.49 121	80.82 90	78.51 164	52.33 230	64.33 215	84.11 139	28.28 317	81.81 177	63.48 115	70.62 223	83.67 169

TAMVS		66.78 191	65.27 199	71.33 175	79.16 136	53.67 138	73.84 221	69.59 272	52.32 231	65.28 195	81.72 194	44.49 167	77.40 253	42.32 284	78.66 133	82.92 188

CDS-MVSNet		66.80 190	65.37 196	71.10 180	78.98 139	53.13 153	73.27 227	71.07 262	52.15 232	64.72 210	80.23 223	43.56 174	77.10 256	45.48 258	78.88 127	83.05 187
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PVSNet_Blended		68.59 149	67.72 143	71.19 177	77.03 197	50.57 190	72.51 238	81.52 99	51.91 233	64.22 219	77.77 264	49.13 107	82.87 153	55.82 167	79.58 115	80.14 238

mvs_anonymous		68.03 162	67.51 151	69.59 207	72.08 272	44.57 265	71.99 245	75.23 218	51.67 234	67.06 160	82.57 170	54.68 48	77.94 243	56.56 162	75.71 164	86.26 80

xiu_mvs_v1_base_debu		68.58 150	67.28 161	72.48 149	78.19 161	57.19 90	75.28 187	75.09 223	51.61 235	70.04 100	81.41 200	32.79 281	79.02 230	63.81 111	77.31 145	81.22 219

xiu_mvs_v1_base		68.58 150	67.28 161	72.48 149	78.19 161	57.19 90	75.28 187	75.09 223	51.61 235	70.04 100	81.41 200	32.79 281	79.02 230	63.81 111	77.31 145	81.22 219

xiu_mvs_v1_base_debi		68.58 150	67.28 161	72.48 149	78.19 161	57.19 90	75.28 187	75.09 223	51.61 235	70.04 100	81.41 200	32.79 281	79.02 230	63.81 111	77.31 145	81.22 219

MVSTER		67.16 182	65.58 195	71.88 158	70.37 294	49.70 205	70.25 270	78.45 168	51.52 238	69.16 121	80.37 218	38.45 223	82.50 165	60.19 141	71.46 216	83.44 176

CNLPA		65.43 208	64.02 208	69.68 205	78.73 146	58.07 77	77.82 134	70.71 265	51.49 239	61.57 250	83.58 154	38.23 227	70.82 288	43.90 270	70.10 234	80.16 237

原ACMM1				74.69 88	85.39 47	59.40 53		83.42 68	51.47 240	70.27 98	86.61 87	48.61 113	86.51 75	53.85 187	87.96 38	78.16 258

miper_enhance_ethall		67.11 183	66.09 187	70.17 196	69.21 309	45.98 249	72.85 232	78.41 171	51.38 241	65.65 188	75.98 286	51.17 88	81.25 187	60.82 137	69.32 248	83.29 180

MSDG		61.81 248	59.23 254	69.55 210	72.64 262	52.63 160	70.45 267	75.81 208	51.38 241	53.70 318	76.11 282	29.52 306	81.08 193	37.70 307	65.79 280	74.93 294

test20.03		53.87 297	54.02 296	53.41 329	61.47 349	28.11 368	61.30 320	59.21 329	51.34 243	52.09 327	77.43 266	33.29 276	58.55 339	29.76 353	60.27 320	73.58 307

MVSFormer		71.50 92	70.38 100	74.88 84	78.76 144	57.15 93	82.79 60	78.48 165	51.26 244	69.49 112	83.22 158	43.99 171	83.24 143	66.06 89	79.37 118	84.23 146

test_djsdf		69.45 134	67.74 142	74.58 95	74.57 238	54.92 129	82.79 60	78.48 165	51.26 244	65.41 193	83.49 156	38.37 224	83.24 143	66.06 89	69.25 251	85.56 105

bld_raw_dy_0_64		64.87 216	63.22 220	69.83 204	74.79 233	53.32 149	78.15 128	62.02 321	51.20 246	60.17 257	83.12 162	24.15 342	74.20 276	63.08 117	72.33 205	81.96 204

dmvs_testset		50.16 314	51.90 304	44.94 347	66.49 327	11.78 384	61.01 325	51.50 352	51.17 247	50.30 339	67.44 341	39.28 214	60.29 331	22.38 366	57.49 329	62.76 352

PAPM		67.92 166	66.69 171	71.63 165	78.09 164	49.02 215	77.09 152	81.24 116	51.04 248	60.91 253	83.98 143	47.71 123	84.99 108	40.81 292	79.32 121	80.90 226

miper_lstm_enhance		62.03 245	60.88 248	65.49 261	66.71 325	46.25 245	56.29 342	75.70 210	50.68 249	61.27 251	75.48 291	40.21 206	68.03 302	56.31 164	65.25 283	82.18 200

gg-mvs-nofinetune		57.86 272	56.43 278	62.18 284	72.62 263	35.35 340	66.57 287	56.33 340	50.65 250	57.64 285	57.10 361	30.65 297	76.36 264	37.38 309	78.88 127	74.82 296

TAPA-MVS	59.36 10	66.60 194	65.20 200	70.81 184	76.63 204	48.75 219	76.52 164	80.04 135	50.64 251	65.24 200	84.93 122	39.15 217	78.54 236	36.77 313	76.88 154	85.14 121
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
dmvs_re		56.77 279	56.83 274	56.61 312	69.23 308	41.02 294	58.37 333	64.18 307	50.59 252	57.45 287	71.42 316	35.54 253	58.94 337	37.23 310	67.45 267	69.87 341

MVP-Stereo		65.41 209	63.80 212	70.22 193	77.62 182	55.53 120	76.30 167	78.53 163	50.59 252	56.47 293	78.65 249	39.84 208	82.68 160	44.10 268	72.12 210	72.44 317
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PCF-MVS	61.88 8	70.95 99	69.49 114	75.35 76	77.63 178	55.71 114	76.04 175	81.81 96	50.30 254	69.66 110	85.40 119	52.51 69	84.89 113	51.82 204	80.24 108	85.45 110
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
baseline2		63.42 229	61.26 243	69.89 203	72.55 265	47.62 234	71.54 250	68.38 282	50.11 255	54.82 307	75.55 290	43.06 178	80.96 194	48.13 233	67.16 270	81.11 222

test-LLR		58.15 270	58.13 266	58.22 303	68.57 313	44.80 261	65.46 296	57.92 334	50.08 256	55.44 299	69.82 329	32.62 286	57.44 342	49.66 221	73.62 181	72.41 318

test0.0.03 1		53.32 302	53.59 299	52.50 333	62.81 345	29.45 364	59.51 329	54.11 347	50.08 256	54.40 313	74.31 300	32.62 286	55.92 351	30.50 350	63.95 293	72.15 323

COLMAP_ROB	52.97 17	61.27 254	58.81 257	68.64 221	74.63 236	52.51 164	78.42 125	73.30 245	49.92 258	50.96 331	81.51 199	23.06 344	79.40 219	31.63 343	65.85 278	74.01 305
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
tpmvs		58.47 266	56.95 272	63.03 280	70.20 295	41.21 293	67.90 283	67.23 288	49.62 259	54.73 309	70.84 320	34.14 266	76.24 266	36.64 317	61.29 313	71.64 326

thisisatest0515		65.83 203	63.50 216	72.82 144	73.75 248	49.50 210	71.32 253	73.12 248	49.39 260	63.82 221	76.50 280	34.95 259	84.84 116	53.20 193	75.49 166	84.13 150

HY-MVS	56.14 13	64.55 221	63.89 209	66.55 243	74.73 235	41.02 294	69.96 272	74.43 230	49.29 261	61.66 248	80.92 210	47.43 130	76.68 261	44.91 263	71.69 213	81.94 205

MIMVSNet1		55.17 292	54.31 293	57.77 308	70.03 299	32.01 358	65.68 294	64.81 302	49.19 262	46.75 348	76.00 283	25.53 336	64.04 318	28.65 357	62.13 307	77.26 270

SCA		60.49 256	58.38 262	66.80 239	74.14 247	48.06 228	63.35 309	63.23 313	49.13 263	59.33 272	72.10 310	37.45 233	74.27 274	44.17 265	62.57 304	78.05 260

test_fmvsmvis_n_1920		70.84 100	70.38 100	72.22 156	71.16 285	55.39 123	75.86 178	72.21 254	49.03 264	73.28 64	86.17 97	51.83 80	77.29 254	75.80 27	78.05 138	83.98 154

testgi		51.90 306	52.37 303	50.51 339	60.39 356	23.55 378	58.42 332	58.15 332	49.03 264	51.83 328	79.21 243	22.39 345	55.59 352	29.24 356	62.64 303	72.40 320

MIMVSNet		57.35 274	57.07 270	58.22 303	74.21 246	37.18 324	62.46 313	60.88 326	48.88 266	55.29 302	75.99 285	31.68 293	62.04 325	31.87 338	72.35 204	75.43 288

gm-plane-assit					71.40 283	41.72 291			48.85 267		73.31 305		82.48 167	48.90 228

cascas		65.98 201	63.42 217	73.64 121	77.26 191	52.58 161	72.26 242	77.21 192	48.56 268	61.21 252	74.60 298	32.57 289	85.82 91	50.38 215	76.75 156	82.52 195

PLC	56.13 14	65.09 214	63.21 221	70.72 187	81.04 98	54.87 130	78.57 122	77.47 186	48.51 269	55.71 296	81.89 190	33.71 270	79.71 214	41.66 289	70.37 228	77.58 265
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
LS3D		64.71 218	62.50 229	71.34 174	79.72 122	55.71 114	79.82 104	74.72 228	48.50 270	56.62 291	84.62 128	33.59 273	82.34 169	29.65 354	75.23 168	75.97 281

anonymousdsp		67.00 186	64.82 203	73.57 125	70.09 298	56.13 106	76.35 166	77.35 190	48.43 271	64.99 208	80.84 214	33.01 278	80.34 208	64.66 103	67.64 266	84.23 146

无先验							79.66 109	74.30 234	48.40 272				80.78 201	53.62 188		79.03 252

114514_t		70.83 101	69.56 111	74.64 92	86.21 31	54.63 132	82.34 69	81.81 96	48.22 273	63.01 229	85.83 109	40.92 204	87.10 58	57.91 154	79.79 111	82.18 200

tpm		57.34 275	58.16 264	54.86 319	71.80 277	34.77 342	67.47 286	56.04 343	48.20 274	60.10 258	76.92 270	37.17 239	53.41 358	40.76 293	65.01 284	76.40 280

test_fmvsm_n_1920		71.73 88	71.14 88	73.50 126	72.52 266	56.53 100	75.60 181	76.16 203	48.11 275	77.22 28	85.56 113	53.10 66	77.43 251	74.86 31	77.14 150	86.55 66

MDA-MVSNet-bldmvs		53.87 297	50.81 309	63.05 279	66.25 329	48.58 222	56.93 340	63.82 309	48.09 276	41.22 360	70.48 325	30.34 300	68.00 303	34.24 328	45.92 358	72.57 314

XXY-MVS		60.68 255	61.67 237	57.70 309	70.43 292	38.45 313	64.19 306	66.47 292	48.05 277	63.22 226	80.86 212	49.28 104	60.47 329	45.25 262	67.28 269	74.19 303

F-COLMAP		63.05 236	60.87 249	69.58 209	76.99 199	53.63 140	78.12 129	76.16 203	47.97 278	52.41 326	81.61 196	27.87 319	78.11 241	40.07 295	66.66 273	77.00 274

Patchmatch-RL test		58.16 269	55.49 283	66.15 250	67.92 318	48.89 218	60.66 326	51.07 355	47.86 279	59.36 269	62.71 355	34.02 268	72.27 283	56.41 163	59.40 322	77.30 268

D2MVS		62.30 242	60.29 251	68.34 226	66.46 328	48.42 224	65.70 293	73.42 244	47.71 280	58.16 282	75.02 294	30.51 298	77.71 248	53.96 186	71.68 214	78.90 254

ANet_high		41.38 329	37.47 336	53.11 330	39.73 380	24.45 376	56.94 339	69.69 269	47.65 281	26.04 372	52.32 364	12.44 362	62.38 324	21.80 367	10.61 381	72.49 315

CostFormer		64.04 224	62.51 228	68.61 222	71.88 275	45.77 250	71.30 254	70.60 266	47.55 282	64.31 216	76.61 276	41.63 193	79.62 217	49.74 219	69.00 255	80.42 232

PatchmatchNet		59.84 260	58.24 263	64.65 268	73.05 256	46.70 242	69.42 276	62.18 319	47.55 282	58.88 275	71.96 312	34.49 263	69.16 297	42.99 279	63.60 295	78.07 259
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
KD-MVS_self_test		55.22 291	53.89 297	59.21 296	57.80 361	27.47 370	57.75 337	74.32 232	47.38 284	50.90 332	70.00 328	28.45 316	70.30 293	40.44 294	57.92 327	79.87 242

ITE_SJBPF				62.09 285	66.16 330	44.55 266		64.32 306	47.36 285	55.31 301	80.34 220	19.27 351	62.68 323	36.29 321	62.39 306	79.04 251

KD-MVS_2432*1600		53.45 299	51.50 307	59.30 293	62.82 343	37.14 325	55.33 343	71.79 258	47.34 286	55.09 304	70.52 323	21.91 348	70.45 291	35.72 323	42.97 361	70.31 337

miper_refine_blended		53.45 299	51.50 307	59.30 293	62.82 343	37.14 325	55.33 343	71.79 258	47.34 286	55.09 304	70.52 323	21.91 348	70.45 291	35.72 323	42.97 361	70.31 337

OurMVSNet-221017-0		61.37 253	58.63 260	69.61 206	72.05 273	48.06 228	73.93 217	72.51 251	47.23 288	54.74 308	80.92 210	21.49 350	81.24 188	48.57 231	56.22 335	79.53 247

tpmrst		58.24 268	58.70 259	56.84 311	66.97 322	34.32 346	69.57 275	61.14 325	47.17 289	58.58 279	71.60 315	41.28 200	60.41 330	49.20 225	62.84 302	75.78 284

PVSNet	50.76 19	58.40 267	57.39 268	61.42 288	75.53 222	44.04 269	61.43 318	63.45 311	47.04 290	56.91 289	73.61 304	27.00 327	64.76 316	39.12 301	72.40 203	75.47 287

FMVSNet5		55.86 286	54.93 286	58.66 301	71.05 286	36.35 334	64.18 307	62.48 318	46.76 291	50.66 336	74.73 297	25.80 334	64.04 318	33.11 333	65.57 281	75.59 286

jason		69.65 128	68.39 135	73.43 131	78.27 159	56.88 97	77.12 151	73.71 242	46.53 292	69.34 116	83.22 158	43.37 175	79.18 223	64.77 102	79.20 123	84.23 146
jason: jason.
MS-PatchMatch		62.42 240	61.46 240	65.31 264	75.21 227	52.10 170	72.05 244	74.05 237	46.41 293	57.42 288	74.36 299	34.35 265	77.57 250	45.62 255	73.67 180	66.26 349

1112_ss		64.00 225	63.36 218	65.93 255	79.28 130	42.58 281	71.35 252	72.36 253	46.41 293	60.55 255	77.89 260	46.27 146	73.28 278	46.18 248	69.97 236	81.92 206

lupinMVS		69.57 130	68.28 136	73.44 130	78.76 144	57.15 93	76.57 162	73.29 246	46.19 295	69.49 112	82.18 181	43.99 171	79.23 222	64.66 103	79.37 118	83.93 155

testdata				64.66 267	81.52 86	52.93 154		65.29 300	46.09 296	73.88 56	87.46 71	38.08 229	66.26 312	53.31 192	78.48 135	74.78 297

UnsupCasMVSNet_eth		53.16 304	52.47 302	55.23 317	59.45 357	33.39 353	59.43 330	69.13 277	45.98 297	50.35 338	72.32 309	29.30 309	58.26 340	42.02 287	44.30 359	74.05 304

AllTest		57.08 277	54.65 288	64.39 270	71.44 280	49.03 213	69.92 273	67.30 285	45.97 298	47.16 345	79.77 230	17.47 352	67.56 304	33.65 330	59.16 323	76.57 278

TestCases				64.39 270	71.44 280	49.03 213		67.30 285	45.97 298	47.16 345	79.77 230	17.47 352	67.56 304	33.65 330	59.16 323	76.57 278

WTY-MVS		59.75 261	60.39 250	57.85 307	72.32 270	37.83 318	61.05 324	64.18 307	45.95 300	61.91 245	79.11 244	47.01 139	60.88 328	42.50 283	69.49 247	74.83 295

IterMVS-SCA-FT		62.49 238	61.52 239	65.40 262	71.99 274	50.80 187	71.15 258	69.63 271	45.71 301	60.61 254	77.93 257	37.45 233	65.99 313	55.67 171	63.50 297	79.42 248

旧先验2							76.08 172		45.32 302	76.55 31			65.56 315	58.75 152

OpenMVS_ROB	52.78 18	60.03 258	58.14 265	65.69 259	70.47 291	44.82 260	75.33 186	70.86 264	45.04 303	56.06 294	76.00 283	26.89 328	79.65 215	35.36 325	67.29 268	72.60 313

TinyColmap		54.14 294	51.72 305	61.40 289	66.84 324	41.97 286	66.52 288	68.51 281	44.81 304	42.69 359	75.77 287	11.66 364	72.94 279	31.96 337	56.77 333	69.27 345

MDTV_nov1_ep13			57.00 271		72.73 261	38.26 314	65.02 303	64.73 304	44.74 305	55.46 298	72.48 308	32.61 288	70.47 290	37.47 308	67.75 265

新几何1				70.76 185	85.66 41	61.13 30		66.43 293	44.68 306	70.29 97	86.64 85	41.29 199	75.23 269	49.72 220	81.75 95	75.93 282

Patchmtry		57.16 276	56.47 277	59.23 295	69.17 310	34.58 345	62.98 310	63.15 314	44.53 307	56.83 290	74.84 295	35.83 251	68.71 299	40.03 296	60.91 314	74.39 301

ppachtmachnet_test		58.06 271	55.38 284	66.10 252	69.51 304	48.99 216	68.01 282	66.13 295	44.50 308	54.05 316	70.74 321	32.09 292	72.34 282	36.68 316	56.71 334	76.99 276

PatchT		53.17 303	53.44 300	52.33 334	68.29 317	25.34 375	58.21 334	54.41 346	44.46 309	54.56 311	69.05 335	33.32 275	60.94 327	36.93 312	61.76 311	70.73 335

EPMVS		53.96 295	53.69 298	54.79 320	66.12 331	31.96 359	62.34 315	49.05 358	44.42 310	55.54 297	71.33 318	30.22 301	56.70 345	41.65 290	62.54 305	75.71 285

pmmvs4		61.48 252	59.39 253	67.76 230	71.57 279	53.86 137	71.42 251	65.34 299	44.20 311	59.46 268	77.92 258	35.90 250	74.71 271	43.87 271	64.87 286	74.71 298

dp		51.89 307	51.60 306	52.77 332	68.44 316	32.45 357	62.36 314	54.57 345	44.16 312	49.31 340	67.91 337	28.87 313	56.61 347	33.89 329	54.89 338	69.24 346

PatchMatch-RL		56.25 284	54.55 289	61.32 290	77.06 196	56.07 108	65.57 295	54.10 348	44.13 313	53.49 324	71.27 319	25.20 337	66.78 308	36.52 319	63.66 294	61.12 353

our_test_3		56.49 280	54.42 290	62.68 282	69.51 304	45.48 256	66.08 291	61.49 323	44.11 314	50.73 335	69.60 332	33.05 277	68.15 301	38.38 304	56.86 331	74.40 300

USDC		56.35 283	54.24 294	62.69 281	64.74 336	40.31 298	65.05 302	73.83 240	43.93 315	47.58 343	77.71 265	15.36 358	75.05 270	38.19 306	61.81 310	72.70 312

PM-MVS		52.33 305	50.19 313	58.75 300	62.10 347	45.14 259	65.75 292	40.38 372	43.60 316	53.52 322	72.65 307	9.16 372	65.87 314	50.41 214	54.18 341	65.24 351

pmmvs-eth3d		58.81 265	56.31 279	66.30 246	67.61 319	52.42 167	72.30 241	64.76 303	43.55 317	54.94 306	74.19 301	28.95 311	72.60 280	43.31 274	57.21 330	73.88 306

new-patchmatchnet		47.56 321	47.73 321	47.06 342	58.81 359	9.37 386	48.78 357	59.21 329	43.28 318	44.22 355	68.66 336	25.67 335	57.20 344	31.57 345	49.35 354	74.62 299

Test_1112_low_res		62.32 241	61.77 236	64.00 272	79.08 138	39.53 305	68.17 280	70.17 267	43.25 319	59.03 274	79.90 227	44.08 169	71.24 287	43.79 272	68.42 260	81.25 218

RPMNet		61.53 250	58.42 261	70.86 183	69.96 300	52.07 171	65.31 300	81.36 106	43.20 320	59.36 269	70.15 327	35.37 254	85.47 101	36.42 320	64.65 288	75.06 290

tpm2		62.07 244	60.10 252	67.99 228	72.79 260	43.86 270	71.05 261	66.85 291	43.14 321	62.77 230	75.39 292	38.32 225	80.80 200	41.69 288	68.88 256	79.32 249

JIA-IIPM		51.56 308	47.68 322	63.21 277	64.61 337	50.73 188	47.71 359	58.77 331	42.90 322	48.46 342	51.72 365	24.97 338	70.24 294	36.06 322	53.89 342	68.64 347

1314		64.61 220	63.21 221	68.80 219	71.87 276	47.46 236	73.95 215	78.39 173	42.88 323	59.97 260	76.60 277	38.11 228	79.39 220	54.84 178	72.32 206	79.55 246

HyFIR lowres test		65.67 205	63.01 223	73.67 118	79.97 118	55.65 116	69.07 278	75.52 213	42.68 324	63.53 224	77.95 256	40.43 205	81.64 178	46.01 250	71.91 211	83.73 167

CR-MVSNet		59.91 259	57.90 267	65.96 254	69.96 300	52.07 171	65.31 300	63.15 314	42.48 325	59.36 269	74.84 295	35.83 251	70.75 289	45.50 257	64.65 288	75.06 290

test222					83.14 68	58.68 72	72.57 237	63.45 311	41.78 326	67.56 152	86.12 98	37.13 241			78.73 132	74.98 293

TDRefinement		53.44 301	50.72 310	61.60 287	64.31 339	46.96 240	70.89 262	65.27 301	41.78 326	44.61 354	77.98 255	11.52 366	66.36 311	28.57 358	51.59 347	71.49 329

sss		56.17 285	56.57 276	54.96 318	66.93 323	36.32 336	57.94 335	61.69 322	41.67 328	58.64 278	75.32 293	38.72 221	56.25 349	42.04 286	66.19 277	72.31 321

PVSNet_0	43.31 20	47.46 322	45.64 325	52.92 331	67.60 320	44.65 263	54.06 347	54.64 344	41.59 329	46.15 350	58.75 358	30.99 295	58.66 338	32.18 336	24.81 374	55.46 361

MVS		67.37 175	66.33 181	70.51 191	75.46 223	50.94 182	73.95 215	81.85 95	41.57 330	62.54 237	78.57 252	47.98 118	85.47 101	52.97 194	82.05 89	75.14 289

Anonymous20240521		55.30 289	54.41 291	57.96 306	60.92 355	41.73 289	71.09 260	71.06 263	41.18 331	48.65 341	73.31 305	16.93 354	59.25 336	42.54 282	64.01 291	72.90 310

Anonymous20231206		55.10 293	55.30 285	54.48 321	69.81 303	33.94 350	62.91 311	62.13 320	41.08 332	55.18 303	75.65 288	32.75 284	56.59 348	30.32 351	67.86 263	72.91 309

MDA-MVSNet_test_wron		50.71 313	48.95 315	56.00 316	61.17 351	41.84 287	51.90 352	56.45 338	40.96 333	44.79 353	67.84 338	30.04 303	55.07 355	36.71 315	50.69 350	71.11 333

YYNet1		50.73 312	48.96 314	56.03 315	61.10 352	41.78 288	51.94 351	56.44 339	40.94 334	44.84 352	67.80 339	30.08 302	55.08 354	36.77 313	50.71 349	71.22 330

CHOSEN 1792x2688		65.08 215	62.84 225	71.82 159	81.49 88	56.26 104	66.32 290	74.20 236	40.53 335	63.16 228	78.65 249	41.30 198	77.80 246	45.80 252	74.09 174	81.40 214

pmmvs5		56.47 281	55.68 282	58.86 299	61.41 350	36.71 331	66.37 289	62.75 316	40.38 336	53.70 318	76.62 275	34.56 261	67.05 306	40.02 297	65.27 282	72.83 311

test_vis1_n_1920		58.86 264	59.06 256	58.25 302	63.76 340	43.14 277	67.49 285	66.36 294	40.22 337	65.89 184	71.95 313	31.04 294	59.75 334	59.94 144	64.90 285	71.85 325

MDTV_nov1_ep13_2view						25.89 373	61.22 321		40.10 338	51.10 330		32.97 279		38.49 303		78.61 255

tpm cat1		59.25 263	56.95 272	66.15 250	72.19 271	46.96 240	68.09 281	65.76 296	40.03 339	57.81 284	70.56 322	38.32 225	74.51 272	38.26 305	61.50 312	77.00 274

test-mter		56.42 282	55.82 281	58.22 303	68.57 313	44.80 261	65.46 296	57.92 334	39.94 340	55.44 299	69.82 329	21.92 347	57.44 342	49.66 221	73.62 181	72.41 318

UnsupCasMVSNet_bld		50.07 315	48.87 316	53.66 326	60.97 354	33.67 351	57.62 338	64.56 305	39.47 341	47.38 344	64.02 353	27.47 322	59.32 335	34.69 327	43.68 360	67.98 348

TESTMET0.1,1		55.28 290	54.90 287	56.42 313	66.56 326	43.67 272	65.46 296	56.27 341	39.18 342	53.83 317	67.44 341	24.21 341	55.46 353	48.04 234	73.11 194	70.13 339

ADS-MVSNet2		51.33 310	48.76 317	59.07 298	66.02 332	44.60 264	50.90 353	59.76 328	36.90 343	50.74 333	66.18 347	26.38 329	63.11 321	27.17 359	54.76 339	69.50 343

ADS-MVSNet		48.48 319	47.77 320	50.63 338	66.02 332	29.92 363	50.90 353	50.87 357	36.90 343	50.74 333	66.18 347	26.38 329	52.47 360	27.17 359	54.76 339	69.50 343

RPSCF		55.80 287	54.22 295	60.53 292	65.13 335	42.91 280	64.30 305	57.62 336	36.84 345	58.05 283	82.28 180	28.01 318	56.24 350	37.14 311	58.61 325	82.44 198

test_cas_vis1_n_1920		56.91 278	56.71 275	57.51 310	59.13 358	45.40 257	63.58 308	61.29 324	36.24 346	67.14 159	71.85 314	29.89 304	56.69 346	57.65 156	63.58 296	70.46 336

Patchmatch-test		49.08 317	48.28 319	51.50 337	64.40 338	30.85 362	45.68 363	48.46 361	35.60 347	46.10 351	72.10 310	34.47 264	46.37 368	27.08 361	60.65 318	77.27 269

CHOSEN 280x420		47.83 320	46.36 324	52.24 336	67.37 321	49.78 204	38.91 371	43.11 370	35.00 348	43.27 358	63.30 354	28.95 311	49.19 365	36.53 318	60.80 316	57.76 358

N_pmnet		39.35 333	40.28 331	36.54 356	63.76 340	1.62 390	49.37 356	0.76 390	34.62 349	43.61 357	66.38 346	26.25 331	42.57 372	26.02 364	51.77 346	65.44 350

PMMVS		53.96 295	53.26 301	56.04 314	62.60 346	50.92 184	61.17 322	56.09 342	32.81 350	53.51 323	66.84 345	34.04 267	59.93 333	44.14 267	68.18 261	57.27 359

CMPMVS	42.80 21	57.81 273	55.97 280	63.32 275	60.98 353	47.38 237	64.66 304	69.50 273	32.06 351	46.83 347	77.80 262	29.50 307	71.36 286	48.68 229	73.75 179	71.21 331
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CVMVSNet		59.63 262	59.14 255	61.08 291	74.47 239	38.84 310	75.20 190	68.74 280	31.15 352	58.24 281	76.51 278	32.39 290	68.58 300	49.77 218	65.84 279	75.81 283

FPMVS		42.18 328	41.11 330	45.39 344	58.03 360	41.01 296	49.50 355	53.81 349	30.07 353	33.71 367	64.03 351	11.69 363	52.08 363	14.01 374	55.11 337	43.09 370

EU-MVSNet		55.61 288	54.41 291	59.19 297	65.41 334	33.42 352	72.44 239	71.91 257	28.81 354	51.27 329	73.87 302	24.76 339	69.08 298	43.04 278	58.20 326	75.06 290

test_vis1_n		49.89 316	48.69 318	53.50 328	53.97 362	37.38 323	61.53 317	47.33 364	28.54 355	59.62 267	67.10 344	13.52 360	52.27 361	49.07 226	57.52 328	70.84 334

test_fmvs1_n		51.37 309	50.35 312	54.42 323	52.85 364	37.71 320	61.16 323	51.93 350	28.15 356	63.81 222	69.73 331	13.72 359	53.95 356	51.16 209	60.65 318	71.59 327

LF4IMVS		42.95 326	42.26 328	45.04 345	48.30 371	32.50 356	54.80 345	48.49 360	28.03 357	40.51 362	70.16 326	9.24 371	43.89 371	31.63 343	49.18 355	58.72 356

test_fmvs1		51.32 311	50.48 311	53.81 325	53.57 363	37.51 322	60.63 327	51.16 353	28.02 358	63.62 223	69.23 334	16.41 355	53.93 357	51.01 210	60.70 317	69.99 340

MVS-HIRNet		45.52 323	44.48 326	48.65 341	68.49 315	34.05 349	59.41 331	44.50 368	27.03 359	37.96 366	50.47 369	26.16 332	64.10 317	26.74 362	59.52 321	47.82 368

PMVS	28.69 22	36.22 336	33.29 340	45.02 346	36.82 382	35.98 339	54.68 346	48.74 359	26.31 360	21.02 375	51.61 366	2.88 384	60.10 332	9.99 380	47.58 356	38.99 375
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
pmmvs3		44.92 324	41.95 329	53.86 324	52.58 366	43.55 273	62.11 316	46.90 366	26.05 361	40.63 361	60.19 357	11.08 369	57.91 341	31.83 342	46.15 357	60.11 354

test_fmvs2		48.69 318	47.49 323	52.29 335	48.63 370	33.06 355	57.76 336	48.05 362	25.71 362	59.76 265	69.60 332	11.57 365	52.23 362	49.45 224	56.86 331	71.58 328

PMMVS2		27.40 344	25.91 347	31.87 360	39.46 381	6.57 387	31.17 374	28.52 381	23.96 363	20.45 376	48.94 372	4.20 380	37.94 376	16.51 371	19.97 376	51.09 363

Gipuma		34.77 337	31.91 341	43.33 349	62.05 348	37.87 316	20.39 376	67.03 289	23.23 364	18.41 377	25.84 377	4.24 378	62.73 322	14.71 373	51.32 348	29.38 376
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_vis1_rt		41.35 330	39.45 332	47.03 343	46.65 373	37.86 317	47.76 358	38.65 373	23.10 365	44.21 356	51.22 367	11.20 368	44.08 370	39.27 300	53.02 344	59.14 355

new_pmnet		34.13 338	34.29 339	33.64 358	52.63 365	18.23 383	44.43 366	33.90 378	22.81 366	30.89 369	53.18 363	10.48 370	35.72 379	20.77 368	39.51 365	46.98 369

mvsany_test1		39.38 332	38.16 335	43.02 350	49.05 368	34.28 347	44.16 367	25.94 383	22.74 367	46.57 349	62.21 356	23.85 343	41.16 375	33.01 334	35.91 369	53.63 362

LCM-MVSNet		40.30 331	35.88 337	53.57 327	42.24 375	29.15 365	45.21 365	60.53 327	22.23 368	28.02 370	50.98 368	3.72 381	61.78 326	31.22 348	38.76 367	69.78 342

test_fmvs3		44.30 325	42.55 327	49.55 340	42.83 374	27.15 371	53.03 349	44.93 367	22.03 369	53.69 320	64.94 350	4.21 379	49.63 364	47.47 235	49.82 352	71.88 324

APD_test1		37.39 335	34.94 338	44.72 348	48.88 369	33.19 354	52.95 350	44.00 369	19.49 370	27.28 371	58.59 359	3.18 383	52.84 359	18.92 369	41.17 364	48.14 367

mvsany_test3		32.62 339	30.57 343	38.77 354	36.16 383	24.20 377	38.10 372	20.63 385	19.14 371	40.36 363	57.43 360	5.06 376	36.63 378	29.59 355	28.66 373	55.49 360

E-PMN		23.77 345	22.73 349	26.90 361	42.02 376	20.67 380	42.66 368	35.70 376	17.43 372	10.28 382	25.05 378	6.42 374	42.39 373	10.28 379	14.71 378	17.63 377

EMVS		22.97 346	21.84 350	26.36 362	40.20 379	19.53 382	41.95 369	34.64 377	17.09 373	9.73 383	22.83 379	7.29 373	42.22 374	9.18 381	13.66 379	17.32 378

test_vis3_rt		32.09 340	30.20 344	37.76 355	35.36 384	27.48 369	40.60 370	28.29 382	16.69 374	32.52 368	40.53 373	1.96 385	37.40 377	33.64 332	42.21 363	48.39 365

test_f		31.86 341	31.05 342	34.28 357	32.33 386	21.86 379	32.34 373	30.46 380	16.02 375	39.78 365	55.45 362	4.80 377	32.36 380	30.61 349	37.66 368	48.64 364

DSMNet-mixed		39.30 334	38.72 333	41.03 351	51.22 367	19.66 381	45.53 364	31.35 379	15.83 376	39.80 364	67.42 343	22.19 346	45.13 369	22.43 365	52.69 345	58.31 357

testf1		31.46 342	28.89 345	39.16 352	41.99 377	28.78 366	46.45 361	37.56 374	14.28 377	21.10 373	48.96 370	1.48 387	47.11 366	13.63 375	34.56 370	41.60 371

APD_test2		31.46 342	28.89 345	39.16 352	41.99 377	28.78 366	46.45 361	37.56 374	14.28 377	21.10 373	48.96 370	1.48 387	47.11 366	13.63 375	34.56 370	41.60 371

MVE	17.77 23	21.41 347	17.77 352	32.34 359	34.34 385	25.44 374	16.11 377	24.11 384	11.19 379	13.22 379	31.92 375	1.58 386	30.95 381	10.47 378	17.03 377	40.62 374
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX				12.03 365	17.97 387	10.91 385		10.60 388	7.46 380	11.07 381	28.36 376	3.28 382	11.29 384	8.01 382	9.74 383	13.89 379

wuyk23d		13.32 350	12.52 353	15.71 364	47.54 372	26.27 372	31.06 375	1.98 389	4.93 381	5.18 384	1.94 384	0.45 389	18.54 383	6.81 383	12.83 380	2.33 381

test_method		19.68 348	18.10 351	24.41 363	13.68 388	3.11 389	12.06 379	42.37 371	2.00 382	11.97 380	36.38 374	5.77 375	29.35 382	15.06 372	23.65 375	40.76 373

tmp_tt		9.43 351	11.14 354	4.30 366	2.38 389	4.40 388	13.62 378	16.08 387	0.39 383	15.89 378	13.06 380	15.80 357	5.54 385	12.63 377	10.46 382	2.95 380

EGC-MVSNET		42.47 327	38.48 334	54.46 322	74.33 243	48.73 220	70.33 269	51.10 354	0.03 384	0.18 385	67.78 340	13.28 361	66.49 310	18.91 370	50.36 351	48.15 366

testmvs		4.52 354	6.03 357	0.01 368	0.01 390	0.00 392	53.86 348	0.00 391	0.01 385	0.04 386	0.27 385	0.00 391	0.00 386	0.04 384	0.00 384	0.03 383

test123		4.73 353	6.30 356	0.02 367	0.01 390	0.01 391	56.36 341	0.00 391	0.01 385	0.04 386	0.21 386	0.01 390	0.00 386	0.03 385	0.00 384	0.04 382

test_blank		0.00 356	0.00 359	0.00 369	0.00 392	0.00 392	0.00 380	0.00 391	0.00 387	0.00 388	0.00 387	0.00 391	0.00 386	0.00 386	0.00 384	0.00 384

uanet_test		0.00 356	0.00 359	0.00 369	0.00 392	0.00 392	0.00 380	0.00 391	0.00 387	0.00 388	0.00 387	0.00 391	0.00 386	0.00 386	0.00 384	0.00 384

DCPMVS		0.00 356	0.00 359	0.00 369	0.00 392	0.00 392	0.00 380	0.00 391	0.00 387	0.00 388	0.00 387	0.00 391	0.00 386	0.00 386	0.00 384	0.00 384

cdsmvs_eth3d_5k		17.50 349	23.34 348	0.00 369	0.00 392	0.00 392	0.00 380	78.63 160	0.00 387	0.00 388	82.18 181	49.25 105	0.00 386	0.00 386	0.00 384	0.00 384

pcd_1.5k_mvsjas		3.92 355	5.23 358	0.00 369	0.00 392	0.00 392	0.00 380	0.00 391	0.00 387	0.00 388	0.00 387	47.05 136	0.00 386	0.00 386	0.00 384	0.00 384

sosnet-low-res		0.00 356	0.00 359	0.00 369	0.00 392	0.00 392	0.00 380	0.00 391	0.00 387	0.00 388	0.00 387	0.00 391	0.00 386	0.00 386	0.00 384	0.00 384

sosnet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 392	0.00 380	0.00 391	0.00 387	0.00 388	0.00 387	0.00 391	0.00 386	0.00 386	0.00 384	0.00 384

uncertanet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 392	0.00 380	0.00 391	0.00 387	0.00 388	0.00 387	0.00 391	0.00 386	0.00 386	0.00 384	0.00 384

Regformer		0.00 356	0.00 359	0.00 369	0.00 392	0.00 392	0.00 380	0.00 391	0.00 387	0.00 388	0.00 387	0.00 391	0.00 386	0.00 386	0.00 384	0.00 384

ab-mvs-re		6.49 352	8.65 355	0.00 369	0.00 392	0.00 392	0.00 380	0.00 391	0.00 387	0.00 388	77.89 260	0.00 391	0.00 386	0.00 386	0.00 384	0.00 384

uanet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 392	0.00 380	0.00 391	0.00 387	0.00 388	0.00 387	0.00 391	0.00 386	0.00 386	0.00 384	0.00 384

MSC_two_6792asdad				79.95 3	87.24 14	61.04 31		85.62 23					90.96 1	79.31 8	90.65 8	87.85 26

No_MVS				79.95 3	87.24 14	61.04 31		85.62 23					90.96 1	79.31 8	90.65 8	87.85 26

eth-test2					0.00 392

eth-test					0.00 392

OPU-MVS				79.83 6	87.54 11	60.93 35	87.82 7				89.89 41	67.01 1	90.33 11	73.16 44	91.15 4	88.23 15

test_0728_SECOND				79.19 15	87.82 3	59.11 62	87.85 5	87.15 3					90.84 3	78.66 14	90.61 11	87.62 36

GSMVS																78.05 260

test_part2					87.58 9	60.47 42				83.42 12

sam_mvs1												34.74 260				78.05 260

sam_mvs												33.43 274

ambc				65.13 265	63.72 342	37.07 327	47.66 360	78.78 156		54.37 314	71.42 316	11.24 367	80.94 195	45.64 254	53.85 343	77.38 267

MTGPA								80.97 122

test_post1							68.67 279				3.64 382	32.39 290	69.49 296	44.17 265

test_post											3.55 383	33.90 269	66.52 309

patchmatchnet-post											64.03 351	34.50 262	74.27 274

GG-mvs-BLEND				62.34 283	71.36 284	37.04 328	69.20 277	57.33 337		54.73 309	65.48 349	30.37 299	77.82 245	34.82 326	74.93 169	72.17 322

MTMP							86.03 18	17.08 386

test9_res														75.28 29	88.31 32	83.81 161

agg_prior2														73.09 45	87.93 39	84.33 142

agg_prior					85.04 50	59.96 46		81.04 120		74.68 46			84.04 127

test_prior4						62.51 14	82.08 76

test_prior				76.69 52	84.20 61	57.27 87		84.88 37					86.43 77			86.38 68

新几何2							76.12 170

旧先验1					83.04 70	53.15 151		67.52 284			87.85 68	44.08 169			80.76 99	78.03 263

原ACMM2							79.02 115

testdata2													72.18 285	46.95 244

segment_acmp												54.23 52

test12				77.76 42	84.52 58	58.41 74		83.36 71		72.93 72		54.61 49	88.05 36		88.12 35	86.81 59

plane_prior7					81.41 89	55.96 110

plane_prior6					81.20 96	56.24 105						45.26 160

plane_prior5								84.01 49					87.21 52	68.16 71	80.58 102	84.65 136

plane_prior4											86.10 99

plane_prior1					81.27 94

n2								0.00 391

nn								0.00 391

door-mid								47.19 365

lessismore_v0				69.91 201	71.42 282	47.80 230		50.90 356		50.39 337	75.56 289	27.43 324	81.33 185	45.91 251	34.10 372	80.59 230

test11								83.47 66

door								47.60 363

HQP5-MVS						54.94 127

BP-MVS														67.04 83

HQP4-MVS										67.85 142			86.93 61			84.32 143

HQP3-MVS								83.90 53							80.35 106

HQP2-MVS												45.46 154

NP-MVS					80.98 99	56.05 109					85.54 116

ACMMP++_ref															74.07 175

ACMMP++															72.16 209

Test By Simon												48.33 116

High-resolution multi-view benchmark