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.

MM		89.16 7	89.23 9	88.97 4	90.79 103	73.65 10	92.66 28	91.17 153	86.57 1	87.39 58	94.97 25	71.70 64	97.68 1	92.19 1	95.63 31	95.57 1

UA-Net		85.08 85	84.96 85	85.45 90	92.07 80	68.07 146	89.78 91	90.86 164	82.48 2	84.60 93	93.20 88	69.35 99	95.22 89	71.39 237	90.88 117	93.07 144

MGCNet		87.69 24	87.55 29	88.12 13	89.45 140	71.76 54	91.47 57	89.54 210	82.14 3	86.65 67	94.28 46	68.28 122	97.46 6	90.81 6	95.31 37	95.15 8

CANet		86.45 48	86.10 61	87.51 42	90.09 116	70.94 77	89.70 94	92.59 80	81.78 4	81.32 161	91.43 148	70.34 81	97.23 16	84.26 75	93.36 73	94.37 64

NCCC		88.06 18	88.01 22	88.24 11	94.41 26	73.62 11	91.22 62	92.83 66	81.50 5	85.79 73	93.47 81	73.02 46	97.00 21	84.90 64	94.94 43	94.10 79

EPNet		83.72 113	82.92 128	86.14 73	84.22 335	69.48 102	91.05 64	85.27 336	81.30 6	76.83 254	91.65 136	66.09 151	95.56 69	76.00 183	93.85 67	93.38 122
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CNVR-MVS		88.93 12	89.13 13	88.33 8	94.77 12	73.82 8	90.51 70	93.00 52	80.90 7	88.06 44	94.06 59	76.43 20	96.84 25	88.48 36	95.99 18	94.34 66

3Dnovator+	77.84 4	85.48 73	84.47 93	88.51 7	91.08 94	73.49 16	93.18 16	93.78 23	80.79 8	76.66 259	93.37 84	60.40 240	96.75 30	77.20 164	93.73 69	95.29 6

TranMVSNet+NR-MVSNet		80.84 180	80.31 177	82.42 243	87.85 214	62.33 310	87.74 184	91.33 148	80.55 9	77.99 228	89.86 194	65.23 160	92.62 230	67.05 284	75.24 381	92.30 181

MSP-MVS		89.51 5	89.91 6	88.30 10	94.28 34	73.46 17	92.90 21	94.11 10	80.27 10	91.35 16	94.16 54	78.35 14	96.77 28	89.59 17	94.22 65	94.67 41
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++		89.02 10	89.15 12	88.63 5	95.01 9	76.03 1	92.38 32	92.85 65	80.26 11	87.78 49	94.27 47	75.89 23	96.81 27	87.45 47	96.44 9	93.05 147

fmvsm_s_conf0.5_n_9		87.39 33	87.95 23	85.70 82	89.48 139	67.88 154	88.59 147	89.05 238	80.19 12	90.70 20	95.40 17	74.56 29	93.92 153	91.54 2	92.07 92	95.31 5

UniMVSNet_NR-MVSNet		81.88 155	81.54 154	82.92 222	88.46 186	63.46 284	87.13 206	92.37 88	80.19 12	78.38 217	89.14 219	71.66 66	93.05 215	70.05 252	76.46 354	92.25 183

SteuartSystems-ACMMP		88.72 14	88.86 14	88.32 9	92.14 79	72.96 25	93.73 5	93.67 25	80.19 12	88.10 43	94.80 27	73.76 38	97.11 17	87.51 46	95.82 24	94.90 17
Skip Steuart: Steuart Systems R&D Blog.
EI-MVSNet-Vis-set		84.19 97	83.81 106	85.31 95	88.18 196	67.85 155	87.66 185	89.73 204	80.05 15	82.95 132	89.59 208	70.74 78	94.82 110	80.66 118	84.72 236	93.28 128

ETV-MVS		84.90 89	84.67 89	85.59 87	89.39 144	68.66 128	88.74 140	92.64 78	79.97 16	84.10 105	85.71 319	69.32 100	95.38 83	80.82 113	91.37 106	92.72 160

fmvsm_s_conf0.5_n_8		86.56 47	87.17 38	84.73 124	87.76 223	65.62 215	89.20 114	92.21 104	79.94 17	89.74 27	94.86 26	68.63 116	94.20 138	90.83 5	91.39 105	94.38 63

EI-MVSNet-UG-set		83.81 107	83.38 118	85.09 105	87.87 213	67.53 167	87.44 198	89.66 205	79.74 18	82.23 145	89.41 217	70.24 84	94.74 116	79.95 124	83.92 251	92.99 152

fmvsm_s_conf0.5_n_3		86.36 53	87.46 32	83.09 211	87.08 264	65.21 228	89.09 123	90.21 187	79.67 19	89.98 24	95.02 24	73.17 43	91.71 273	91.30 3	91.60 100	92.34 178

CS-MVS		86.69 44	86.95 42	85.90 79	90.76 104	67.57 165	92.83 22	93.30 38	79.67 19	84.57 94	92.27 109	71.47 67	95.02 101	84.24 77	93.46 72	95.13 10

casdiffmvs_mvg		85.99 59	86.09 62	85.70 82	87.65 231	67.22 181	88.69 143	93.04 47	79.64 21	85.33 77	92.54 105	73.30 40	94.50 126	83.49 83	91.14 110	95.37 2
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MTAPA		87.23 36	87.00 39	87.90 22	94.18 39	74.25 5	86.58 231	92.02 113	79.45 22	85.88 71	94.80 27	68.07 124	96.21 51	86.69 52	95.34 35	93.23 129

EC-MVSNet		86.01 58	86.38 52	84.91 115	89.31 149	66.27 196	92.32 35	93.63 26	79.37 23	84.17 104	91.88 125	69.04 111	95.43 78	83.93 81	93.77 68	93.01 150

NormalMVS		86.29 54	85.88 65	87.52 41	93.26 56	72.47 38	91.65 47	92.19 107	79.31 24	84.39 97	92.18 115	64.64 166	95.53 72	80.70 116	94.65 51	94.56 54

SymmetryMVS		85.38 78	84.81 87	87.07 51	91.47 88	72.47 38	91.65 47	88.06 273	79.31 24	84.39 97	92.18 115	64.64 166	95.53 72	80.70 116	90.91 116	93.21 132

XVS		87.18 37	86.91 44	88.00 17	94.42 24	73.33 19	92.78 23	92.99 55	79.14 26	83.67 115	94.17 53	67.45 130	96.60 38	83.06 87	94.50 56	94.07 81

X-MVStestdata		80.37 203	77.83 242	88.00 17	94.42 24	73.33 19	92.78 23	92.99 55	79.14 26	83.67 115	12.47 512	67.45 130	96.60 38	83.06 87	94.50 56	94.07 81

HQP_MVS		83.64 116	83.14 121	85.14 100	90.08 117	68.71 124	91.25 60	92.44 83	79.12 28	78.92 204	91.00 165	60.42 238	95.38 83	78.71 146	86.32 206	91.33 216

plane_prior2							91.25 60		79.12 28

IS-MVSNet		83.15 132	82.81 129	84.18 157	89.94 124	63.30 288	91.59 51	88.46 266	79.04 30	79.49 193	92.16 117	65.10 161	94.28 132	67.71 275	91.86 98	94.95 14

DU-MVS		81.12 175	80.52 172	82.90 223	87.80 217	63.46 284	87.02 211	91.87 123	79.01 31	78.38 217	89.07 221	65.02 162	93.05 215	70.05 252	76.46 354	92.20 186

NR-MVSNet		80.23 207	79.38 204	82.78 233	87.80 217	63.34 287	86.31 243	91.09 157	79.01 31	72.17 349	89.07 221	67.20 133	92.81 227	66.08 291	75.65 367	92.20 186

SPE-MVS-test		86.29 54	86.48 51	85.71 81	91.02 96	67.21 182	92.36 34	93.78 23	78.97 33	83.51 122	91.20 156	70.65 80	95.15 92	81.96 102	94.89 45	94.77 29

DELS-MVS		85.41 76	85.30 80	85.77 80	88.49 184	67.93 153	85.52 271	93.44 32	78.70 34	83.63 117	89.03 223	74.57 28	95.71 67	80.26 122	94.04 66	93.66 105
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
WR-MVS		79.49 220	79.22 211	80.27 298	88.79 174	58.35 368	85.06 281	88.61 264	78.56 35	77.65 235	88.34 246	63.81 175	90.66 325	64.98 300	77.22 342	91.80 200

plane_prior3						68.60 129			78.44 36	78.92 204

UniMVSNet (Re)		81.60 163	81.11 159	83.09 211	88.38 190	64.41 258	87.60 186	93.02 51	78.42 37	78.56 212	88.16 252	69.78 93	93.26 197	69.58 259	76.49 353	91.60 206

DVP-MVS++		90.23 1	91.01 1	87.89 24	94.34 31	71.25 65	95.06 1	94.23 6	78.38 38	92.78 4	95.74 8	82.45 3	97.49 4	89.42 19	96.68 2	94.95 14

test_0728_THIRD									78.38 38	92.12 11	95.78 6	81.46 8	97.40 9	89.42 19	96.57 7	94.67 41

testing3-2		75.12 321	75.19 303	74.91 396	90.40 110	45.09 479	80.29 384	78.42 431	78.37 40	76.54 264	87.75 262	44.36 406	87.28 383	57.04 387	83.49 263	92.37 177

test_one_0601					95.07 7	71.46 60		94.14 9	78.27 41	92.05 13	95.74 8	80.83 12

hybridcas		85.11 83	85.18 82	84.90 116	87.47 243	65.68 213	88.53 151	92.38 87	77.91 42	84.27 101	92.48 106	72.19 56	93.88 158	80.37 119	90.97 113	95.15 8

SD-MVS		88.06 18	88.50 18	86.71 61	92.60 76	72.71 29	91.81 46	93.19 41	77.87 43	90.32 23	94.00 63	74.83 27	93.78 161	87.63 45	94.27 64	93.65 109
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
casdiffmvs		85.11 83	85.14 83	85.01 108	87.20 255	65.77 212	87.75 183	92.83 66	77.84 44	84.36 100	92.38 108	72.15 57	93.93 152	81.27 109	90.48 122	95.33 4
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
KinetiMVS		83.31 130	82.61 134	85.39 93	87.08 264	67.56 166	88.06 171	91.65 136	77.80 45	82.21 146	91.79 128	57.27 265	94.07 144	77.77 157	89.89 135	94.56 54

BP-MVS1		84.32 92	83.71 109	86.17 69	87.84 215	67.85 155	89.38 109	89.64 207	77.73 46	83.98 108	92.12 120	56.89 270	95.43 78	84.03 80	91.75 99	95.24 7

CP-MVSNet		78.22 255	78.34 229	77.84 360	87.83 216	54.54 426	87.94 176	91.17 153	77.65 47	73.48 330	88.49 242	62.24 201	88.43 368	62.19 333	74.07 390	90.55 247

plane_prior						68.71 124	90.38 78		77.62 48						86.16 211

baseline		84.93 87	84.98 84	84.80 121	87.30 253	65.39 221	87.30 203	92.88 63	77.62 48	84.04 107	92.26 110	71.81 61	93.96 146	81.31 107	90.30 125	95.03 12

VDD-MVS		83.01 137	82.36 139	84.96 110	91.02 96	66.40 193	88.91 128	88.11 269	77.57 50	84.39 97	93.29 86	52.19 313	93.91 154	77.05 167	88.70 157	94.57 52

MP-MVS		87.71 23	87.64 26	87.93 21	94.36 30	73.88 6	92.71 27	92.65 76	77.57 50	83.84 111	94.40 41	72.24 55	96.28 48	85.65 59	95.30 38	93.62 112
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PEN-MVS		77.73 270	77.69 250	77.84 360	87.07 266	53.91 431	87.91 178	91.18 152	77.56 52	73.14 334	88.82 232	61.23 222	89.17 353	59.95 355	72.37 405	90.43 252

OPM-MVS		83.50 122	82.95 127	85.14 100	88.79 174	70.95 76	89.13 121	91.52 142	77.55 53	80.96 169	91.75 131	60.71 230	94.50 126	79.67 133	86.51 204	89.97 279
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DeepPCF-MVS	80.84 1	88.10 16	88.56 17	86.73 60	92.24 78	69.03 111	89.57 99	93.39 35	77.53 54	89.79 25	94.12 56	78.98 13	96.58 40	85.66 58	95.72 27	94.58 50

PS-CasMVS		78.01 264	78.09 234	77.77 362	87.71 226	54.39 428	88.02 172	91.22 150	77.50 55	73.26 332	88.64 237	60.73 229	88.41 369	61.88 338	73.88 394	90.53 248

MSLP-MVS++		85.43 75	85.76 69	84.45 136	91.93 82	70.24 86	90.71 67	92.86 64	77.46 56	84.22 102	92.81 100	67.16 134	92.94 219	80.36 120	94.35 62	90.16 263

RRT-MVS		82.60 145	82.10 145	84.10 159	87.98 209	62.94 300	87.45 193	91.27 149	77.42 57	79.85 188	90.28 186	56.62 273	94.70 119	79.87 130	88.15 170	94.67 41

fmvsm_s_conf0.5_n_11		86.06 56	86.75 47	84.00 176	87.78 220	66.09 198	89.96 86	90.80 166	77.37 58	86.72 66	94.20 52	72.51 52	92.78 228	89.08 22	92.33 87	93.13 141

DVP-MVS		89.60 4	90.35 4	87.33 45	95.27 5	71.25 65	93.49 10	92.73 70	77.33 59	92.12 11	95.78 6	80.98 10	97.40 9	89.08 22	96.41 12	93.33 126
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 5	71.25 65	93.60 7	94.11 10	77.33 59	92.81 3	95.79 5	80.98 10

MED-MVS		89.75 3	90.37 3	87.89 24	94.57 17	71.43 61	93.28 12	94.36 3	77.30 61	92.25 9	95.87 3	81.59 7	97.39 11	88.15 39	95.96 19	94.85 23

TestfortrainingZip a		88.83 13	89.21 11	87.68 37	94.57 17	71.25 65	93.28 12	93.91 19	77.30 61	91.13 18	95.87 3	77.62 16	96.95 22	86.12 57	93.07 75	94.85 23

BridgeMVS		86.78 42	86.99 40	86.15 71	91.24 91	67.61 163	90.51 70	92.90 62	77.26 63	87.44 57	91.63 138	71.27 71	96.06 55	85.62 60	95.01 40	94.78 28

SED-MVS		90.08 2	90.85 2	87.77 28	95.30 2	70.98 73	93.57 8	94.06 14	77.24 64	93.10 1	95.72 10	82.99 1	97.44 7	89.07 25	96.63 4	94.88 18

test_241102_TWO								94.06 14	77.24 64	92.78 4	95.72 10	81.26 9	97.44 7	89.07 25	96.58 6	94.26 72

3Dnovator	76.31 5	83.38 126	82.31 140	86.59 62	87.94 210	72.94 28	90.64 68	92.14 112	77.21 66	75.47 285	92.83 98	58.56 252	94.72 117	73.24 215	92.71 81	92.13 193

test_241102_ONE					95.30 2	70.98 73		94.06 14	77.17 67	93.10 1	95.39 18	82.99 1	97.27 14

WR-MVS_H		78.51 250	78.49 224	78.56 344	88.02 206	56.38 403	88.43 153	92.67 73	77.14 68	73.89 324	87.55 270	66.25 147	89.24 351	58.92 367	73.55 397	90.06 273

lecture		88.09 17	88.59 16	86.58 63	93.26 56	69.77 97	93.70 6	94.16 8	77.13 69	89.76 26	95.52 16	72.26 54	96.27 49	86.87 50	94.65 51	93.70 104

DeepC-MVS	79.81 2	87.08 40	86.88 45	87.69 36	91.16 92	72.32 45	90.31 79	93.94 18	77.12 70	82.82 137	94.23 50	72.13 58	97.09 18	84.83 67	95.37 34	93.65 109
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
FC-MVSNet-test		81.52 167	82.02 148	80.03 305	88.42 189	55.97 409	87.95 175	93.42 34	77.10 71	77.38 240	90.98 167	69.96 90	91.79 268	68.46 271	84.50 239	92.33 179

DTE-MVSNet		76.99 286	76.80 270	77.54 369	86.24 285	53.06 441	87.52 188	90.66 169	77.08 72	72.50 343	88.67 236	60.48 237	89.52 345	57.33 384	70.74 417	90.05 274

LFMVS		81.82 157	81.23 157	83.57 192	91.89 83	63.43 286	89.84 87	81.85 391	77.04 73	83.21 125	93.10 89	52.26 312	93.43 190	71.98 232	89.95 133	93.85 93

casdiffseed414692147		83.62 118	83.02 124	85.40 92	87.31 252	67.50 168	88.70 142	91.72 132	76.97 74	82.77 139	91.72 132	66.85 137	93.71 168	73.06 217	88.12 171	94.98 13

UGNet		80.83 181	79.59 200	84.54 128	88.04 205	68.09 145	89.42 106	88.16 268	76.95 75	76.22 271	89.46 213	49.30 362	93.94 149	68.48 270	90.31 124	91.60 206
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
FIs		82.07 151	82.42 136	81.04 279	88.80 173	58.34 369	88.26 164	93.49 31	76.93 76	78.47 216	91.04 162	69.92 91	92.34 248	69.87 256	84.97 232	92.44 176

GST-MVS		87.42 31	87.26 34	87.89 24	94.12 40	72.97 24	92.39 31	93.43 33	76.89 77	84.68 87	93.99 65	70.67 79	96.82 26	84.18 79	95.01 40	93.90 91

mPP-MVS		86.67 46	86.32 53	87.72 33	94.41 26	73.55 13	92.74 25	92.22 102	76.87 78	82.81 138	94.25 49	66.44 144	96.24 50	82.88 92	94.28 63	93.38 122

ZNCC-MVS		87.94 22	87.85 24	88.20 12	94.39 28	73.33 19	93.03 19	93.81 22	76.81 79	85.24 78	94.32 44	71.76 62	96.93 23	85.53 61	95.79 25	94.32 68

VPNet		78.69 245	78.66 221	78.76 339	88.31 192	55.72 413	84.45 299	86.63 317	76.79 80	78.26 220	90.55 179	59.30 246	89.70 343	66.63 286	77.05 344	90.88 232

HFP-MVS		87.58 26	87.47 31	87.94 19	94.58 16	73.54 15	93.04 17	93.24 39	76.78 81	84.91 83	94.44 39	70.78 77	96.61 37	84.53 72	94.89 45	93.66 105

ACMMPR		87.44 29	87.23 36	88.08 15	94.64 13	73.59 12	93.04 17	93.20 40	76.78 81	84.66 90	94.52 32	68.81 113	96.65 35	84.53 72	94.90 44	94.00 85

ACMMP		85.89 65	85.39 76	87.38 44	93.59 49	72.63 33	92.74 25	93.18 45	76.78 81	80.73 175	93.82 72	64.33 169	96.29 47	82.67 99	90.69 119	93.23 129
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
region2R		87.42 31	87.20 37	88.09 14	94.63 14	73.55 13	93.03 19	93.12 46	76.73 84	84.45 95	94.52 32	69.09 107	96.70 31	84.37 74	94.83 48	94.03 83

sasdasda		85.91 63	85.87 67	86.04 75	89.84 126	69.44 106	90.45 76	93.00 52	76.70 85	88.01 46	91.23 152	73.28 41	93.91 154	81.50 105	88.80 153	94.77 29

canonicalmvs		85.91 63	85.87 67	86.04 75	89.84 126	69.44 106	90.45 76	93.00 52	76.70 85	88.01 46	91.23 152	73.28 41	93.91 154	81.50 105	88.80 153	94.77 29

CP-MVS		87.11 38	86.92 43	87.68 37	94.20 38	73.86 7	93.98 3	92.82 69	76.62 87	83.68 114	94.46 36	67.93 125	95.95 63	84.20 78	94.39 60	93.23 129

DeepC-MVS_fast	79.65 3	86.91 41	86.62 50	87.76 29	93.52 50	72.37 43	91.26 59	93.04 47	76.62 87	84.22 102	93.36 85	71.44 68	96.76 29	80.82 113	95.33 36	94.16 75
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TestfortrainingZip				87.28 46	92.85 68	72.05 50	93.28 12	93.32 37	76.52 89	88.91 32	93.52 77	77.30 17	96.67 33		91.98 94	93.13 141

E5new		84.22 93	84.12 96	84.51 131	87.60 233	65.36 223	87.45 193	92.31 91	76.51 90	83.53 118	92.26 110	69.25 104	93.50 181	79.88 126	88.26 164	94.69 36

E6new		84.22 93	84.12 96	84.52 129	87.60 233	65.36 223	87.45 193	92.30 93	76.51 90	83.53 118	92.26 110	69.26 102	93.49 183	79.88 126	88.26 164	94.69 36

E6		84.22 93	84.12 96	84.52 129	87.60 233	65.36 223	87.45 193	92.30 93	76.51 90	83.53 118	92.26 110	69.26 102	93.49 183	79.88 126	88.26 164	94.69 36

E5		84.22 93	84.12 96	84.51 131	87.60 233	65.36 223	87.45 193	92.31 91	76.51 90	83.53 118	92.26 110	69.25 104	93.50 181	79.88 126	88.26 164	94.69 36

MGCFI-Net		85.06 86	85.51 74	83.70 187	89.42 141	63.01 294	89.43 104	92.62 79	76.43 94	87.53 54	91.34 150	72.82 50	93.42 191	81.28 108	88.74 156	94.66 44

TSAR-MVS + GP.		85.71 69	85.33 78	86.84 57	91.34 89	72.50 36	89.07 124	87.28 294	76.41 95	85.80 72	90.22 190	74.15 36	95.37 86	81.82 103	91.88 95	92.65 165

HQP-NCC					89.33 146		89.17 116		76.41 95	77.23 245

ACMP_Plane					89.33 146		89.17 116		76.41 95	77.23 245

HQP-MVS		82.61 143	82.02 148	84.37 141	89.33 146	66.98 185	89.17 116	92.19 107	76.41 95	77.23 245	90.23 189	60.17 241	95.11 95	77.47 161	85.99 216	91.03 226

E4		84.10 99	83.99 102	84.45 136	87.58 241	64.99 237	86.54 233	92.25 98	76.38 99	83.37 123	92.09 121	69.88 92	93.58 170	79.78 131	88.03 175	94.77 29

CANet_DTU		80.61 192	79.87 190	82.83 226	85.60 301	63.17 293	87.36 200	88.65 262	76.37 100	75.88 278	88.44 244	53.51 301	93.07 213	73.30 213	89.74 137	92.25 183

VNet		82.21 148	82.41 137	81.62 260	90.82 101	60.93 337	84.47 296	89.78 199	76.36 101	84.07 106	91.88 125	64.71 165	90.26 331	70.68 244	88.89 151	93.66 105

Vis-MVSNet		83.46 123	82.80 130	85.43 91	90.25 113	68.74 122	90.30 80	90.13 190	76.33 102	80.87 172	92.89 96	61.00 227	94.20 138	72.45 229	90.97 113	93.35 125
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ME-MVS		88.98 11	89.39 8	87.75 30	94.54 20	71.43 61	91.61 49	94.25 5	76.30 103	90.62 21	95.03 22	78.06 15	97.07 19	88.15 39	95.96 19	94.75 34

ACMMP_NAP		88.05 20	88.08 21	87.94 19	93.70 45	73.05 22	90.86 65	93.59 28	76.27 104	88.14 42	95.09 21	71.06 74	96.67 33	87.67 44	96.37 14	94.09 80

fmvsm_s_conf0.5_n_10		86.38 52	86.76 46	85.24 97	87.33 249	67.30 176	89.50 101	90.98 158	76.25 105	90.56 22	94.75 29	68.38 119	94.24 137	90.80 7	92.32 89	94.19 74

alignmvs		85.48 73	85.32 79	85.96 78	89.51 136	69.47 103	89.74 92	92.47 82	76.17 106	87.73 53	91.46 147	70.32 82	93.78 161	81.51 104	88.95 150	94.63 47

MVS_111021_HR		85.14 82	84.75 88	86.32 66	91.65 86	72.70 30	85.98 253	90.33 182	76.11 107	82.08 148	91.61 141	71.36 70	94.17 141	81.02 110	92.58 82	92.08 194

HPM-MVS		87.11 38	86.98 41	87.50 43	93.88 43	72.16 47	92.19 38	93.33 36	76.07 108	83.81 112	93.95 68	69.77 94	96.01 59	85.15 62	94.66 50	94.32 68
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
h-mvs33		83.15 132	82.19 143	86.02 77	90.56 106	70.85 80	88.15 169	89.16 233	76.02 109	84.67 88	91.39 149	61.54 213	95.50 74	82.71 96	75.48 371	91.72 205

hse-mvs2		81.72 158	80.94 163	84.07 165	88.72 177	67.68 161	85.87 257	87.26 299	76.02 109	84.67 88	88.22 251	61.54 213	93.48 186	82.71 96	73.44 399	91.06 224

DPE-MVS		89.48 6	89.98 5	88.01 16	94.80 11	72.69 31	91.59 51	94.10 12	75.90 111	92.29 7	95.66 12	81.67 6	97.38 13	87.44 48	96.34 15	93.95 88
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
E2		84.00 102	83.87 103	84.39 139	87.70 228	64.95 238	86.40 240	92.23 99	75.85 112	83.21 125	91.78 129	70.09 87	93.55 175	79.52 135	88.05 173	94.66 44

E3		84.00 102	83.87 103	84.39 139	87.70 228	64.95 238	86.40 240	92.23 99	75.85 112	83.21 125	91.78 129	70.09 87	93.55 175	79.52 135	88.05 173	94.66 44

CLD-MVS		82.31 147	81.65 153	84.29 149	88.47 185	67.73 159	85.81 261	92.35 89	75.78 114	78.33 219	86.58 301	64.01 172	94.35 130	76.05 182	87.48 186	90.79 235
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
viewmacassd2359aftdt		83.76 111	83.66 111	84.07 165	86.59 279	64.56 250	86.88 218	91.82 126	75.72 115	83.34 124	92.15 119	68.24 123	92.88 222	79.05 138	89.15 148	94.77 29

SF-MVS		88.46 15	88.74 15	87.64 39	92.78 71	71.95 52	92.40 29	94.74 2	75.71 116	89.16 29	95.10 20	75.65 25	96.19 52	87.07 49	96.01 17	94.79 27

testdata1							84.14 311		75.71 116

APDe-MVS		89.15 8	89.63 7	87.73 31	94.49 22	71.69 55	93.83 4	93.96 17	75.70 118	91.06 19	96.03 1	76.84 18	97.03 20	89.09 21	95.65 30	94.47 59
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
VPA-MVSNet		80.60 194	80.55 171	80.76 286	88.07 204	60.80 340	86.86 219	91.58 141	75.67 119	80.24 184	89.45 215	63.34 176	90.25 332	70.51 246	79.22 321	91.23 219

fmvsm_l_conf0.5_n_9		85.84 66	86.63 49	83.46 194	87.12 263	66.01 201	88.56 149	89.43 214	75.59 120	89.32 28	94.32 44	72.89 47	91.21 301	90.11 11	92.33 87	93.16 137

PGM-MVS		86.68 45	86.27 55	87.90 22	94.22 37	73.38 18	90.22 81	93.04 47	75.53 121	83.86 110	94.42 40	67.87 127	96.64 36	82.70 98	94.57 55	93.66 105

Effi-MVS+		83.62 118	83.08 122	85.24 97	88.38 190	67.45 169	88.89 129	89.15 234	75.50 122	82.27 144	88.28 248	69.61 96	94.45 129	77.81 156	87.84 178	93.84 95

viewcassd2359sk11		83.89 105	83.74 108	84.34 144	87.76 223	64.91 244	86.30 244	92.22 102	75.47 123	83.04 131	91.52 143	70.15 85	93.53 178	79.26 137	87.96 176	94.57 52

fmvsm_s_conf0.5_n_4		85.39 77	85.75 70	84.30 148	86.70 275	65.83 208	88.77 136	89.78 199	75.46 124	88.35 37	93.73 74	69.19 106	93.06 214	91.30 3	88.44 162	94.02 84

fmvsm_s_conf0.5_n_6		85.55 72	86.20 56	83.60 189	87.32 251	65.13 231	88.86 130	91.63 137	75.41 125	88.23 41	93.45 82	68.56 117	92.47 240	89.52 18	92.78 79	93.20 134

test_prior2							88.85 132		75.41 125	84.91 83	93.54 76	74.28 34		83.31 85	95.86 23

LPG-MVS_test		82.08 150	81.27 156	84.50 133	89.23 154	68.76 120	90.22 81	91.94 119	75.37 127	76.64 260	91.51 144	54.29 292	94.91 103	78.44 148	83.78 252	89.83 284

LGP-MVS_train				84.50 133	89.23 154	68.76 120		91.94 119	75.37 127	76.64 260	91.51 144	54.29 292	94.91 103	78.44 148	83.78 252	89.83 284

fmvsm_l_conf0.5_n_3		86.02 57	86.32 53	85.14 100	87.20 255	68.54 131	89.57 99	90.44 176	75.31 129	87.49 55	94.39 42	72.86 48	92.72 229	89.04 27	90.56 121	94.16 75

MED-MVS test				87.86 27	94.57 17	71.43 61	93.28 12	94.36 3	75.24 130	92.25 9	95.03 22		97.39 11	88.15 39	95.96 19	94.75 34

viewdifsd2359ckpt07		82.83 140	82.78 132	82.99 218	86.51 281	62.58 303	85.09 280	90.83 165	75.22 131	82.28 143	91.63 138	69.43 98	92.03 257	77.71 158	86.32 206	94.34 66

MG-MVS		83.41 124	83.45 116	83.28 201	92.74 72	62.28 312	88.17 167	89.50 212	75.22 131	81.49 159	92.74 104	66.75 138	95.11 95	72.85 219	91.58 102	92.45 175

SSC-MVS3.2		73.35 345	73.39 327	73.23 414	85.30 310	49.01 464	74.58 447	81.57 393	75.21 133	73.68 327	85.58 325	52.53 306	82.05 431	54.33 405	77.69 338	88.63 327

LCM-MVSNet-Re		77.05 285	76.94 267	77.36 370	87.20 255	51.60 450	80.06 387	80.46 409	75.20 134	67.69 402	86.72 291	62.48 195	88.98 357	63.44 310	89.25 144	91.51 210

SDMVSNet		80.38 201	80.18 180	80.99 280	89.03 163	64.94 241	80.45 381	89.40 215	75.19 135	76.61 262	89.98 192	60.61 235	87.69 378	76.83 172	83.55 261	90.33 257

sd_testset		77.70 273	77.40 257	78.60 342	89.03 163	60.02 354	79.00 402	85.83 331	75.19 135	76.61 262	89.98 192	54.81 284	85.46 403	62.63 326	83.55 261	90.33 257

MP-MVS-pluss		87.67 25	87.72 25	87.54 40	93.64 48	72.04 51	89.80 90	93.50 30	75.17 137	86.34 69	95.29 19	70.86 76	96.00 60	88.78 31	96.04 16	94.58 50
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
E3new		83.78 110	83.60 113	84.31 146	87.76 223	64.89 245	86.24 247	92.20 105	75.15 138	82.87 134	91.23 152	70.11 86	93.52 180	79.05 138	87.79 179	94.51 57

test1111		79.43 223	79.18 212	80.15 303	89.99 122	53.31 437	87.33 202	77.05 443	75.04 139	80.23 185	92.77 103	48.97 367	92.33 249	68.87 266	92.40 86	94.81 26

Effi-MVS+-dtu		80.03 211	78.57 223	84.42 138	85.13 316	68.74 122	88.77 136	88.10 270	74.99 140	74.97 309	83.49 377	57.27 265	93.36 192	73.53 209	80.88 296	91.18 220

reproduce-ours		87.47 27	87.61 27	87.07 51	93.27 54	71.60 56	91.56 54	93.19 41	74.98 141	88.96 30	95.54 14	71.20 72	96.54 41	86.28 54	93.49 70	93.06 145

our_new_method		87.47 27	87.61 27	87.07 51	93.27 54	71.60 56	91.56 54	93.19 41	74.98 141	88.96 30	95.54 14	71.20 72	96.54 41	86.28 54	93.49 70	93.06 145

fmvsm_s_conf0.5_n_7		83.34 127	84.03 101	81.28 271	85.73 297	65.13 231	85.40 272	89.90 197	74.96 143	82.13 147	93.89 69	66.65 139	87.92 374	86.56 53	91.05 111	90.80 234

OMC-MVS		82.69 141	81.97 150	84.85 118	88.75 176	67.42 170	87.98 173	90.87 163	74.92 144	79.72 190	91.65 136	62.19 202	93.96 146	75.26 194	86.42 205	93.16 137

viewmanbaseed2359cas		83.66 114	83.55 114	84.00 176	86.81 271	64.53 251	86.65 228	91.75 131	74.89 145	83.15 130	91.68 134	68.74 115	92.83 226	79.02 140	89.24 145	94.63 47

test2506		77.30 282	76.49 278	79.74 318	90.08 117	52.02 443	87.86 181	63.10 486	74.88 146	80.16 186	92.79 101	38.29 447	92.35 247	68.74 268	92.50 84	94.86 21

ECVR-MVS		79.61 216	79.26 209	80.67 288	90.08 117	54.69 424	87.89 179	77.44 439	74.88 146	80.27 183	92.79 101	48.96 368	92.45 241	68.55 269	92.50 84	94.86 21

MonoMVSNet		76.49 297	75.80 286	78.58 343	81.55 399	58.45 367	86.36 242	86.22 324	74.87 148	74.73 313	83.73 370	51.79 327	88.73 362	70.78 241	72.15 408	88.55 330

nrg030		83.88 106	83.53 115	84.96 110	86.77 273	69.28 110	90.46 75	92.67 73	74.79 149	82.95 132	91.33 151	72.70 51	93.09 212	80.79 115	79.28 320	92.50 171

SMA-MVS		89.08 9	89.23 9	88.61 6	94.25 35	73.73 9	92.40 29	93.63 26	74.77 150	92.29 7	95.97 2	74.28 34	97.24 15	88.58 33	96.91 1	94.87 20
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
reproduce_model		87.28 35	87.39 33	86.95 55	93.10 62	71.24 70	91.60 50	93.19 41	74.69 151	88.80 34	95.61 13	70.29 83	96.44 44	86.20 56	93.08 74	93.16 137

MVS_111021_LR		82.61 143	82.11 144	84.11 158	88.82 168	71.58 58	85.15 277	86.16 326	74.69 151	80.47 181	91.04 162	62.29 199	90.55 326	80.33 121	90.08 130	90.20 262

EIA-MVS		83.31 130	82.80 130	84.82 119	89.59 132	65.59 216	88.21 165	92.68 72	74.66 153	78.96 202	86.42 306	69.06 109	95.26 88	75.54 190	90.09 129	93.62 112

TSAR-MVS + MP.		88.02 21	88.11 20	87.72 33	93.68 47	72.13 48	91.41 58	92.35 89	74.62 154	88.90 33	93.85 71	75.75 24	96.00 60	87.80 43	94.63 53	95.04 11
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SR-MVS		86.73 43	86.67 48	86.91 56	94.11 41	72.11 49	92.37 33	92.56 81	74.50 155	86.84 65	94.65 31	67.31 132	95.77 65	84.80 68	92.85 78	92.84 159

FOURS1					95.00 10	72.39 41	95.06 1	93.84 20	74.49 156	91.30 17

ACMP	74.13 6	81.51 169	80.57 170	84.36 142	89.42 141	68.69 127	89.97 85	91.50 146	74.46 157	75.04 307	90.41 181	53.82 298	94.54 123	77.56 160	82.91 272	89.86 283
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
EPP-MVSNet		83.40 125	83.02 124	84.57 127	90.13 115	64.47 256	92.32 35	90.73 168	74.45 158	79.35 198	91.10 159	69.05 110	95.12 93	72.78 220	87.22 190	94.13 77

balanced_ft_v1		83.98 104	83.64 112	85.03 106	89.76 129	65.86 207	88.31 162	91.71 133	74.41 159	80.41 182	90.82 170	62.90 190	94.90 105	83.04 89	91.37 106	94.32 68

fmvsm_s_conf0.5_n_2		84.04 100	84.11 100	83.81 185	86.17 288	65.00 236	86.96 213	87.28 294	74.35 160	88.25 40	94.23 50	61.82 208	92.60 232	89.85 12	88.09 172	93.84 95

fmvsm_s_conf0.1_n_2		83.80 108	83.79 107	83.83 183	85.62 300	64.94 241	87.03 210	86.62 318	74.32 161	87.97 48	94.33 43	60.67 232	92.60 232	89.72 14	87.79 179	93.96 86

save fliter					93.80 44	72.35 44	90.47 74	91.17 153	74.31 162

MVS_Test		83.15 132	83.06 123	83.41 198	86.86 268	63.21 290	86.11 251	92.00 115	74.31 162	82.87 134	89.44 216	70.03 89	93.21 201	77.39 163	88.50 161	93.81 97

myMVS_eth3d28		73.62 336	73.53 326	73.90 410	88.20 195	47.41 469	78.06 417	79.37 423	74.29 164	73.98 323	84.29 354	44.67 402	83.54 420	51.47 419	87.39 187	90.74 239

UniMVSNet_ETH3D		79.10 234	78.24 232	81.70 259	86.85 269	60.24 352	87.28 204	88.79 250	74.25 165	76.84 253	90.53 180	49.48 358	91.56 279	67.98 273	82.15 281	93.29 127

IterMVS-LS		80.06 210	79.38 204	82.11 251	85.89 293	63.20 291	86.79 222	89.34 217	74.19 166	75.45 288	86.72 291	66.62 140	92.39 244	72.58 222	76.86 347	90.75 238
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		80.52 198	79.98 186	82.12 249	84.28 333	63.19 292	86.41 237	88.95 245	74.18 167	78.69 207	87.54 271	66.62 140	92.43 242	72.57 223	80.57 302	90.74 239

Vis-MVSNet (Re-imp)		78.36 253	78.45 225	78.07 356	88.64 180	51.78 449	86.70 226	79.63 421	74.14 168	75.11 304	90.83 169	61.29 221	89.75 341	58.10 377	91.60 100	92.69 163

v8		79.97 213	79.02 215	82.80 229	84.09 338	64.50 255	87.96 174	90.29 185	74.13 169	75.24 300	86.81 288	62.88 191	93.89 157	74.39 202	75.40 376	90.00 275

guyue		81.13 174	80.64 169	82.60 240	86.52 280	63.92 268	86.69 227	87.73 284	73.97 170	80.83 174	89.69 202	56.70 271	91.33 295	78.26 155	85.40 229	92.54 168

CSCG		86.41 51	86.19 58	87.07 51	92.91 67	72.48 37	90.81 66	93.56 29	73.95 171	83.16 129	91.07 161	75.94 22	95.19 90	79.94 125	94.38 61	93.55 117

thres100view900		76.50 294	75.55 293	79.33 329	89.52 135	56.99 392	85.83 260	83.23 367	73.94 172	76.32 269	87.12 283	51.89 324	91.95 262	48.33 439	83.75 255	89.07 302

9.14			88.26 19		92.84 70		91.52 56	94.75 1	73.93 173	88.57 36	94.67 30	75.57 26	95.79 64	86.77 51	95.76 26

HPM-MVS_fast		85.35 79	84.95 86	86.57 64	93.69 46	70.58 85	92.15 40	91.62 138	73.89 174	82.67 141	94.09 57	62.60 192	95.54 71	80.93 111	92.93 77	93.57 115

PAPM_NR		83.02 136	82.41 137	84.82 119	92.47 77	66.37 194	87.93 177	91.80 127	73.82 175	77.32 242	90.66 174	67.90 126	94.90 105	70.37 247	89.48 142	93.19 135

thres600view7		76.50 294	75.44 294	79.68 321	89.40 143	57.16 389	85.53 269	83.23 367	73.79 176	76.26 270	87.09 284	51.89 324	91.89 265	48.05 444	83.72 258	90.00 275

testing91		76.54 292	75.66 291	79.18 333	88.43 188	55.89 410	81.08 368	83.00 374	73.76 177	75.34 293	84.29 354	46.20 390	90.07 335	64.33 304	84.50 239	91.58 208

AstraMVS		80.81 182	80.14 183	82.80 229	86.05 292	63.96 265	86.46 236	85.90 330	73.71 178	80.85 173	90.56 178	54.06 296	91.57 278	79.72 132	83.97 250	92.86 157

v7n		78.97 238	77.58 253	83.14 209	83.45 355	65.51 217	88.32 161	91.21 151	73.69 179	72.41 345	86.32 309	57.93 256	93.81 160	69.18 262	75.65 367	90.11 267

dcpmvs_2		85.63 70	86.15 60	84.06 168	91.71 85	64.94 241	86.47 235	91.87 123	73.63 180	86.60 68	93.02 94	76.57 19	91.87 267	83.36 84	92.15 90	95.35 3

v2v482		80.23 207	79.29 208	83.05 215	83.62 351	64.14 262	87.04 209	89.97 194	73.61 181	78.18 223	87.22 279	61.10 225	93.82 159	76.11 180	76.78 350	91.18 220

Baseline_NR-MVSNet		78.15 259	78.33 230	77.61 366	85.79 295	56.21 407	86.78 223	85.76 332	73.60 182	77.93 229	87.57 268	65.02 162	88.99 356	67.14 283	75.33 378	87.63 350

BH-RMVSNet		79.61 216	78.44 226	83.14 209	89.38 145	65.93 204	84.95 284	87.15 302	73.56 183	78.19 222	89.79 200	56.67 272	93.36 192	59.53 360	86.74 200	90.13 265

APD-MVS_3200maxsize		85.97 61	85.88 65	86.22 68	92.69 73	69.53 100	91.93 42	92.99 55	73.54 184	85.94 70	94.51 35	65.80 156	95.61 68	83.04 89	92.51 83	93.53 119

SR-MVS-dyc-post		85.77 67	85.61 72	86.23 67	93.06 64	70.63 83	91.88 43	92.27 95	73.53 185	85.69 74	94.45 37	65.00 164	95.56 69	82.75 94	91.87 96	92.50 171

RE-MVS-def			85.48 75		93.06 64	70.63 83	91.88 43	92.27 95	73.53 185	85.69 74	94.45 37	63.87 173		82.75 94	91.87 96	92.50 171

reproduce_monomvs		75.40 317	74.38 315	78.46 349	83.92 343	57.80 380	83.78 316	86.94 308	73.47 187	72.25 348	84.47 348	38.74 443	89.27 350	75.32 193	70.53 418	88.31 334

test_fmvsmconf_n		85.92 62	86.04 63	85.57 88	85.03 319	69.51 101	89.62 98	90.58 171	73.42 188	87.75 51	94.02 61	72.85 49	93.24 198	90.37 8	90.75 118	93.96 86

tfpn200view9		76.42 300	75.37 298	79.55 326	89.13 158	57.65 383	85.17 275	83.60 359	73.41 189	76.45 265	86.39 307	52.12 314	91.95 262	48.33 439	83.75 255	89.07 302

thres400		76.50 294	75.37 298	79.86 311	89.13 158	57.65 383	85.17 275	83.60 359	73.41 189	76.45 265	86.39 307	52.12 314	91.95 262	48.33 439	83.75 255	90.00 275

diffmvs_AUTHOR		82.38 146	82.27 142	82.73 237	83.26 359	63.80 270	83.89 314	89.76 201	73.35 191	82.37 142	90.84 168	66.25 147	90.79 320	82.77 93	87.93 177	93.59 114

test_fmvsmconf0.1_n		85.61 71	85.65 71	85.50 89	82.99 373	69.39 108	89.65 95	90.29 185	73.31 192	87.77 50	94.15 55	71.72 63	93.23 199	90.31 9	90.67 120	93.89 92

testing99		76.09 306	75.12 305	79.00 334	88.16 197	55.50 416	80.79 372	81.40 396	73.30 193	75.17 301	84.27 357	44.48 405	90.02 336	64.28 305	84.22 248	91.48 213

v148		78.72 244	77.80 244	81.47 264	82.73 379	61.96 318	86.30 244	88.08 271	73.26 194	76.18 273	85.47 328	62.46 196	92.36 246	71.92 233	73.82 395	90.09 269

FA-MVS(test-final)		80.96 178	79.91 188	84.10 159	88.30 193	65.01 235	84.55 295	90.01 193	73.25 195	79.61 191	87.57 268	58.35 254	94.72 117	71.29 238	86.25 209	92.56 167

test_fmvsmconf0.01_n		84.73 90	84.52 92	85.34 94	80.25 416	69.03 111	89.47 102	89.65 206	73.24 196	86.98 63	94.27 47	66.62 140	93.23 199	90.26 10	89.95 133	93.78 101

viewdifsd2359ckpt11		80.37 203	79.73 194	82.30 246	83.70 349	62.39 307	84.20 308	86.67 314	73.22 197	80.90 170	90.62 175	63.00 188	91.56 279	76.81 173	78.44 327	92.95 154

viewmsd2359difaftdt		80.37 203	79.73 194	82.30 246	83.70 349	62.39 307	84.20 308	86.67 314	73.22 197	80.90 170	90.62 175	63.00 188	91.56 279	76.81 173	78.44 327	92.95 154

v10		79.74 215	78.67 220	82.97 221	84.06 339	64.95 238	87.88 180	90.62 170	73.11 199	75.11 304	86.56 302	61.46 216	94.05 145	73.68 207	75.55 369	89.90 281

MCST-MVS		87.37 34	87.25 35	87.73 31	94.53 21	72.46 40	89.82 88	93.82 21	73.07 200	84.86 86	92.89 96	76.22 21	96.33 46	84.89 66	95.13 39	94.40 62

baseline1		76.98 287	76.75 274	77.66 364	88.13 200	55.66 414	85.12 278	81.89 389	73.04 201	76.79 255	88.90 229	62.43 197	87.78 377	63.30 312	71.18 415	89.55 293

APD-MVS		87.44 29	87.52 30	87.19 48	94.24 36	72.39 41	91.86 45	92.83 66	73.01 202	88.58 35	94.52 32	73.36 39	96.49 43	84.26 75	95.01 40	92.70 161
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
diffmvs		82.10 149	81.88 151	82.76 235	83.00 369	63.78 272	83.68 319	89.76 201	72.94 203	82.02 149	89.85 195	65.96 155	90.79 320	82.38 100	87.30 189	93.71 103
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
K. test v3		71.19 371	68.51 383	79.21 332	83.04 368	57.78 381	84.35 305	76.91 444	72.90 204	62.99 449	82.86 389	39.27 439	91.09 307	61.65 342	52.66 477	88.75 322

MVSMamba_PlusPlus		85.99 59	85.96 64	86.05 74	91.09 93	67.64 162	89.63 97	92.65 76	72.89 205	84.64 91	91.71 133	71.85 60	96.03 56	84.77 69	94.45 59	94.49 58

GDP-MVS		83.52 121	82.64 133	86.16 70	88.14 199	68.45 133	89.13 121	92.69 71	72.82 206	83.71 113	91.86 127	55.69 279	95.35 87	80.03 123	89.74 137	94.69 36

fmvsm_s_conf0.5_n_5		85.22 81	85.55 73	84.25 155	86.26 284	67.40 172	89.18 115	89.31 223	72.50 207	88.31 38	93.86 70	69.66 95	91.96 261	89.81 13	91.05 111	93.38 122

Fast-Effi-MVS+-dtu		78.02 263	76.49 278	82.62 239	83.16 365	66.96 187	86.94 215	87.45 291	72.45 208	71.49 357	84.17 361	54.79 288	91.58 276	67.61 276	80.31 305	89.30 300

PHI-MVS		86.43 49	86.17 59	87.24 47	90.88 100	70.96 75	92.27 37	94.07 13	72.45 208	85.22 79	91.90 124	69.47 97	96.42 45	83.28 86	95.94 22	94.35 65

thres200		75.55 312	74.47 313	78.82 338	87.78 220	57.85 378	83.07 339	83.51 362	72.44 210	75.84 279	84.42 349	52.08 317	91.75 270	47.41 446	83.64 260	86.86 381

test_yl		81.17 172	80.47 174	83.24 204	89.13 158	63.62 273	86.21 248	89.95 195	72.43 211	81.78 154	89.61 206	57.50 262	93.58 170	70.75 242	86.90 196	92.52 169

DCV-MVSNet		81.17 172	80.47 174	83.24 204	89.13 158	63.62 273	86.21 248	89.95 195	72.43 211	81.78 154	89.61 206	57.50 262	93.58 170	70.75 242	86.90 196	92.52 169

viewdifsd2359ckpt13		82.91 138	82.29 141	84.77 122	86.96 267	66.90 189	87.47 190	91.62 138	72.19 213	81.68 156	90.71 172	66.92 136	93.28 194	75.90 184	87.15 192	94.12 78

BH-untuned		79.47 221	78.60 222	82.05 252	89.19 156	65.91 205	86.07 252	88.52 265	72.18 214	75.42 289	87.69 265	61.15 224	93.54 177	60.38 352	86.83 199	86.70 386

TransMVSNet (Re)		75.39 318	74.56 311	77.86 359	85.50 305	57.10 391	86.78 223	86.09 328	72.17 215	71.53 356	87.34 274	63.01 187	89.31 349	56.84 390	61.83 459	87.17 371

GA-MVS		76.87 289	75.17 304	81.97 255	82.75 378	62.58 303	81.44 363	86.35 323	72.16 216	74.74 312	82.89 388	46.20 390	92.02 259	68.85 267	81.09 293	91.30 218

VortexMVS		78.57 249	77.89 240	80.59 289	85.89 293	62.76 302	85.61 262	89.62 208	72.06 217	74.99 308	85.38 330	55.94 278	90.77 323	74.99 195	76.58 351	88.23 337

mmtdpeth		74.16 329	73.01 333	77.60 368	83.72 348	61.13 330	85.10 279	85.10 339	72.06 217	77.21 249	80.33 418	43.84 410	85.75 397	77.14 166	52.61 478	85.91 402

v1144		80.03 211	79.03 214	83.01 217	83.78 346	64.51 253	87.11 208	90.57 173	71.96 219	78.08 226	86.20 311	61.41 217	93.94 149	74.93 196	77.23 341	90.60 245

viewdifsd2359ckpt09		83.34 127	82.55 135	85.70 82	87.64 232	67.72 160	88.43 153	91.68 135	71.91 220	81.65 157	90.68 173	67.10 135	94.75 115	76.17 179	87.70 182	94.62 49

PS-MVSNAJss		82.07 151	81.31 155	84.34 144	86.51 281	67.27 178	89.27 112	91.51 143	71.75 221	79.37 197	90.22 190	63.15 183	94.27 133	77.69 159	82.36 280	91.49 212

EPNet_dtu		75.46 314	74.86 306	77.23 373	82.57 383	54.60 425	86.89 217	83.09 371	71.64 222	66.25 425	85.86 317	55.99 277	88.04 373	54.92 401	86.55 203	89.05 307
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
GBi-Net		78.40 251	77.40 257	81.40 267	87.60 233	63.01 294	88.39 156	89.28 224	71.63 223	75.34 293	87.28 275	54.80 285	91.11 302	62.72 322	79.57 312	90.09 269

test1		78.40 251	77.40 257	81.40 267	87.60 233	63.01 294	88.39 156	89.28 224	71.63 223	75.34 293	87.28 275	54.80 285	91.11 302	62.72 322	79.57 312	90.09 269

FMVSNet2		78.20 257	77.21 261	81.20 274	87.60 233	62.89 301	87.47 190	89.02 240	71.63 223	75.29 299	87.28 275	54.80 285	91.10 305	62.38 330	79.38 318	89.61 291

patch_mono-2		83.65 115	84.54 90	80.99 280	90.06 121	65.83 208	84.21 307	88.74 257	71.60 226	85.01 80	92.44 107	74.51 30	83.50 421	82.15 101	92.15 90	93.64 111

V42		79.38 227	78.24 232	82.83 226	81.10 408	65.50 218	85.55 267	89.82 198	71.57 227	78.21 221	86.12 313	60.66 233	93.18 207	75.64 187	75.46 373	89.81 286

API-MVS		81.99 153	81.23 157	84.26 154	90.94 98	70.18 92	91.10 63	89.32 222	71.51 228	78.66 209	88.28 248	65.26 159	95.10 98	64.74 302	91.23 109	87.51 356

tttt0517		79.40 225	77.91 238	83.90 182	88.10 202	63.84 269	88.37 159	84.05 354	71.45 229	76.78 256	89.12 220	49.93 354	94.89 107	70.18 251	83.18 270	92.96 153

pm-mvs1		77.25 283	76.68 276	78.93 336	84.22 335	58.62 366	86.41 237	88.36 267	71.37 230	73.31 331	88.01 258	61.22 223	89.15 354	64.24 306	73.01 402	89.03 308

Elysia		81.53 165	80.16 181	85.62 85	85.51 303	68.25 140	88.84 133	92.19 107	71.31 231	80.50 179	89.83 196	46.89 379	94.82 110	76.85 169	89.57 139	93.80 99

StellarMVS		81.53 165	80.16 181	85.62 85	85.51 303	68.25 140	88.84 133	92.19 107	71.31 231	80.50 179	89.83 196	46.89 379	94.82 110	76.85 169	89.57 139	93.80 99

testing222		74.04 331	72.66 337	78.19 352	87.89 212	55.36 417	81.06 369	79.20 426	71.30 233	74.65 315	83.57 376	39.11 442	88.67 364	51.43 421	85.75 223	90.53 248

GeoE		81.71 159	81.01 162	83.80 186	89.51 136	64.45 257	88.97 126	88.73 258	71.27 234	78.63 210	89.76 201	66.32 146	93.20 204	69.89 255	86.02 215	93.74 102

tt0805		78.73 243	77.83 242	81.43 265	85.17 312	60.30 351	89.41 107	90.90 161	71.21 235	77.17 250	88.73 233	46.38 385	93.21 201	72.57 223	78.96 322	90.79 235

FMVSNet3		77.88 267	76.85 269	80.97 282	86.84 270	62.36 309	86.52 234	88.77 251	71.13 236	75.34 293	86.66 297	54.07 295	91.10 305	62.72 322	79.57 312	89.45 295

VDDNet		81.52 167	80.67 167	84.05 171	90.44 109	64.13 263	89.73 93	85.91 329	71.11 237	83.18 128	93.48 79	50.54 344	93.49 183	73.40 212	88.25 168	94.54 56

fmvsm_s_conf0.5_n		83.80 108	83.71 109	84.07 165	86.69 276	67.31 175	89.46 103	83.07 372	71.09 238	86.96 64	93.70 75	69.02 112	91.47 289	88.79 30	84.62 238	93.44 121

XVG-OURS		80.41 199	79.23 210	83.97 179	85.64 299	69.02 113	83.03 341	90.39 177	71.09 238	77.63 236	91.49 146	54.62 291	91.35 293	75.71 186	83.47 264	91.54 209

SSM_0407		81.58 164	80.48 173	84.87 117	88.81 169	67.96 150	87.37 199	89.25 228	71.06 240	79.48 194	90.39 183	59.57 243	94.48 128	72.45 229	85.93 218	92.18 188

SSM_0404		81.91 154	80.84 165	85.13 103	89.24 153	68.26 138	87.84 182	89.25 228	71.06 240	80.62 176	90.39 183	59.57 243	94.65 121	72.45 229	87.19 191	92.47 174

SixPastTwentyTwo		73.37 342	71.26 355	79.70 320	85.08 317	57.89 377	85.57 263	83.56 361	71.03 242	65.66 429	85.88 316	42.10 422	92.57 234	59.11 365	63.34 453	88.65 326

ZD-MVS					94.38 29	72.22 46		92.67 73	70.98 243	87.75 51	94.07 58	74.01 37	96.70 31	84.66 70	94.84 47

mamba_0408		79.37 228	77.52 254	84.93 113	88.81 169	67.96 150	65.03 483	88.66 260	70.96 244	79.48 194	89.80 198	58.69 249	94.65 121	70.35 248	85.93 218	92.18 188

SSM_04072		77.67 275	77.52 254	78.12 354	88.81 169	67.96 150	65.03 483	88.66 260	70.96 244	79.48 194	89.80 198	58.69 249	74.23 477	70.35 248	85.93 218	92.18 188

v1192		79.59 218	78.43 227	83.07 214	83.55 353	64.52 252	86.93 216	90.58 171	70.83 246	77.78 233	85.90 315	59.15 247	93.94 149	73.96 206	77.19 343	90.76 237

Fast-Effi-MVS+		80.81 182	79.92 187	83.47 193	88.85 165	64.51 253	85.53 269	89.39 216	70.79 247	78.49 214	85.06 339	67.54 129	93.58 170	67.03 285	86.58 202	92.32 180

PS-MVSNAJ		81.69 160	81.02 161	83.70 187	89.51 136	68.21 143	84.28 306	90.09 191	70.79 247	81.26 165	85.62 324	63.15 183	94.29 131	75.62 188	88.87 152	88.59 328

hybrid		81.05 176	80.66 168	82.22 248	81.97 391	62.99 298	83.42 327	88.68 259	70.76 249	80.56 178	90.40 182	64.49 168	90.48 327	79.57 134	86.06 213	93.19 135

LTVRE_ROB	69.57 13	76.25 303	74.54 312	81.41 266	88.60 181	64.38 259	79.24 397	89.12 237	70.76 249	69.79 378	87.86 261	49.09 365	93.20 204	56.21 396	80.16 306	86.65 388
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
testing11		75.14 320	74.01 318	78.53 346	88.16 197	56.38 403	80.74 375	80.42 411	70.67 251	72.69 342	83.72 371	43.61 412	89.86 338	62.29 332	83.76 254	89.36 298

fmvsm_s_conf0.1_n		83.56 120	83.38 118	84.10 159	84.86 321	67.28 177	89.40 108	83.01 373	70.67 251	87.08 61	93.96 67	68.38 119	91.45 290	88.56 34	84.50 239	93.56 116

xiu_mvs_v2_base		81.69 160	81.05 160	83.60 189	89.15 157	68.03 148	84.46 298	90.02 192	70.67 251	81.30 164	86.53 304	63.17 182	94.19 140	75.60 189	88.54 159	88.57 329

XVG-OURS-SEG-HR		80.81 182	79.76 193	83.96 180	85.60 301	68.78 119	83.54 326	90.50 174	70.66 254	76.71 258	91.66 135	60.69 231	91.26 296	76.94 168	81.58 288	91.83 198

Anonymous202405211		78.25 254	77.01 264	81.99 254	91.03 95	60.67 344	84.77 287	83.90 356	70.65 255	80.00 187	91.20 156	41.08 429	91.43 291	65.21 297	85.26 230	93.85 93

DP-MVS Recon		83.11 135	82.09 146	86.15 71	94.44 23	70.92 78	88.79 135	92.20 105	70.53 256	79.17 200	91.03 164	64.12 171	96.03 56	68.39 272	90.14 128	91.50 211

icg_test_0407_2		78.92 240	78.93 217	78.90 337	87.13 258	63.59 277	76.58 430	89.33 218	70.51 257	77.82 230	89.03 223	61.84 206	81.38 436	72.56 225	85.56 225	91.74 201

IMVS_0407		80.61 192	79.90 189	82.75 236	87.13 258	63.59 277	85.33 273	89.33 218	70.51 257	77.82 230	89.03 223	61.84 206	92.91 220	72.56 225	85.56 225	91.74 201

IMVS_0404		77.16 284	76.42 281	79.37 328	87.13 258	63.59 277	77.12 427	89.33 218	70.51 257	66.22 426	89.03 223	50.36 346	82.78 426	72.56 225	85.56 225	91.74 201

IMVS_0403		80.80 185	80.12 184	82.87 225	87.13 258	63.59 277	85.19 274	89.33 218	70.51 257	78.49 214	89.03 223	63.26 179	93.27 196	72.56 225	85.56 225	91.74 201

FMVSNet1		77.44 278	76.12 285	81.40 267	86.81 271	63.01 294	88.39 156	89.28 224	70.49 261	74.39 319	87.28 275	49.06 366	91.11 302	60.91 348	78.52 325	90.09 269

LuminaMVS		80.68 190	79.62 199	83.83 183	85.07 318	68.01 149	86.99 212	88.83 248	70.36 262	81.38 160	87.99 259	50.11 349	92.51 239	79.02 140	86.89 198	90.97 229

testing3		68.56 403	67.67 400	71.22 434	87.33 249	42.87 484	83.06 340	71.54 464	70.36 262	69.08 385	84.38 351	30.33 470	85.69 399	37.50 476	75.45 374	85.09 418

ab-mvs		79.51 219	78.97 216	81.14 276	88.46 186	60.91 338	83.84 315	89.24 230	70.36 262	79.03 201	88.87 231	63.23 181	90.21 333	65.12 298	82.57 278	92.28 182

tfpnnormal		74.39 325	73.16 331	78.08 355	86.10 291	58.05 372	84.65 292	87.53 288	70.32 265	71.22 360	85.63 323	54.97 283	89.86 338	43.03 463	75.02 383	86.32 391

ACMM	73.20 8	80.78 189	79.84 191	83.58 191	89.31 149	68.37 135	89.99 84	91.60 140	70.28 266	77.25 243	89.66 204	53.37 303	93.53 178	74.24 204	82.85 273	88.85 317
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
fmvsm_s_conf0.5_n_a		83.63 117	83.41 117	84.28 150	86.14 289	68.12 144	89.43 104	82.87 377	70.27 267	87.27 60	93.80 73	69.09 107	91.58 276	88.21 38	83.65 259	93.14 140

ACMH+	68.96 14	76.01 307	74.01 318	82.03 253	88.60 181	65.31 227	88.86 130	87.55 287	70.25 268	67.75 401	87.47 273	41.27 427	93.19 206	58.37 374	75.94 364	87.60 351

IB-MVS	68.01 15	75.85 309	73.36 329	83.31 200	84.76 324	66.03 199	83.38 329	85.06 340	70.21 269	69.40 380	81.05 408	45.76 395	94.66 120	65.10 299	75.49 370	89.25 301
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
thisisatest0530		79.40 225	77.76 247	84.31 146	87.69 230	65.10 234	87.36 200	84.26 352	70.04 270	77.42 239	88.26 250	49.94 352	94.79 114	70.20 250	84.70 237	93.03 148

mvsmamba		80.60 194	79.38 204	84.27 152	89.74 130	67.24 180	87.47 190	86.95 307	70.02 271	75.38 291	88.93 228	51.24 335	92.56 235	75.47 192	89.22 146	93.00 151

test_fmvsmvis_n_1920		84.02 101	83.87 103	84.49 135	84.12 337	69.37 109	88.15 169	87.96 276	70.01 272	83.95 109	93.23 87	68.80 114	91.51 286	88.61 32	89.96 132	92.57 166

v144192		79.47 221	78.37 228	82.78 233	83.35 356	63.96 265	86.96 213	90.36 181	69.99 273	77.50 237	85.67 322	60.66 233	93.77 163	74.27 203	76.58 351	90.62 243

test_fmvsm_n_1920		85.29 80	85.34 77	85.13 103	86.12 290	69.93 93	88.65 145	90.78 167	69.97 274	88.27 39	93.98 66	71.39 69	91.54 283	88.49 35	90.45 123	93.91 89

c3_l		78.75 242	77.91 238	81.26 272	82.89 376	61.56 324	84.09 312	89.13 236	69.97 274	75.56 283	84.29 354	66.36 145	92.09 256	73.47 211	75.48 371	90.12 266

v1921920		79.22 230	78.03 235	82.80 229	83.30 358	63.94 267	86.80 221	90.33 182	69.91 276	77.48 238	85.53 326	58.44 253	93.75 165	73.60 208	76.85 348	90.71 241

ACMH	67.68 16	75.89 308	73.93 320	81.77 258	88.71 178	66.61 191	88.62 146	89.01 241	69.81 277	66.78 416	86.70 295	41.95 424	91.51 286	55.64 397	78.14 333	87.17 371
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
fmvsm_s_conf0.1_n_a		83.32 129	82.99 126	84.28 150	83.79 345	68.07 146	89.34 111	82.85 378	69.80 278	87.36 59	94.06 59	68.34 121	91.56 279	87.95 42	83.46 265	93.21 132

DPM-MVS		84.93 87	84.29 94	86.84 57	90.20 114	73.04 23	87.12 207	93.04 47	69.80 278	82.85 136	91.22 155	73.06 45	96.02 58	76.72 176	94.63 53	91.46 215

MAR-MVS		81.84 156	80.70 166	85.27 96	91.32 90	71.53 59	89.82 88	90.92 160	69.77 280	78.50 213	86.21 310	62.36 198	94.52 125	65.36 296	92.05 93	89.77 287
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-ACMP-BASELINE		76.11 305	74.27 317	81.62 260	83.20 362	64.67 249	83.60 323	89.75 203	69.75 281	71.85 352	87.09 284	32.78 463	92.11 255	69.99 254	80.43 304	88.09 341

BH-w/o		78.21 256	77.33 260	80.84 284	88.81 169	65.13 231	84.87 285	87.85 281	69.75 281	74.52 317	84.74 346	61.34 219	93.11 211	58.24 376	85.84 221	84.27 426

v1240		78.99 237	77.78 245	82.64 238	83.21 361	63.54 281	86.62 230	90.30 184	69.74 283	77.33 241	85.68 321	57.04 268	93.76 164	73.13 216	76.92 345	90.62 243

FE-MVSNET2		72.88 357	71.28 353	77.67 363	78.30 440	57.78 381	84.43 301	88.92 247	69.56 284	64.61 438	81.67 404	46.73 383	88.54 367	59.33 361	67.99 432	86.69 387

ET-MVSNet_ETH3D		78.63 246	76.63 277	84.64 126	86.73 274	69.47 103	85.01 282	84.61 345	69.54 285	66.51 423	86.59 299	50.16 348	91.75 270	76.26 178	84.24 247	92.69 163

eth_miper_zixun_eth		77.92 266	76.69 275	81.61 262	83.00 369	61.98 317	83.15 334	89.20 232	69.52 286	74.86 311	84.35 353	61.76 209	92.56 235	71.50 236	72.89 403	90.28 260

PVSNet_Blended_VisFu		82.62 142	81.83 152	84.96 110	90.80 102	69.76 98	88.74 140	91.70 134	69.39 287	78.96 202	88.46 243	65.47 158	94.87 109	74.42 201	88.57 158	90.24 261

mvs_tets		79.13 233	77.77 246	83.22 206	84.70 325	66.37 194	89.17 116	90.19 188	69.38 288	75.40 290	89.46 213	44.17 408	93.15 208	76.78 175	80.70 300	90.14 264

PVSNet_BlendedMVS		80.60 194	80.02 185	82.36 245	88.85 165	65.40 219	86.16 250	92.00 115	69.34 289	78.11 224	86.09 314	66.02 153	94.27 133	71.52 234	82.06 283	87.39 359

SD_0403		74.65 324	74.77 308	74.29 404	86.20 287	47.42 468	83.71 318	85.12 338	69.30 290	68.50 393	87.95 260	59.40 245	86.05 394	49.38 433	83.35 266	89.40 296

AdaColmap		80.58 197	79.42 203	84.06 168	93.09 63	68.91 116	89.36 110	88.97 244	69.27 291	75.70 281	89.69 202	57.20 267	95.77 65	63.06 317	88.41 163	87.50 357

ETVMVS		72.25 364	71.05 358	75.84 382	87.77 222	51.91 446	79.39 395	74.98 452	69.26 292	73.71 326	82.95 386	40.82 431	86.14 393	46.17 452	84.43 244	89.47 294

ITE_SJBPF				78.22 351	81.77 395	60.57 346		83.30 365	69.25 293	67.54 403	87.20 280	36.33 456	87.28 383	54.34 404	74.62 387	86.80 383

cl____		77.72 271	76.76 272	80.58 290	82.49 385	60.48 348	83.09 337	87.87 279	69.22 294	74.38 320	85.22 335	62.10 203	91.53 284	71.09 239	75.41 375	89.73 289

DIV-MVS_self_test		77.72 271	76.76 272	80.58 290	82.48 386	60.48 348	83.09 337	87.86 280	69.22 294	74.38 320	85.24 333	62.10 203	91.53 284	71.09 239	75.40 376	89.74 288

jajsoiax		79.29 229	77.96 236	83.27 202	84.68 326	66.57 192	89.25 113	90.16 189	69.20 296	75.46 287	89.49 210	45.75 396	93.13 210	76.84 171	80.80 298	90.11 267

IterMVS-SCA-FT		75.43 315	73.87 322	80.11 304	82.69 380	64.85 246	81.57 360	83.47 363	69.16 297	70.49 364	84.15 362	51.95 320	88.15 371	69.23 261	72.14 409	87.34 364

CL-MVSNet_self_test		72.37 361	71.46 349	75.09 394	79.49 429	53.53 433	80.76 374	85.01 342	69.12 298	70.51 363	82.05 401	57.92 257	84.13 414	52.27 415	66.00 440	87.60 351

AUN-MVS		79.21 231	77.60 252	84.05 171	88.71 178	67.61 163	85.84 259	87.26 299	69.08 299	77.23 245	88.14 256	53.20 305	93.47 187	75.50 191	73.45 398	91.06 224

xiu_mvs_v1_base_debu		80.80 185	79.72 196	84.03 173	87.35 244	70.19 89	85.56 264	88.77 251	69.06 300	81.83 150	88.16 252	50.91 338	92.85 223	78.29 152	87.56 183	89.06 304

xiu_mvs_v1_base		80.80 185	79.72 196	84.03 173	87.35 244	70.19 89	85.56 264	88.77 251	69.06 300	81.83 150	88.16 252	50.91 338	92.85 223	78.29 152	87.56 183	89.06 304

xiu_mvs_v1_base_debi		80.80 185	79.72 196	84.03 173	87.35 244	70.19 89	85.56 264	88.77 251	69.06 300	81.83 150	88.16 252	50.91 338	92.85 223	78.29 152	87.56 183	89.06 304

MVSTER		79.01 236	77.88 241	82.38 244	83.07 366	64.80 247	84.08 313	88.95 245	69.01 303	78.69 207	87.17 282	54.70 289	92.43 242	74.69 197	80.57 302	89.89 282

usedtu_dtu_shiyan1		76.43 298	75.32 300	79.76 316	83.00 369	60.72 341	81.74 355	88.76 255	68.99 304	72.98 336	84.19 359	56.41 275	90.27 329	62.39 328	79.40 316	88.31 334

FE-MVSNET3		76.43 298	75.32 300	79.76 316	83.00 369	60.72 341	81.74 355	88.76 255	68.99 304	72.98 336	84.19 359	56.41 275	90.27 329	62.39 328	79.40 316	88.31 334

cl22		78.07 261	77.01 264	81.23 273	82.37 388	61.83 320	83.55 324	87.98 275	68.96 306	75.06 306	83.87 364	61.40 218	91.88 266	73.53 209	76.39 356	89.98 278

miper_ehance_all_eth		78.59 248	77.76 247	81.08 278	82.66 381	61.56 324	83.65 320	89.15 234	68.87 307	75.55 284	83.79 368	66.49 143	92.03 257	73.25 214	76.39 356	89.64 290

PAPR		81.66 162	80.89 164	83.99 178	90.27 112	64.00 264	86.76 225	91.77 130	68.84 308	77.13 252	89.50 209	67.63 128	94.88 108	67.55 277	88.52 160	93.09 143

CPTT-MVS		83.73 112	83.33 120	84.92 114	93.28 53	70.86 79	92.09 41	90.38 178	68.75 309	79.57 192	92.83 98	60.60 236	93.04 217	80.92 112	91.56 103	90.86 233

train_agg		86.43 49	86.20 56	87.13 50	93.26 56	72.96 25	88.75 138	91.89 121	68.69 310	85.00 81	93.10 89	74.43 31	95.41 81	84.97 63	95.71 28	93.02 149

test_8					93.13 60	72.57 35	88.68 144	91.84 125	68.69 310	84.87 85	93.10 89	74.43 31	95.16 91

dmvs_re		71.14 372	70.58 366	72.80 421	81.96 392	59.68 357	75.60 438	79.34 424	68.55 312	69.27 384	80.72 414	49.42 359	76.54 458	52.56 414	77.79 335	82.19 450

MVSFormer		82.85 139	82.05 147	85.24 97	87.35 244	70.21 87	90.50 72	90.38 178	68.55 312	81.32 161	89.47 211	61.68 210	93.46 188	78.98 143	90.26 126	92.05 195

test_djsdf		80.30 206	79.32 207	83.27 202	83.98 341	65.37 222	90.50 72	90.38 178	68.55 312	76.19 272	88.70 234	56.44 274	93.46 188	78.98 143	80.14 308	90.97 229

TEST9					93.26 56	72.96 25	88.75 138	91.89 121	68.44 315	85.00 81	93.10 89	74.36 33	95.41 81

FE-MVS		77.78 269	75.68 289	84.08 164	88.09 203	66.00 202	83.13 335	87.79 282	68.42 316	78.01 227	85.23 334	45.50 399	95.12 93	59.11 365	85.83 222	91.11 222

CDPH-MVS		85.76 68	85.29 81	87.17 49	93.49 51	71.08 71	88.58 148	92.42 86	68.32 317	84.61 92	93.48 79	72.32 53	96.15 54	79.00 142	95.43 33	94.28 71

PC_three_1452									68.21 318	92.02 14	94.00 63	82.09 5	95.98 62	84.58 71	96.68 2	94.95 14

fmvsm_l_conf0.5_n		84.47 91	84.54 90	84.27 152	85.42 306	68.81 117	88.49 152	87.26 299	68.08 319	88.03 45	93.49 78	72.04 59	91.77 269	88.90 29	89.14 149	92.24 185

IterMVS		74.29 326	72.94 334	78.35 350	81.53 400	63.49 283	81.58 359	82.49 381	68.06 320	69.99 373	83.69 372	51.66 329	85.54 401	65.85 293	71.64 412	86.01 399
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dmvs_testset		62.63 433	64.11 423	58.19 465	78.55 436	24.76 503	75.28 439	65.94 480	67.91 321	60.34 458	76.01 458	53.56 300	73.94 479	31.79 482	67.65 433	75.88 472

TAMVS		78.89 241	77.51 256	83.03 216	87.80 217	67.79 158	84.72 288	85.05 341	67.63 322	76.75 257	87.70 264	62.25 200	90.82 319	58.53 372	87.13 193	90.49 250

PVSNet_Blended		80.98 177	80.34 176	82.90 223	88.85 165	65.40 219	84.43 301	92.00 115	67.62 323	78.11 224	85.05 340	66.02 153	94.27 133	71.52 234	89.50 141	89.01 309

TR-MVS		77.44 278	76.18 284	81.20 274	88.24 194	63.24 289	84.61 293	86.40 321	67.55 324	77.81 232	86.48 305	54.10 294	93.15 208	57.75 380	82.72 276	87.20 369

CDS-MVSNet		79.07 235	77.70 249	83.17 208	87.60 233	68.23 142	84.40 304	86.20 325	67.49 325	76.36 268	86.54 303	61.54 213	90.79 320	61.86 339	87.33 188	90.49 250
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
fmvsm_l_conf0.5_n_a		84.13 98	84.16 95	84.06 168	85.38 307	68.40 134	88.34 160	86.85 311	67.48 326	87.48 56	93.40 83	70.89 75	91.61 274	88.38 37	89.22 146	92.16 192

mvs_anonymous		79.42 224	79.11 213	80.34 296	84.45 332	57.97 375	82.59 343	87.62 286	67.40 327	76.17 275	88.56 241	68.47 118	89.59 344	70.65 245	86.05 214	93.47 120

viewmambaseed2359dif		80.41 199	79.84 191	82.12 249	82.95 375	62.50 306	83.39 328	88.06 273	67.11 328	80.98 168	90.31 185	66.20 149	91.01 310	74.62 198	84.90 233	92.86 157

mvs5depth		69.45 395	67.45 404	75.46 390	73.93 465	55.83 411	79.19 399	83.23 367	66.89 329	71.63 355	83.32 379	33.69 462	85.09 406	59.81 357	55.34 474	85.46 409

IU-MVS					95.30 2	71.25 65		92.95 61	66.81 330	92.39 6				88.94 28	96.63 4	94.85 23

baseline2		75.70 310	73.83 323	81.30 270	83.26 359	61.79 321	82.57 344	80.65 404	66.81 330	66.88 414	83.42 378	57.86 258	92.19 253	63.47 309	79.57 312	89.91 280

miper_lstm_enhance		74.11 330	73.11 332	77.13 374	80.11 418	59.62 358	72.23 454	86.92 310	66.76 332	70.40 365	82.92 387	56.93 269	82.92 425	69.06 264	72.63 404	88.87 316

OpenMVS	72.83 10	79.77 214	78.33 230	84.09 163	85.17 312	69.91 94	90.57 69	90.97 159	66.70 333	72.17 349	91.91 123	54.70 289	93.96 146	61.81 340	90.95 115	88.41 333

test-LLR		72.94 354	72.43 339	74.48 401	81.35 404	58.04 373	78.38 411	77.46 437	66.66 334	69.95 374	79.00 433	48.06 371	79.24 444	66.13 288	84.83 234	86.15 395

test20.03		67.45 410	66.95 409	68.94 443	75.48 460	44.84 480	77.50 423	77.67 435	66.66 334	63.01 448	83.80 367	47.02 377	78.40 448	42.53 467	68.86 427	83.58 435

test0.0.03 1		68.00 408	67.69 399	68.90 444	77.55 449	47.43 467	75.70 437	72.95 463	66.66 334	66.56 419	82.29 398	48.06 371	75.87 467	44.97 459	74.51 388	83.41 436

Syy-MVS		68.05 407	67.85 394	68.67 447	84.68 326	40.97 490	78.62 408	73.08 461	66.65 337	66.74 417	79.46 428	52.11 316	82.30 429	32.89 481	76.38 359	82.75 445

myMVS_eth3d		67.02 414	66.29 414	69.21 442	84.68 326	42.58 485	78.62 408	73.08 461	66.65 337	66.74 417	79.46 428	31.53 467	82.30 429	39.43 473	76.38 359	82.75 445

QAPM		80.88 179	79.50 202	85.03 106	88.01 208	68.97 115	91.59 51	92.00 115	66.63 339	75.15 303	92.16 117	57.70 259	95.45 76	63.52 308	88.76 155	90.66 242

XXY-MVS		75.41 316	75.56 292	74.96 395	83.59 352	57.82 379	80.59 378	83.87 357	66.54 340	74.93 310	88.31 247	63.24 180	80.09 442	62.16 334	76.85 348	86.97 379

OurMVSNet-221017-0		74.26 327	72.42 340	79.80 313	83.76 347	59.59 359	85.92 256	86.64 316	66.39 341	66.96 413	87.58 267	39.46 438	91.60 275	65.76 294	69.27 423	88.22 338

SCA		74.22 328	72.33 341	79.91 309	84.05 340	62.17 313	79.96 390	79.29 425	66.30 342	72.38 346	80.13 421	51.95 320	88.60 365	59.25 363	77.67 339	88.96 313

testgi		66.67 417	66.53 413	67.08 454	75.62 459	41.69 489	75.93 433	76.50 446	66.11 343	65.20 436	86.59 299	35.72 458	74.71 474	43.71 460	73.38 400	84.84 421

HY-MVS	69.67 12	77.95 265	77.15 262	80.36 295	87.57 242	60.21 353	83.37 330	87.78 283	66.11 343	75.37 292	87.06 286	63.27 178	90.48 327	61.38 345	82.43 279	90.40 254

EG-PatchMatch MVS		74.04 331	71.82 345	80.71 287	84.92 320	67.42 170	85.86 258	88.08 271	66.04 345	64.22 441	83.85 365	35.10 459	92.56 235	57.44 382	80.83 297	82.16 451

CNLPA		78.08 260	76.79 271	81.97 255	90.40 110	71.07 72	87.59 187	84.55 346	66.03 346	72.38 346	89.64 205	57.56 261	86.04 395	59.61 359	83.35 266	88.79 320

gbinet_0.2-2-1-0.02		73.24 348	70.86 363	80.39 293	78.03 443	61.62 323	83.10 336	86.69 313	65.98 347	69.29 383	76.15 457	49.77 355	91.51 286	62.75 321	66.00 440	88.03 342

Anonymous20240529		80.19 209	78.89 218	84.10 159	90.60 105	64.75 248	88.95 127	90.90 161	65.97 348	80.59 177	91.17 158	49.97 351	93.73 167	69.16 263	82.70 277	93.81 97

TAPA-MVS	73.13 9	79.15 232	77.94 237	82.79 232	89.59 132	62.99 298	88.16 168	91.51 143	65.77 349	77.14 251	91.09 160	60.91 228	93.21 201	50.26 429	87.05 194	92.17 191
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MSDG		73.36 344	70.99 359	80.49 292	84.51 331	65.80 210	80.71 376	86.13 327	65.70 350	65.46 431	83.74 369	44.60 403	90.91 316	51.13 422	76.89 346	84.74 422

anonymousdsp		78.60 247	77.15 262	82.98 220	80.51 414	67.08 183	87.24 205	89.53 211	65.66 351	75.16 302	87.19 281	52.52 307	92.25 251	77.17 165	79.34 319	89.61 291

test_0402		72.79 358	70.44 369	79.84 312	88.13 200	65.99 203	85.93 255	84.29 350	65.57 352	67.40 409	85.49 327	46.92 378	92.61 231	35.88 478	74.38 389	80.94 458

UBG		73.08 351	72.27 342	75.51 388	88.02 206	51.29 454	78.35 414	77.38 440	65.52 353	73.87 325	82.36 395	45.55 397	86.48 390	55.02 400	84.39 245	88.75 322

miper_enhance_ethall		77.87 268	76.86 268	80.92 283	81.65 396	61.38 328	82.68 342	88.98 242	65.52 353	75.47 285	82.30 397	65.76 157	92.00 260	72.95 218	76.39 356	89.39 297

WBMVS		73.43 339	72.81 335	75.28 392	87.91 211	50.99 456	78.59 410	81.31 398	65.51 355	74.47 318	84.83 343	46.39 384	86.68 387	58.41 373	77.86 334	88.17 340

blend_shiyan4		72.29 363	69.65 375	80.21 301	78.24 441	62.16 314	82.29 348	87.27 297	65.41 356	68.43 395	76.42 453	39.91 436	91.23 298	63.21 315	65.66 447	87.22 368

blended_shiyan8		73.38 340	71.17 356	80.02 306	78.36 438	61.51 326	82.43 345	87.28 294	65.40 357	68.61 389	77.53 446	51.91 323	91.00 313	63.28 313	65.76 442	87.53 355

blended_shiyan6		73.38 340	71.17 356	80.01 307	78.36 438	61.48 327	82.43 345	87.27 297	65.40 357	68.56 391	77.55 445	51.94 322	91.01 310	63.27 314	65.76 442	87.55 354

UnsupCasMVSNet_eth		67.33 411	65.99 415	71.37 430	73.48 470	51.47 452	75.16 441	85.19 337	65.20 359	60.78 456	80.93 413	42.35 418	77.20 454	57.12 385	53.69 476	85.44 410

wanda-best-256-512		72.94 354	70.66 364	79.79 314	77.80 445	61.03 335	81.31 365	87.15 302	65.18 360	68.09 396	76.28 454	51.32 331	90.97 314	63.06 317	65.76 442	87.35 361

FE-blended-shiyan7		72.94 354	70.66 364	79.79 314	77.80 445	61.03 335	81.31 365	87.15 302	65.18 360	68.09 396	76.28 454	51.32 331	90.97 314	63.06 317	65.76 442	87.35 361

WTY-MVS		75.65 311	75.68 289	75.57 386	86.40 283	56.82 394	77.92 420	82.40 382	65.10 362	76.18 273	87.72 263	63.13 186	80.90 439	60.31 353	81.96 284	89.00 311

thisisatest0515		77.33 281	75.38 297	83.18 207	85.27 311	63.80 270	82.11 351	83.27 366	65.06 363	75.91 277	83.84 366	49.54 357	94.27 133	67.24 281	86.19 210	91.48 213

MVP-Stereo		76.12 304	74.46 314	81.13 277	85.37 308	69.79 96	84.42 303	87.95 277	65.03 364	67.46 406	85.33 331	53.28 304	91.73 272	58.01 378	83.27 268	81.85 453
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Anonymous20231211		78.97 238	77.69 250	82.81 228	90.54 107	64.29 260	90.11 83	91.51 143	65.01 365	76.16 276	88.13 257	50.56 343	93.03 218	69.68 258	77.56 340	91.11 222

pmmvs6		74.69 323	73.39 327	78.61 341	81.38 403	57.48 386	86.64 229	87.95 277	64.99 366	70.18 368	86.61 298	50.43 345	89.52 345	62.12 335	70.18 420	88.83 318

PAPM		77.68 274	76.40 282	81.51 263	87.29 254	61.85 319	83.78 316	89.59 209	64.74 367	71.23 359	88.70 234	62.59 193	93.66 169	52.66 413	87.03 195	89.01 309

MIMVSNet		70.69 379	69.30 377	74.88 397	84.52 330	56.35 405	75.87 436	79.42 422	64.59 368	67.76 400	82.41 394	41.10 428	81.54 434	46.64 450	81.34 289	86.75 385

tpm		72.37 361	71.71 346	74.35 403	82.19 389	52.00 444	79.22 398	77.29 441	64.56 369	72.95 338	83.68 373	51.35 330	83.26 424	58.33 375	75.80 365	87.81 347

MDA-MVSNet-bldmvs		66.68 416	63.66 426	75.75 383	79.28 432	60.56 347	73.92 450	78.35 432	64.43 370	50.13 482	79.87 425	44.02 409	83.67 417	46.10 453	56.86 468	83.03 442

usedtu_blend_shiyan5		73.29 346	70.96 360	80.25 299	77.80 445	62.16 314	84.44 300	87.38 292	64.41 371	68.09 396	76.28 454	51.32 331	91.23 298	63.21 315	65.76 442	87.35 361

MIMVSNet1		68.58 402	66.78 412	73.98 409	80.07 419	51.82 448	80.77 373	84.37 347	64.40 372	59.75 462	82.16 400	36.47 455	83.63 418	42.73 464	70.33 419	86.48 390

D2MVS		74.82 322	73.21 330	79.64 323	79.81 423	62.56 305	80.34 383	87.35 293	64.37 373	68.86 386	82.66 392	46.37 386	90.10 334	67.91 274	81.24 291	86.25 392

PLC	70.83 11	78.05 262	76.37 283	83.08 213	91.88 84	67.80 157	88.19 166	89.46 213	64.33 374	69.87 376	88.38 245	53.66 299	93.58 170	58.86 368	82.73 275	87.86 346
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PatchmatchNet		73.12 350	71.33 352	78.49 348	83.18 363	60.85 339	79.63 392	78.57 430	64.13 375	71.73 353	79.81 426	51.20 336	85.97 396	57.40 383	76.36 361	88.66 325
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
KD-MVS_2432*1600		66.22 421	63.89 424	73.21 415	75.47 461	53.42 435	70.76 461	84.35 348	64.10 376	66.52 421	78.52 437	34.55 460	84.98 407	50.40 425	50.33 481	81.23 456

miper_refine_blended		66.22 421	63.89 424	73.21 415	75.47 461	53.42 435	70.76 461	84.35 348	64.10 376	66.52 421	78.52 437	34.55 460	84.98 407	50.40 425	50.33 481	81.23 456

tpmvs		71.09 373	69.29 378	76.49 378	82.04 390	56.04 408	78.92 405	81.37 397	64.05 378	67.18 411	78.28 439	49.74 356	89.77 340	49.67 432	72.37 405	83.67 434

F-COLMAP		76.38 302	74.33 316	82.50 242	89.28 151	66.95 188	88.41 155	89.03 239	64.05 378	66.83 415	88.61 238	46.78 381	92.89 221	57.48 381	78.55 324	87.67 349

DP-MVS		76.78 290	74.57 310	83.42 196	93.29 52	69.46 105	88.55 150	83.70 358	63.98 380	70.20 367	88.89 230	54.01 297	94.80 113	46.66 448	81.88 286	86.01 399

原ACMM1				84.35 143	93.01 66	68.79 118		92.44 83	63.96 381	81.09 166	91.57 142	66.06 152	95.45 76	67.19 282	94.82 49	88.81 319

PM-MVS		66.41 419	64.14 422	73.20 417	73.92 466	56.45 400	78.97 403	64.96 483	63.88 382	64.72 437	80.24 420	19.84 487	83.44 422	66.24 287	64.52 451	79.71 464

FE-MVSNET		67.25 413	65.33 417	73.02 419	75.86 456	52.54 442	80.26 386	80.56 406	63.80 383	60.39 457	79.70 427	41.41 426	84.66 412	43.34 462	62.62 457	81.86 452

UWE-MVS		72.13 366	71.49 348	74.03 408	86.66 277	47.70 466	81.40 364	76.89 445	63.60 384	75.59 282	84.22 358	39.94 435	85.62 400	48.98 436	86.13 212	88.77 321

0.4-1-1-0.1		70.93 375	67.94 393	79.91 309	79.35 431	61.27 329	78.95 404	82.19 386	63.36 385	67.50 404	69.40 476	39.83 437	91.04 309	62.44 327	68.40 429	87.40 358

jason		81.39 170	80.29 178	84.70 125	86.63 278	69.90 95	85.95 254	86.77 312	63.24 386	81.07 167	89.47 211	61.08 226	92.15 254	78.33 151	90.07 131	92.05 195
jason: jason.
KD-MVS_self_test		68.81 399	67.59 402	72.46 424	74.29 464	45.45 474	77.93 419	87.00 306	63.12 387	63.99 444	78.99 435	42.32 419	84.77 410	56.55 394	64.09 452	87.16 373

gg-mvs-nofinetune		69.95 391	67.96 391	75.94 381	83.07 366	54.51 427	77.23 426	70.29 467	63.11 388	70.32 366	62.33 481	43.62 411	88.69 363	53.88 407	87.76 181	84.62 424

tpmrst		72.39 359	72.13 343	73.18 418	80.54 413	49.91 461	79.91 391	79.08 427	63.11 388	71.69 354	79.95 423	55.32 281	82.77 427	65.66 295	73.89 393	86.87 380

PCF-MVS	73.52 7	80.38 201	78.84 219	85.01 108	87.71 226	68.99 114	83.65 320	91.46 147	63.00 390	77.77 234	90.28 186	66.10 150	95.09 99	61.40 344	88.22 169	90.94 231
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
COLMAP_ROB	66.92 17	73.01 352	70.41 370	80.81 285	87.13 258	65.63 214	88.30 163	84.19 353	62.96 391	63.80 446	87.69 265	38.04 448	92.56 235	46.66 448	74.91 384	84.24 427
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Patchmatch-RL test		70.24 385	67.78 398	77.61 366	77.43 450	59.57 360	71.16 458	70.33 466	62.94 392	68.65 388	72.77 469	50.62 342	85.49 402	69.58 259	66.58 437	87.77 348

lupinMVS		81.39 170	80.27 179	84.76 123	87.35 244	70.21 87	85.55 267	86.41 320	62.85 393	81.32 161	88.61 238	61.68 210	92.24 252	78.41 150	90.26 126	91.83 198

test_vis1_n_1920		75.52 313	75.78 287	74.75 400	79.84 422	57.44 387	83.26 332	85.52 334	62.83 394	79.34 199	86.17 312	45.10 401	79.71 443	78.75 145	81.21 292	87.10 377

EPMVS		69.02 398	68.16 387	71.59 428	79.61 427	49.80 463	77.40 424	66.93 477	62.82 395	70.01 371	79.05 431	45.79 394	77.86 452	56.58 393	75.26 380	87.13 374

PatchMatch-RL		72.38 360	70.90 361	76.80 377	88.60 181	67.38 173	79.53 393	76.17 449	62.75 396	69.36 381	82.00 403	45.51 398	84.89 409	53.62 408	80.58 301	78.12 467

gm-plane-assit					81.40 402	53.83 432			62.72 397		80.94 411		92.39 244	63.40 311

0.3-1-1-0.015		70.03 389	66.80 411	79.72 319	78.18 442	61.07 333	77.63 422	82.32 385	62.65 398	65.50 430	67.29 477	37.62 451	90.91 316	61.99 337	68.04 431	87.19 370

FMVSNet5		69.50 394	67.96 391	74.15 406	82.97 374	55.35 418	80.01 389	82.12 388	62.56 399	63.02 447	81.53 405	36.92 452	81.92 432	48.42 438	74.06 391	85.17 416

sss		73.60 337	73.64 325	73.51 413	82.80 377	55.01 422	76.12 432	81.69 392	62.47 400	74.68 314	85.85 318	57.32 264	78.11 450	60.86 349	80.93 294	87.39 359

0.4-1-1-0.2		70.01 390	66.86 410	79.44 327	77.61 448	60.64 345	76.77 429	82.34 384	62.40 401	65.91 428	66.65 478	40.05 434	90.83 318	61.77 341	68.24 430	86.86 381

WB-MVSnew		71.96 368	71.65 347	72.89 420	84.67 329	51.88 447	82.29 348	77.57 436	62.31 402	73.67 328	83.00 385	53.49 302	81.10 438	45.75 455	82.13 282	85.70 405

AllTest		70.96 374	68.09 389	79.58 324	85.15 314	63.62 273	84.58 294	79.83 418	62.31 402	60.32 459	86.73 289	32.02 464	88.96 359	50.28 427	71.57 413	86.15 395

TestCases				79.58 324	85.15 314	63.62 273		79.83 418	62.31 402	60.32 459	86.73 289	32.02 464	88.96 359	50.28 427	71.57 413	86.15 395

1112_ss		77.40 280	76.43 280	80.32 297	89.11 162	60.41 350	83.65 320	87.72 285	62.13 405	73.05 335	86.72 291	62.58 194	89.97 337	62.11 336	80.80 298	90.59 246

PVSNet	64.34 18	72.08 367	70.87 362	75.69 384	86.21 286	56.44 401	74.37 448	80.73 403	62.06 406	70.17 369	82.23 399	42.86 416	83.31 423	54.77 402	84.45 243	87.32 365

UWE-MVS-28		65.32 424	64.93 418	66.49 455	78.70 435	38.55 492	77.86 421	64.39 484	62.00 407	64.13 442	83.60 374	41.44 425	76.00 465	31.39 483	80.89 295	84.92 419

LS3D		76.95 288	74.82 307	83.37 199	90.45 108	67.36 174	89.15 120	86.94 308	61.87 408	69.52 379	90.61 177	51.71 328	94.53 124	46.38 451	86.71 201	88.21 339

CostFormer		75.24 319	73.90 321	79.27 330	82.65 382	58.27 370	80.80 371	82.73 380	61.57 409	75.33 297	83.13 383	55.52 280	91.07 308	64.98 300	78.34 332	88.45 331

new-patchmatchnet		61.73 435	61.73 435	61.70 461	72.74 476	24.50 504	69.16 468	78.03 433	61.40 410	56.72 471	75.53 462	38.42 445	76.48 460	45.95 454	57.67 467	84.13 429

ANet_high		50.57 453	46.10 457	63.99 458	48.67 503	39.13 491	70.99 460	80.85 401	61.39 411	31.18 492	57.70 489	17.02 490	73.65 480	31.22 484	15.89 502	79.18 465

MS-PatchMatch		73.83 334	72.67 336	77.30 372	83.87 344	66.02 200	81.82 353	84.66 344	61.37 412	68.61 389	82.82 390	47.29 374	88.21 370	59.27 362	84.32 246	77.68 468

USDC		70.33 384	68.37 384	76.21 380	80.60 412	56.23 406	79.19 399	86.49 319	60.89 413	61.29 454	85.47 328	31.78 466	89.47 347	53.37 410	76.21 362	82.94 444

cascas		76.72 291	74.64 309	82.99 218	85.78 296	65.88 206	82.33 347	89.21 231	60.85 414	72.74 339	81.02 409	47.28 375	93.75 165	67.48 278	85.02 231	89.34 299

sc_t1		72.19 365	69.51 376	80.23 300	84.81 322	61.09 332	84.68 289	80.22 415	60.70 415	71.27 358	83.58 375	36.59 454	89.24 351	60.41 351	63.31 454	90.37 255

MDTV_nov1_ep13			69.97 374		83.18 363	53.48 434	77.10 428	80.18 417	60.45 416	69.33 382	80.44 415	48.89 369	86.90 385	51.60 418	78.51 326

TinyColmap		67.30 412	64.81 419	74.76 399	81.92 394	56.68 398	80.29 384	81.49 395	60.33 417	56.27 474	83.22 380	24.77 479	87.66 379	45.52 456	69.47 422	79.95 463

test-mter		71.41 370	70.39 371	74.48 401	81.35 404	58.04 373	78.38 411	77.46 437	60.32 418	69.95 374	79.00 433	36.08 457	79.24 444	66.13 288	84.83 234	86.15 395

1314		76.53 293	75.30 302	80.21 301	83.93 342	62.32 311	84.66 290	88.81 249	60.23 419	70.16 370	84.07 363	55.30 282	90.73 324	67.37 279	83.21 269	87.59 353

PatchT		68.46 405	67.85 394	70.29 438	80.70 411	43.93 482	72.47 453	74.88 453	60.15 420	70.55 362	76.57 450	49.94 352	81.59 433	50.58 423	74.83 385	85.34 411

无先验							87.48 189	88.98 242	60.00 421				94.12 142	67.28 280		88.97 312

CR-MVSNet		73.37 342	71.27 354	79.67 322	81.32 406	65.19 229	75.92 434	80.30 413	59.92 422	72.73 340	81.19 406	52.50 308	86.69 386	59.84 356	77.71 336	87.11 375

TDRefinement		67.49 409	64.34 421	76.92 375	73.47 471	61.07 333	84.86 286	82.98 375	59.77 423	58.30 466	85.13 337	26.06 475	87.89 375	47.92 445	60.59 464	81.81 454

dp		66.80 415	65.43 416	70.90 437	79.74 426	48.82 465	75.12 443	74.77 454	59.61 424	64.08 443	77.23 447	42.89 415	80.72 440	48.86 437	66.58 437	83.16 439

our_test_3		69.14 397	67.00 408	75.57 386	79.80 424	58.80 364	77.96 418	77.81 434	59.55 425	62.90 450	78.25 440	47.43 373	83.97 415	51.71 417	67.58 434	83.93 432

Test_1112_low_res		76.40 301	75.44 294	79.27 330	89.28 151	58.09 371	81.69 358	87.07 305	59.53 426	72.48 344	86.67 296	61.30 220	89.33 348	60.81 350	80.15 307	90.41 253

pmmvs4		74.03 333	71.91 344	80.39 293	81.96 392	68.32 136	81.45 362	82.14 387	59.32 427	69.87 376	85.13 337	52.40 310	88.13 372	60.21 354	74.74 386	84.73 423

testdata				79.97 308	90.90 99	64.21 261		84.71 343	59.27 428	85.40 76	92.91 95	62.02 205	89.08 355	68.95 265	91.37 106	86.63 389

WB-MVS		54.94 443	54.72 444	55.60 471	73.50 469	20.90 506	74.27 449	61.19 488	59.16 429	50.61 480	74.15 465	47.19 376	75.78 468	17.31 498	35.07 490	70.12 478

ppachtmachnet_test		70.04 388	67.34 406	78.14 353	79.80 424	61.13 330	79.19 399	80.59 405	59.16 429	65.27 433	79.29 430	46.75 382	87.29 382	49.33 434	66.72 435	86.00 401

RPSCF		73.23 349	71.46 349	78.54 345	82.50 384	59.85 355	82.18 350	82.84 379	58.96 431	71.15 361	89.41 217	45.48 400	84.77 410	58.82 369	71.83 411	91.02 228

pmmvs-eth3d		70.50 382	67.83 396	78.52 347	77.37 451	66.18 197	81.82 353	81.51 394	58.90 432	63.90 445	80.42 416	42.69 417	86.28 392	58.56 371	65.30 449	83.11 440

tt0320-xc		70.11 387	67.45 404	78.07 356	85.33 309	59.51 361	83.28 331	78.96 428	58.77 433	67.10 412	80.28 419	36.73 453	87.42 381	56.83 391	59.77 466	87.29 366

OpenMVS_ROB	64.09 19	70.56 381	68.19 386	77.65 365	80.26 415	59.41 362	85.01 282	82.96 376	58.76 434	65.43 432	82.33 396	37.63 450	91.23 298	45.34 458	76.03 363	82.32 448

114514_t		80.68 190	79.51 201	84.20 156	94.09 42	67.27 178	89.64 96	91.11 156	58.75 435	74.08 322	90.72 171	58.10 255	95.04 100	69.70 257	89.42 143	90.30 259

Patchmtry		70.74 378	69.16 380	75.49 389	80.72 410	54.07 430	74.94 445	80.30 413	58.34 436	70.01 371	81.19 406	52.50 308	86.54 388	53.37 410	71.09 416	85.87 404

test_cas_vis1_n_1920		73.76 335	73.74 324	73.81 411	75.90 455	59.77 356	80.51 379	82.40 382	58.30 437	81.62 158	85.69 320	44.35 407	76.41 461	76.29 177	78.61 323	85.23 413

Anonymous20240521		68.80 400	67.22 407	73.55 412	74.33 463	54.11 429	83.18 333	85.61 333	58.15 438	61.68 453	80.94 411	30.71 469	81.27 437	57.00 388	73.34 401	85.28 412

tt0320		70.49 383	68.03 390	77.89 358	84.78 323	59.12 363	83.55 324	80.44 410	58.13 439	67.43 408	80.41 417	39.26 440	87.54 380	55.12 399	63.18 455	86.99 378

旧先验2							86.56 232		58.10 440	87.04 62			88.98 357	74.07 205

JIA-IIPM		66.32 420	62.82 432	76.82 376	77.09 452	61.72 322	65.34 481	75.38 450	58.04 441	64.51 439	62.32 482	42.05 423	86.51 389	51.45 420	69.22 424	82.21 449

pmmvs5		71.55 369	70.20 373	75.61 385	77.83 444	56.39 402	81.74 355	80.89 400	57.76 442	67.46 406	84.49 347	49.26 363	85.32 405	57.08 386	75.29 379	85.11 417

TESTMET0.1,1		69.89 392	69.00 381	72.55 423	79.27 433	56.85 393	78.38 411	74.71 456	57.64 443	68.09 396	77.19 448	37.75 449	76.70 457	63.92 307	84.09 249	84.10 430

RPMNet		73.51 338	70.49 368	82.58 241	81.32 406	65.19 229	75.92 434	92.27 95	57.60 444	72.73 340	76.45 451	52.30 311	95.43 78	48.14 443	77.71 336	87.11 375

SSC-MVS		53.88 446	53.59 446	54.75 473	72.87 475	19.59 507	73.84 451	60.53 490	57.58 445	49.18 484	73.45 468	46.34 388	75.47 471	16.20 501	32.28 492	69.20 479

新几何1				83.42 196	93.13 60	70.71 81		85.48 335	57.43 446	81.80 153	91.98 122	63.28 177	92.27 250	64.60 303	92.99 76	87.27 367

YYNet1		65.03 425	62.91 430	71.38 429	75.85 457	56.60 399	69.12 469	74.66 457	57.28 447	54.12 476	77.87 442	45.85 393	74.48 475	49.95 430	61.52 461	83.05 441

MDA-MVSNet_test_wron		65.03 425	62.92 429	71.37 430	75.93 454	56.73 395	69.09 470	74.73 455	57.28 447	54.03 477	77.89 441	45.88 392	74.39 476	49.89 431	61.55 460	82.99 443

Anonymous20231206		68.60 401	67.80 397	71.02 435	80.23 417	50.75 458	78.30 415	80.47 408	56.79 449	66.11 427	82.63 393	46.35 387	78.95 446	43.62 461	75.70 366	83.36 437

tpm2		73.26 347	71.46 349	78.63 340	83.34 357	56.71 397	80.65 377	80.40 412	56.63 450	73.55 329	82.02 402	51.80 326	91.24 297	56.35 395	78.42 330	87.95 343

CHOSEN 1792x2688		77.63 276	75.69 288	83.44 195	89.98 123	68.58 130	78.70 407	87.50 289	56.38 451	75.80 280	86.84 287	58.67 251	91.40 292	61.58 343	85.75 223	90.34 256

HyFIR lowres test		77.53 277	75.40 296	83.94 181	89.59 132	66.62 190	80.36 382	88.64 263	56.29 452	76.45 265	85.17 336	57.64 260	93.28 194	61.34 346	83.10 271	91.91 197

usedtu_dtu_shiyan2		64.75 428	61.63 436	74.10 407	70.64 480	53.18 440	82.10 352	81.27 399	56.22 453	56.39 473	74.67 464	27.94 473	83.56 419	42.71 465	62.73 456	85.57 407

PVSNet_0	57.27 20	61.67 436	59.27 439	68.85 445	79.61 427	57.44 387	68.01 471	73.44 460	55.93 454	58.54 465	70.41 474	44.58 404	77.55 453	47.01 447	35.91 489	71.55 477

UnsupCasMVSNet_bld		63.70 431	61.53 437	70.21 439	73.69 468	51.39 453	72.82 452	81.89 389	55.63 455	57.81 468	71.80 471	38.67 444	78.61 447	49.26 435	52.21 479	80.63 460

MDTV_nov1_ep13_2view						37.79 493	75.16 441		55.10 456	66.53 420		49.34 361		53.98 406		87.94 344

MVS		78.19 258	76.99 266	81.78 257	85.66 298	66.99 184	84.66 290	90.47 175	55.08 457	72.02 351	85.27 332	63.83 174	94.11 143	66.10 290	89.80 136	84.24 427

test222					91.50 87	68.26 138	84.16 310	83.20 370	54.63 458	79.74 189	91.63 138	58.97 248			91.42 104	86.77 384

dongtai		45.42 457	45.38 458	45.55 477	73.36 472	26.85 501	67.72 472	34.19 503	54.15 459	49.65 483	56.41 492	25.43 476	62.94 493	19.45 496	28.09 494	46.86 496

CHOSEN 280x420		66.51 418	64.71 420	71.90 426	81.45 401	63.52 282	57.98 490	68.95 473	53.57 460	62.59 451	76.70 449	46.22 389	75.29 473	55.25 398	79.68 311	76.88 470

ADS-MVSNet2		66.20 423	63.33 427	74.82 398	79.92 420	58.75 365	67.55 473	75.19 451	53.37 461	65.25 434	75.86 459	42.32 419	80.53 441	41.57 468	68.91 425	85.18 414

ADS-MVSNet		64.36 429	62.88 431	68.78 446	79.92 420	47.17 470	67.55 473	71.18 465	53.37 461	65.25 434	75.86 459	42.32 419	73.99 478	41.57 468	68.91 425	85.18 414

LF4IMVS		64.02 430	62.19 433	69.50 441	70.90 479	53.29 438	76.13 431	77.18 442	52.65 463	58.59 464	80.98 410	23.55 482	76.52 459	53.06 412	66.66 436	78.68 466

tpm cat1		70.57 380	68.31 385	77.35 371	82.41 387	57.95 376	78.08 416	80.22 415	52.04 464	68.54 392	77.66 444	52.00 319	87.84 376	51.77 416	72.07 410	86.25 392

test_vis1_n		69.85 393	69.21 379	71.77 427	72.66 477	55.27 420	81.48 361	76.21 448	52.03 465	75.30 298	83.20 382	28.97 471	76.22 463	74.60 199	78.41 331	83.81 433

Patchmatch-test		64.82 427	63.24 428	69.57 440	79.42 430	49.82 462	63.49 487	69.05 472	51.98 466	59.95 461	80.13 421	50.91 338	70.98 482	40.66 470	73.57 396	87.90 345

N_pmnet		52.79 449	53.26 447	51.40 475	78.99 434	7.68 518	69.52 465	3.89 517	51.63 467	57.01 470	74.98 463	40.83 430	65.96 490	37.78 475	64.67 450	80.56 462

test_fmvs1_n		70.86 377	70.24 372	72.73 422	72.51 478	55.28 419	81.27 367	79.71 420	51.49 468	78.73 206	84.87 342	27.54 474	77.02 455	76.06 181	79.97 310	85.88 403

test_fmvs1		70.93 375	70.52 367	72.16 425	73.71 467	55.05 421	80.82 370	78.77 429	51.21 469	78.58 211	84.41 350	31.20 468	76.94 456	75.88 185	80.12 309	84.47 425

PMMVS		69.34 396	68.67 382	71.35 432	75.67 458	62.03 316	75.17 440	73.46 459	50.00 470	68.68 387	79.05 431	52.07 318	78.13 449	61.16 347	82.77 274	73.90 474

test_fmvs2		68.35 406	67.48 403	70.98 436	69.50 482	51.95 445	80.05 388	76.38 447	49.33 471	74.65 315	84.38 351	23.30 483	75.40 472	74.51 200	75.17 382	85.60 406

ttmdpeth		59.91 438	57.10 442	68.34 449	67.13 486	46.65 473	74.64 446	67.41 476	48.30 472	62.52 452	85.04 341	20.40 485	75.93 466	42.55 466	45.90 487	82.44 447

CMPMVS	51.72 21	70.19 386	68.16 387	76.28 379	73.15 474	57.55 385	79.47 394	83.92 355	48.02 473	56.48 472	84.81 344	43.13 414	86.42 391	62.67 325	81.81 287	84.89 420
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
mvsany_test1		62.30 434	61.26 438	65.41 457	69.52 481	54.86 423	66.86 475	49.78 497	46.65 474	68.50 393	83.21 381	49.15 364	66.28 489	56.93 389	60.77 462	75.11 473

kuosan		39.70 461	40.40 462	37.58 481	64.52 489	26.98 499	65.62 480	33.02 504	46.12 475	42.79 487	48.99 497	24.10 481	46.56 501	12.16 505	26.30 495	39.20 498

test_fmvs3		63.36 432	61.82 434	67.98 451	62.51 491	46.96 472	77.37 425	74.03 458	45.24 476	67.50 404	78.79 436	12.16 495	72.98 481	72.77 221	66.02 439	83.99 431

CVMVSNet		72.99 353	72.58 338	74.25 405	84.28 333	50.85 457	86.41 237	83.45 364	44.56 477	73.23 333	87.54 271	49.38 360	85.70 398	65.90 292	78.44 327	86.19 394

test_vis1_rt		60.28 437	58.42 440	65.84 456	67.25 485	55.60 415	70.44 463	60.94 489	44.33 478	59.00 463	66.64 479	24.91 478	68.67 487	62.80 320	69.48 421	73.25 475

mvsany_test3		53.99 445	51.45 450	61.61 462	55.51 496	44.74 481	63.52 486	45.41 501	43.69 479	58.11 467	76.45 451	17.99 488	63.76 492	54.77 402	47.59 483	76.34 471

EU-MVSNet		68.53 404	67.61 401	71.31 433	78.51 437	47.01 471	84.47 296	84.27 351	42.27 480	66.44 424	84.79 345	40.44 432	83.76 416	58.76 370	68.54 428	83.17 438

FPMVS		53.68 447	51.64 449	59.81 464	65.08 488	51.03 455	69.48 466	69.58 470	41.46 481	40.67 488	72.32 470	16.46 491	70.00 486	24.24 493	65.42 448	58.40 488

pmmvs3		57.79 440	54.26 445	68.37 448	64.02 490	56.72 396	75.12 443	65.17 481	40.20 482	52.93 478	69.86 475	20.36 486	75.48 470	45.45 457	55.25 475	72.90 476

new_pmnet		50.91 452	50.29 452	52.78 474	68.58 483	34.94 496	63.71 485	56.63 494	39.73 483	44.95 485	65.47 480	21.93 484	58.48 494	34.98 479	56.62 469	64.92 482

MVS-HIRNet		59.14 439	57.67 441	63.57 459	81.65 396	43.50 483	71.73 455	65.06 482	39.59 484	51.43 479	57.73 488	38.34 446	82.58 428	39.53 471	73.95 392	64.62 483

MVStest1		56.63 442	52.76 448	68.25 450	61.67 492	53.25 439	71.67 456	68.90 474	38.59 485	50.59 481	83.05 384	25.08 477	70.66 483	36.76 477	38.56 488	80.83 459

PMMVS2		40.82 460	38.86 464	46.69 476	53.84 498	16.45 511	48.61 493	49.92 496	37.49 486	31.67 491	60.97 484	8.14 501	56.42 496	28.42 486	30.72 493	67.19 481

test_vis3_rt		49.26 454	47.02 456	56.00 468	54.30 497	45.27 478	66.76 477	48.08 498	36.83 487	44.38 486	53.20 494	7.17 502	64.07 491	56.77 392	55.66 471	58.65 487

test_f		52.09 450	50.82 451	55.90 469	53.82 499	42.31 488	59.42 489	58.31 493	36.45 488	56.12 475	70.96 473	12.18 494	57.79 495	53.51 409	56.57 470	67.60 480

LCM-MVSNet		54.25 444	49.68 454	67.97 452	53.73 500	45.28 477	66.85 476	80.78 402	35.96 489	39.45 490	62.23 483	8.70 499	78.06 451	48.24 442	51.20 480	80.57 461

APD_test1		53.31 448	49.93 453	63.42 460	65.68 487	50.13 460	71.59 457	66.90 478	34.43 490	40.58 489	71.56 472	8.65 500	76.27 462	34.64 480	55.36 473	63.86 484

PMVS	37.38 22	44.16 459	40.28 463	55.82 470	40.82 505	42.54 487	65.12 482	63.99 485	34.43 490	24.48 497	57.12 490	3.92 505	76.17 464	17.10 499	55.52 472	48.75 493
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		45.18 458	41.86 461	55.16 472	77.03 453	51.52 451	32.50 499	80.52 407	32.46 492	27.12 495	35.02 502	9.52 498	75.50 469	22.31 495	60.21 465	38.45 499
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DSMNet-mixed		57.77 441	56.90 443	60.38 463	67.70 484	35.61 494	69.18 467	53.97 495	32.30 493	57.49 469	79.88 424	40.39 433	68.57 488	38.78 474	72.37 405	76.97 469

testf1		45.72 455	41.96 459	57.00 466	56.90 494	45.32 475	66.14 478	59.26 491	26.19 494	30.89 493	60.96 485	4.14 503	70.64 484	26.39 491	46.73 485	55.04 489

APD_test2		45.72 455	41.96 459	57.00 466	56.90 494	45.32 475	66.14 478	59.26 491	26.19 494	30.89 493	60.96 485	4.14 503	70.64 484	26.39 491	46.73 485	55.04 489

E-PMN		31.77 462	30.64 465	35.15 483	52.87 501	27.67 498	57.09 491	47.86 499	24.64 496	16.40 506	33.05 503	11.23 496	54.90 497	14.46 502	18.15 500	22.87 504

EMVS		30.81 464	29.65 466	34.27 484	50.96 502	25.95 502	56.58 492	46.80 500	24.01 497	15.53 507	30.68 505	12.47 493	54.43 498	12.81 504	17.05 501	22.43 505

RoMa-SfM		28.67 466	25.38 470	38.54 479	32.61 509	22.48 505	40.24 494	7.23 513	21.81 498	26.66 496	60.46 487	0.96 509	41.72 502	26.47 490	11.95 505	51.40 492

DKM		25.67 468	23.01 472	33.64 485	32.08 510	19.25 509	37.50 496	5.52 514	18.67 499	23.58 500	55.44 493	0.64 513	34.02 504	23.95 494	9.73 506	47.66 495

PDCNetPlus		24.75 469	22.46 473	31.64 486	35.53 507	17.00 510	32.00 500	9.46 510	18.43 500	18.56 505	51.31 496	1.65 507	33.00 506	26.51 489	8.70 508	44.91 497

MVE	26.22 23	30.37 465	25.89 469	43.81 478	44.55 504	35.46 495	28.87 502	39.07 502	18.20 501	18.58 504	40.18 500	2.68 506	47.37 500	17.07 500	23.78 497	48.60 494
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX				27.40 488	40.17 506	26.90 500		24.59 507	17.44 502	23.95 498	48.61 498	9.77 497	26.48 507	18.06 497	24.47 496	28.83 503

LoFTR		27.52 467	24.27 471	37.29 482	34.75 508	19.27 508	33.78 498	21.60 508	12.42 503	21.61 502	56.59 491	0.91 510	40.37 503	13.94 503	22.80 498	52.22 491

MatchFormer		22.13 470	19.86 475	28.93 487	28.66 511	15.74 512	31.91 501	17.10 509	7.75 504	18.87 503	47.50 499	0.62 515	33.92 505	7.49 508	18.87 499	37.14 500

wuyk23d		16.82 473	15.94 476	19.46 491	58.74 493	31.45 497	39.22 495	3.74 519	6.84 505	6.04 510	2.70 534	1.27 508	24.29 509	10.54 506	14.40 504	2.63 517

ELoFTR		14.23 474	11.56 477	22.24 489	11.02 517	6.56 519	13.59 506	7.57 512	5.55 506	11.96 509	39.09 501	0.21 524	24.93 508	9.43 507	5.66 513	35.22 501

GLUNet-SfM		12.90 475	10.00 478	21.62 490	13.58 516	8.30 516	10.19 508	9.30 511	4.31 507	12.18 508	30.90 504	0.50 519	22.76 510	4.89 509	4.14 519	33.79 502

test_method		31.52 463	29.28 467	38.23 480	27.03 512	6.50 520	20.94 503	62.21 487	4.05 508	22.35 501	52.50 495	13.33 492	47.58 499	27.04 488	34.04 491	60.62 485

ALIKED-LG		8.61 476	8.70 480	8.33 493	20.63 513	8.70 515	15.50 504	4.61 515	2.19 509	5.84 511	18.70 507	0.80 511	8.06 512	1.03 517	8.97 507	8.25 506

ALIKED-MNN		7.86 477	7.83 483	7.97 494	19.40 514	8.86 514	14.48 505	3.90 516	1.59 510	4.74 516	16.49 508	0.59 516	7.65 513	0.91 518	8.34 510	7.39 509

ALIKED-NN		7.51 478	7.61 484	7.21 495	18.26 515	8.10 517	13.45 507	3.88 518	1.50 511	4.87 514	16.47 509	0.64 513	7.00 514	0.88 519	8.50 509	6.52 514

tmp_tt		18.61 472	21.40 474	10.23 492	4.82 536	10.11 513	34.70 497	30.74 506	1.48 512	23.91 499	26.07 506	28.42 472	13.41 511	27.12 487	15.35 503	7.17 512

SP-DiffGlue		4.29 484	4.46 487	3.77 500	3.68 537	2.12 527	5.97 513	2.22 521	1.10 513	4.89 513	13.93 511	0.66 512	1.95 521	2.47 510	5.24 514	7.22 511

XFeat-MNN		4.39 483	4.49 486	4.10 496	2.88 538	1.91 533	5.86 514	2.57 520	1.06 514	5.04 512	13.99 510	0.43 522	4.47 515	2.00 511	6.55 511	5.92 515

SP-SuperGlue		4.24 486	4.38 489	3.81 499	10.75 519	2.00 529	8.18 510	2.09 522	1.00 515	2.41 517	8.29 514	0.56 517	2.05 520	1.27 513	4.91 516	7.39 509

SP-LightGlue		4.27 485	4.41 488	3.86 497	10.99 518	1.99 530	8.19 509	2.06 523	0.98 516	2.37 518	8.29 514	0.56 517	2.10 518	1.27 513	4.99 515	7.48 508

SP-NN		4.00 488	4.12 491	3.63 501	9.92 521	1.81 535	7.94 512	1.90 526	0.86 517	2.15 520	8.00 517	0.50 519	2.09 519	1.20 515	4.63 518	6.98 513

SP-MNN		4.14 487	4.24 490	3.82 498	10.32 520	1.83 534	8.11 511	1.99 524	0.82 518	2.23 519	8.27 516	0.47 521	2.14 517	1.20 515	4.77 517	7.49 507

XFeat-NN		3.78 489	3.96 492	3.23 502	2.65 539	1.53 538	4.99 515	1.92 525	0.81 519	4.77 515	12.37 513	0.38 523	3.39 516	1.64 512	6.13 512	4.77 516

SIFT-NN		2.77 490	2.92 493	2.34 503	8.70 522	3.08 521	4.46 516	1.01 528	0.68 520	1.46 521	5.49 518	0.16 525	1.65 522	0.26 520	4.04 520	2.27 518

SIFT-MNN		2.63 491	2.75 494	2.25 504	8.10 523	2.84 522	4.08 517	1.02 527	0.68 520	1.28 522	5.34 521	0.15 526	1.64 523	0.26 520	3.88 522	2.27 518

SIFT-NN-UMatch		2.26 495	2.39 498	1.89 509	6.21 531	2.08 528	3.76 519	0.83 531	0.66 522	1.04 526	5.09 522	0.14 527	1.52 526	0.23 523	3.51 524	2.07 522

SIFT-NCM-Cal		2.40 493	2.52 496	2.05 506	7.74 524	2.54 524	3.75 520	0.84 530	0.65 523	0.89 529	4.78 527	0.13 530	1.60 524	0.19 531	3.71 523	2.01 524

SIFT-NN-NCMNet		2.52 492	2.64 495	2.14 505	7.53 525	2.74 523	4.00 518	0.98 529	0.65 523	1.24 524	5.08 524	0.14 527	1.60 524	0.23 523	3.94 521	2.07 522

SIFT-NN-CMatch		2.31 494	2.41 497	2.00 507	6.59 529	2.34 526	3.48 521	0.83 531	0.65 523	1.28 522	5.09 522	0.14 527	1.52 526	0.23 523	3.41 525	2.14 520

SIFT-ConvMatch		2.25 496	2.37 499	1.90 508	7.29 526	2.37 525	3.21 524	0.75 533	0.65 523	1.03 527	4.91 525	0.12 533	1.51 528	0.22 526	3.13 527	1.81 525

SIFT-UMatch		2.16 497	2.30 500	1.72 511	6.99 527	1.97 532	3.32 522	0.70 535	0.64 527	0.91 528	4.86 526	0.12 533	1.49 529	0.22 526	2.97 528	1.72 527

SIFT-CM-Cal		2.02 499	2.13 502	1.67 512	6.79 528	1.99 530	2.79 526	0.64 536	0.63 528	0.87 530	4.48 530	0.13 530	1.41 531	0.19 531	2.70 529	1.61 529

SIFT-UM-Cal		1.97 500	2.12 503	1.52 513	6.57 530	1.67 536	2.93 525	0.57 538	0.62 529	0.83 531	4.55 529	0.11 535	1.37 532	0.20 530	2.69 530	1.53 530

SIFT-NN-PointCN		2.07 498	2.18 501	1.74 510	5.75 532	1.65 537	3.27 523	0.73 534	0.60 530	1.07 525	4.62 528	0.13 530	1.43 530	0.21 528	3.22 526	2.12 521

SIFT-NCMNet		1.44 503	1.56 506	1.08 516	5.14 535	1.07 541	1.97 529	0.32 540	0.56 531	0.64 534	3.23 533	0.07 538	1.01 535	0.14 535	1.95 533	1.15 531

SIFT-PCN-Cal		1.72 501	1.82 505	1.39 514	5.64 533	1.19 540	2.39 528	0.53 539	0.55 532	0.72 532	3.90 531	0.09 536	1.22 534	0.17 533	2.42 532	1.76 526

SIFT-PointCN		1.72 501	1.83 504	1.36 515	5.55 534	1.22 539	2.59 527	0.59 537	0.55 532	0.71 533	3.77 532	0.08 537	1.24 533	0.17 533	2.48 531	1.63 528

EGC-MVSNET		52.07 451	47.05 455	67.14 453	83.51 354	60.71 343	80.50 380	67.75 475	0.07 534	0.43 535	75.85 461	24.26 480	81.54 434	28.82 485	62.25 458	59.16 486

testmvs		6.04 481	8.02 482	0.10 518	0.08 540	0.03 543	69.74 464	0.04 541	0.05 535	0.31 536	1.68 535	0.02 540	0.04 536	0.24 522	0.02 534	0.25 533

test123		6.12 480	8.11 481	0.14 517	0.06 541	0.09 542	71.05 459	0.03 542	0.04 536	0.25 537	1.30 536	0.05 539	0.03 537	0.21 528	0.01 535	0.29 532

mmdepth		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

monomultidepth		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

test_blank		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

uanet_test		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

DCPMVS		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

cdsmvs_eth3d_5k		19.96 471	26.61 468	0.00 519	0.00 542	0.00 544	0.00 530	89.26 227	0.00 537	0.00 538	88.61 238	61.62 212	0.00 538	0.00 536	0.00 536	0.00 534

pcd_1.5k_mvsjas		5.26 482	7.02 485	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	63.15 183	0.00 538	0.00 536	0.00 536	0.00 534

sosnet-low-res		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

sosnet		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

uncertanet		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

Regformer		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

ab-mvs-re		7.23 479	9.64 479	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	86.72 291	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

uanet		0.00 504	0.00 507	0.00 519	0.00 542	0.00 544	0.00 530	0.00 543	0.00 537	0.00 538	0.00 537	0.00 541	0.00 538	0.00 536	0.00 536	0.00 534

WAC-MVS						42.58 485								39.46 472

MSC_two_6792asdad				89.16 1	94.34 31	75.53 2		92.99 55					97.53 2	89.67 15	96.44 9	94.41 60

No_MVS				89.16 1	94.34 31	75.53 2		92.99 55					97.53 2	89.67 15	96.44 9	94.41 60

eth-test2					0.00 542

eth-test					0.00 542

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 8				94.02 61	82.45 3	96.87 24	83.77 82	96.48 8	94.88 18

test_0728_SECOND				87.71 35	95.34 1	71.43 61	93.49 10	94.23 6					97.49 4	89.08 22	96.41 12	94.21 73

GSMVS																88.96 313

test_part2					95.06 8	72.65 32				91.80 15

sam_mvs1												51.32 331				88.96 313

sam_mvs												50.01 350

ambc				75.24 393	73.16 473	50.51 459	63.05 488	87.47 290		64.28 440	77.81 443	17.80 489	89.73 342	57.88 379	60.64 463	85.49 408

MTGPA								92.02 113

test_post1							78.90 406				5.43 520	48.81 370	85.44 404	59.25 363

test_post											5.46 519	50.36 346	84.24 413

patchmatchnet-post											74.00 466	51.12 337	88.60 365

GG-mvs-BLEND				75.38 391	81.59 398	55.80 412	79.32 396	69.63 469		67.19 410	73.67 467	43.24 413	88.90 361	50.41 424	84.50 239	81.45 455

MTMP							92.18 39	32.83 505

test9_res														84.90 64	95.70 29	92.87 156

agg_prior2														82.91 91	95.45 32	92.70 161

agg_prior					92.85 68	71.94 53		91.78 129		84.41 96			94.93 102

test_prior4						72.60 34	89.01 125

test_prior				86.33 65	92.61 75	69.59 99		92.97 60					95.48 75			93.91 89

新几何2							86.29 246

旧先验1					91.96 81	65.79 211		86.37 322			93.08 93	69.31 101			92.74 80	88.74 324

原ACMM2							86.86 219

testdata2													91.01 310	62.37 331

segment_acmp												73.08 44

test12				86.80 59	92.63 74	70.70 82		91.79 128		82.71 140		71.67 65	96.16 53		94.50 56	93.54 118

plane_prior7					90.08 117	68.51 132

plane_prior6					89.84 126	68.70 126						60.42 238

plane_prior5								92.44 83					95.38 83	78.71 146	86.32 206	91.33 216

plane_prior4											91.00 165

plane_prior1					89.90 125

n2								0.00 543

nn								0.00 543

door-mid								69.98 468

lessismore_v0				78.97 335	81.01 409	57.15 390		65.99 479		61.16 455	82.82 390	39.12 441	91.34 294	59.67 358	46.92 484	88.43 332

test11								92.23 99

door								69.44 471

HQP5-MVS						66.98 185

BP-MVS														77.47 161

HQP4-MVS										77.24 244			95.11 95			91.03 226

HQP3-MVS								92.19 107							85.99 216

HQP2-MVS												60.17 241

NP-MVS					89.62 131	68.32 136					90.24 188

ACMMP++_ref															81.95 285

ACMMP++															81.25 290

Test By Simon												64.33 169

High-resolution multi-view benchmark