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.

MSP-MVS		90.38 5	91.87 1	85.88 91	92.83 79	64.03 195	93.06 116	94.33 55	82.19 33	93.65 3	96.15 38	85.89 1	97.19 87	91.02 38	97.75 1	96.43 31
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
DVP-MVS++		90.53 4	91.09 5	88.87 16	97.31 4	69.91 42	93.96 73	94.37 53	72.48 193	92.07 9	96.85 18	83.82 2	99.15 2	91.53 34	97.42 4	97.55 4

OPU-MVS				89.97 3	97.52 3	73.15 14	96.89 6				97.00 10	83.82 2	99.15 2	95.72 5	97.63 3	97.62 2

PC_three_1452									80.91 52	94.07 2	96.83 20	83.57 4	99.12 5	95.70 7	97.42 4	97.55 4

DPM-MVS		90.70 3	90.52 9	91.24 1	89.68 160	76.68 2	97.29 1	95.35 16	82.87 26	91.58 14	97.22 4	79.93 5	99.10 9	83.12 106	97.64 2	97.94 1

baseline2		83.68 108	83.42 99	84.48 148	87.37 225	66.00 144	90.06 245	95.93 8	79.71 71	69.08 248	90.39 181	77.92 6	96.28 137	78.91 144	81.38 186	91.16 216

GG-mvs-BLEND				86.53 73	91.91 110	69.67 52	75.02 380	94.75 34		78.67 141	90.85 173	77.91 7	94.56 212	72.25 193	93.74 45	95.36 66

gg-mvs-nofinetune		77.18 223	74.31 244	85.80 96	91.42 124	68.36 79	71.78 385	94.72 35	49.61 385	77.12 156	45.92 411	77.41 8	93.98 240	67.62 237	93.16 55	95.05 84

SED-MVS		89.94 9	90.36 10	88.70 18	96.45 12	69.38 55	96.89 6	94.44 47	71.65 223	92.11 7	97.21 5	76.79 9	99.11 6	92.34 26	95.36 14	97.62 2

test_241102_ONE					96.45 12	69.38 55		94.44 47	71.65 223	92.11 7	97.05 8	76.79 9	99.11 6

test_0728_THIRD									72.48 193	90.55 21	96.93 12	76.24 11	99.08 11	91.53 34	94.99 18	96.43 31

DPE-MVS		88.77 17	89.21 16	87.45 43	96.26 20	67.56 103	94.17 60	94.15 60	68.77 272	90.74 19	97.27 2	76.09 12	98.49 29	90.58 42	94.91 21	96.30 34
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
TSAR-MVS + GP.		87.96 21	88.37 21	86.70 65	93.51 61	65.32 160	95.15 36	93.84 66	78.17 100	85.93 57	94.80 80	75.80 13	98.21 34	89.38 45	88.78 109	96.59 19

DeepPCF-MVS	81.17 1	89.72 10	91.38 4	84.72 136	93.00 75	58.16 317	96.72 9	94.41 49	86.50 8	90.25 24	97.83 1	75.46 14	98.67 25	92.78 23	95.49 13	97.32 6

BP-MVS1		86.54 47	86.68 45	86.13 85	87.80 215	67.18 114	92.97 121	95.62 10	79.92 66	82.84 88	94.14 104	74.95 15	96.46 131	82.91 108	88.96 108	94.74 99

dcpmvs_2		87.37 32	87.55 32	86.85 58	95.04 32	68.20 87	90.36 236	90.66 208	79.37 78	81.20 103	93.67 114	74.73 16	96.55 126	90.88 39	92.00 69	95.82 48

MVSTER		82.47 128	82.05 124	83.74 169	92.68 86	69.01 64	91.90 171	93.21 95	79.83 67	72.14 211	85.71 253	74.72 17	94.72 202	75.72 163	72.49 256	87.50 262

test_241102_TWO								94.41 49	71.65 223	92.07 9	97.21 5	74.58 18	99.11 6	92.34 26	95.36 14	96.59 19

WBMVS		81.67 141	80.98 142	83.72 173	93.07 73	69.40 53	94.33 56	93.05 104	76.84 122	72.05 213	84.14 268	74.49 19	93.88 245	72.76 187	68.09 285	87.88 258

test_one_0601					96.32 18	69.74 49		94.18 58	71.42 234	90.67 20	96.85 18	74.45 20

DELS-MVS		90.05 8	90.09 11	89.94 4	93.14 70	73.88 9	97.01 4	94.40 51	88.32 3	85.71 59	94.91 77	74.11 21	98.91 18	87.26 66	95.94 8	97.03 12
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
patch_mono-2		89.71 11	90.99 6	85.85 94	96.04 24	63.70 205	95.04 40	95.19 20	86.74 7	91.53 16	95.15 70	73.86 22	97.58 61	93.38 18	92.00 69	96.28 37

DVP-MVS		89.41 13	89.73 14	88.45 25	96.40 15	69.99 38	96.64 10	94.52 43	71.92 209	90.55 21	96.93 12	73.77 23	99.08 11	91.91 32	94.90 22	96.29 35
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					96.40 15	69.99 38	96.76 8	94.33 55	71.92 209	91.89 11	97.11 7	73.77 23

ET-MVSNet_ETH3D		84.01 98	83.15 108	86.58 70	90.78 141	70.89 28	94.74 48	94.62 41	81.44 44	58.19 343	93.64 115	73.64 25	92.35 292	82.66 110	78.66 210	96.50 27

UBG		86.83 41	86.70 44	87.20 48	93.07 73	69.81 46	93.43 106	95.56 13	81.52 40	81.50 99	92.12 149	73.58 26	96.28 137	84.37 94	85.20 146	95.51 59

CSCG		86.87 38	86.26 49	88.72 17	95.05 31	70.79 29	93.83 85	95.33 17	68.48 276	77.63 149	94.35 95	73.04 27	98.45 30	84.92 88	93.71 47	96.92 14

tttt0517		79.50 181	78.53 182	82.41 209	87.22 229	61.43 263	89.75 254	94.76 33	69.29 264	67.91 266	88.06 219	72.92 28	95.63 168	62.91 281	73.90 247	90.16 227

GDP-MVS		85.54 68	85.32 68	86.18 83	87.64 218	67.95 94	92.91 125	92.36 130	77.81 106	83.69 80	94.31 98	72.84 29	96.41 133	80.39 130	85.95 141	94.19 125

MCST-MVS		91.08 1	91.46 3	89.94 4	97.66 2	73.37 10	97.13 2	95.58 11	89.33 1	85.77 58	96.26 34	72.84 29	99.38 1	92.64 24	95.93 9	97.08 11

thisisatest0515		83.41 111	82.49 120	86.16 84	89.46 166	68.26 83	93.54 98	94.70 37	74.31 154	75.75 166	90.92 171	72.62 31	96.52 127	69.64 214	81.50 185	93.71 147

thisisatest0530		81.15 149	80.07 155	84.39 151	88.26 199	65.63 153	91.40 190	94.62 41	71.27 236	70.93 226	89.18 200	72.47 32	96.04 151	65.62 260	76.89 227	91.49 205

balanced_conf03		89.08 15	88.84 17	89.81 6	93.66 54	75.15 5	90.61 230	93.43 88	84.06 16	86.20 53	90.17 187	72.42 33	96.98 104	93.09 20	95.92 10	97.29 7

testing11		86.71 45	86.44 47	87.55 40	93.54 59	71.35 21	93.65 92	95.58 11	81.36 47	80.69 111	92.21 148	72.30 34	96.46 131	85.18 84	83.43 164	94.82 97

TSAR-MVS + MP.		88.11 20	88.64 18	86.54 72	91.73 115	68.04 90	90.36 236	93.55 81	82.89 25	91.29 17	92.89 130	72.27 35	96.03 152	87.99 56	94.77 26	95.54 58
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
EPP-MVSNet		81.79 140	81.52 131	82.61 203	88.77 186	60.21 292	93.02 120	93.66 77	68.52 275	72.90 197	90.39 181	72.19 36	94.96 194	74.93 171	79.29 204	92.67 177

CostFormer		82.33 130	81.15 135	85.86 93	89.01 180	68.46 77	82.39 336	93.01 106	75.59 137	80.25 118	81.57 300	72.03 37	94.96 194	79.06 142	77.48 221	94.16 128

HPM-MVS++		89.37 14	89.95 13	87.64 34	95.10 30	68.23 86	95.24 33	94.49 45	82.43 30	88.90 34	96.35 31	71.89 38	98.63 26	88.76 52	96.40 6	96.06 41

testing99		86.01 56	85.47 65	87.63 38	93.62 55	71.25 23	93.47 104	95.23 19	80.42 58	80.60 113	91.95 153	71.73 39	96.50 129	80.02 133	82.22 176	95.13 80

MVSMamba_PlusPlus		84.97 79	83.65 90	88.93 14	90.17 151	74.04 8	87.84 288	92.69 118	62.18 328	81.47 101	87.64 225	71.47 40	96.28 137	84.69 90	94.74 31	96.47 28

CNVR-MVS		90.32 6	90.89 8	88.61 22	96.76 8	70.65 30	96.47 14	94.83 31	84.83 12	89.07 33	96.80 21	70.86 41	99.06 15	92.64 24	95.71 11	96.12 40

IB-MVS	77.80 4	82.18 132	80.46 153	87.35 45	89.14 177	70.28 35	95.59 26	95.17 22	78.85 90	70.19 236	85.82 251	70.66 42	97.67 53	72.19 196	66.52 297	94.09 132
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
testing91		85.93 58	85.31 69	87.78 32	93.59 57	71.47 19	93.50 101	95.08 26	80.26 60	80.53 114	91.93 154	70.43 43	96.51 128	80.32 131	82.13 178	95.37 64

ETVMVS		84.22 94	83.71 88	85.76 98	92.58 89	68.25 85	92.45 147	95.53 15	79.54 74	79.46 127	91.64 161	70.29 44	94.18 227	69.16 222	82.76 172	94.84 94

MM		90.87 2	91.52 2	88.92 15	92.12 100	71.10 27	97.02 3	96.04 6	88.70 2	91.57 15	96.19 36	70.12 45	98.91 18	96.83 1	95.06 17	96.76 15

fmvsm_l_conf0.5_n		87.49 29	88.19 24	85.39 109	86.95 235	64.37 185	94.30 57	88.45 298	80.51 55	92.70 4	96.86 16	69.98 46	97.15 92	95.83 4	88.08 117	94.65 105

baseline1		81.84 139	81.03 140	84.28 156	91.60 118	66.62 130	91.08 210	91.66 170	81.87 36	74.86 178	91.67 160	69.98 46	94.92 197	71.76 199	64.75 312	91.29 214

fmvsm_l_conf0.5_n_a		87.44 31	88.15 25	85.30 113	87.10 232	64.19 192	94.41 53	88.14 307	80.24 63	92.54 5	96.97 11	69.52 48	97.17 88	95.89 3	88.51 112	94.56 108

testing222		85.18 73	84.69 80	86.63 67	92.91 77	69.91 42	92.61 139	95.80 9	80.31 59	80.38 116	92.27 145	68.73 49	95.19 187	75.94 161	83.27 166	94.81 98

alignmvs		87.28 33	86.97 39	88.24 27	91.30 129	71.14 26	95.61 25	93.56 80	79.30 79	87.07 46	95.25 65	68.43 50	96.93 112	87.87 57	84.33 156	96.65 17

PAPM		85.89 60	85.46 66	87.18 49	88.20 203	72.42 15	92.41 148	92.77 114	82.11 34	80.34 117	93.07 125	68.27 51	95.02 190	78.39 149	93.59 49	94.09 132

train_agg		87.21 34	87.42 34	86.60 68	94.18 41	67.28 110	94.16 61	93.51 82	71.87 214	85.52 61	95.33 58	68.19 52	97.27 83	89.09 49	94.90 22	95.25 77

test_8					94.19 40	67.19 112	94.15 63	93.42 89	71.87 214	85.38 64	95.35 57	68.19 52	96.95 109

TEST9					94.18 41	67.28 110	94.16 61	93.51 82	71.75 220	85.52 61	95.33 58	68.01 54	97.27 83

test_prior2							95.10 38		75.40 141	85.25 67	95.61 49	67.94 55		87.47 63	94.77 26

WTY-MVS		86.32 50	85.81 59	87.85 29	92.82 81	69.37 57	95.20 34	95.25 18	82.71 27	81.91 96	94.73 81	67.93 56	97.63 58	79.55 136	82.25 175	96.54 22

APDe-MVS		87.54 27	87.84 28	86.65 66	96.07 23	66.30 138	94.84 46	93.78 67	69.35 263	88.39 36	96.34 32	67.74 57	97.66 56	90.62 41	93.44 51	96.01 44
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_fmvsm_n_1920		87.69 26	88.50 19	85.27 116	87.05 234	63.55 212	93.69 90	91.08 196	84.18 15	90.17 26	97.04 9	67.58 58	97.99 39	95.72 5	90.03 96	94.26 121

tpm2		79.80 177	77.95 191	85.34 112	88.28 198	68.26 83	81.56 342	91.42 179	70.11 254	77.59 151	80.50 318	67.40 59	94.26 225	67.34 239	77.35 222	93.51 152

miper_enhance_ethall		78.86 194	77.97 190	81.54 233	88.00 208	65.17 164	91.41 188	89.15 269	75.19 144	68.79 255	83.98 271	67.17 60	92.82 271	72.73 188	65.30 303	86.62 282

SF-MVS		87.03 36	87.09 37	86.84 59	92.70 85	67.45 108	93.64 93	93.76 70	70.78 247	86.25 51	96.44 29	66.98 61	97.79 47	88.68 53	94.56 34	95.28 73

HY-MVS	76.49 5	84.28 90	83.36 102	87.02 55	92.22 95	67.74 98	84.65 314	94.50 44	79.15 83	82.23 94	87.93 220	66.88 62	96.94 110	80.53 128	82.20 177	96.39 33

EPNet		87.84 24	88.38 20	86.23 82	93.30 64	66.05 142	95.26 32	94.84 30	87.09 5	88.06 37	94.53 86	66.79 63	97.34 76	83.89 99	91.68 74	95.29 71
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
9.14			87.63 30		93.86 48		94.41 53	94.18 58	72.76 188	86.21 52	96.51 27	66.64 64	97.88 44	90.08 43	94.04 39

FIs		79.47 183	79.41 169	79.67 280	85.95 255	59.40 303	91.68 183	93.94 64	78.06 101	68.96 252	88.28 210	66.61 65	91.77 305	66.20 254	74.99 236	87.82 259

NCCC		89.07 16	89.46 15	87.91 28	96.60 10	69.05 63	96.38 15	94.64 40	84.42 13	86.74 49	96.20 35	66.56 66	98.76 24	89.03 51	94.56 34	95.92 46

MVS_0304		90.32 6	90.90 7	88.55 23	94.05 45	70.23 36	97.00 5	93.73 74	87.30 4	92.15 6	96.15 38	66.38 67	98.94 17	96.71 2	94.67 33	96.47 28

reproduce_monomvs		79.49 182	79.11 176	80.64 254	92.91 77	61.47 262	91.17 208	93.28 93	83.09 23	64.04 305	82.38 287	66.19 68	94.57 209	81.19 124	57.71 360	85.88 299

SD-MVS		87.49 29	87.49 33	87.50 42	93.60 56	68.82 69	93.90 77	92.63 123	76.86 121	87.90 39	95.76 45	66.17 69	97.63 58	89.06 50	91.48 78	96.05 42
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
UniMVSNet_NR-MVSNet		78.15 209	77.55 196	79.98 271	84.46 283	60.26 290	92.25 151	93.20 97	77.50 114	68.88 253	86.61 241	66.10 70	92.13 297	66.38 251	62.55 329	87.54 261

CHOSEN 280x420		77.35 221	76.95 209	78.55 295	87.07 233	62.68 236	69.71 391	82.95 364	68.80 271	71.48 222	87.27 233	66.03 71	84.00 375	76.47 159	82.81 170	88.95 242

CANet		89.61 12	89.99 12	88.46 24	94.39 39	69.71 50	96.53 13	93.78 67	86.89 6	89.68 30	95.78 44	65.94 72	99.10 9	92.99 21	93.91 42	96.58 21

segment_acmp												65.94 72

fmvsm_s_conf0.5_n_3		86.88 37	87.99 27	83.58 178	87.26 227	60.74 277	93.21 113	87.94 314	84.22 14	91.70 13	97.27 2	65.91 74	95.02 190	93.95 15	90.42 93	94.99 87

Vis-MVSNet (Re-imp)		79.24 186	79.57 164	78.24 300	88.46 191	52.29 355	90.41 233	89.12 272	74.24 155	69.13 246	91.91 155	65.77 75	90.09 332	59.00 304	88.09 116	92.33 186

FC-MVSNet-test		77.99 211	78.08 188	77.70 303	84.89 276	55.51 341	90.27 239	93.75 73	76.87 120	66.80 285	87.59 226	65.71 76	90.23 329	62.89 282	73.94 245	87.37 266

SMA-MVS		88.14 18	88.29 22	87.67 33	93.21 67	68.72 72	93.85 80	94.03 63	74.18 156	91.74 12	96.67 24	65.61 77	98.42 33	89.24 48	96.08 7	95.88 47
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
test12				87.09 52	94.60 36	68.86 67		92.91 110		82.67 93		65.44 78	97.55 64		93.69 48	94.84 94

fmvsm_l_conf0.5_n_3		87.54 27	88.29 22	85.30 113	86.92 240	62.63 237	95.02 42	90.28 224	84.95 11	90.27 23	96.86 16	65.36 79	97.52 66	94.93 9	90.03 96	95.76 50

test_fmvsmconf_n		86.58 46	87.17 36	84.82 129	85.28 267	62.55 238	94.26 59	89.78 242	83.81 19	87.78 40	96.33 33	65.33 80	96.98 104	94.40 12	87.55 123	94.95 89

旧先验1					91.94 107	60.74 277		91.50 176			94.36 91	65.23 81			91.84 71	94.55 109

1112_ss		80.56 161	79.83 161	82.77 197	88.65 187	60.78 273	92.29 150	88.36 300	72.58 191	72.46 207	94.95 73	65.09 82	93.42 256	66.38 251	77.71 215	94.10 131

MVSFormer		83.75 105	82.88 113	86.37 78	89.24 175	71.18 24	89.07 268	90.69 205	65.80 295	87.13 44	94.34 96	64.99 83	92.67 279	72.83 184	91.80 72	95.27 74

lupinMVS		87.74 25	87.77 29	87.63 38	89.24 175	71.18 24	96.57 12	92.90 111	82.70 28	87.13 44	95.27 63	64.99 83	95.80 157	89.34 46	91.80 72	95.93 45

tpmrst		80.57 160	79.14 175	84.84 128	90.10 152	68.28 82	81.70 340	89.72 249	77.63 112	75.96 165	79.54 332	64.94 85	92.71 276	75.43 165	77.28 224	93.55 151

ZD-MVS					96.63 9	65.50 158		93.50 84	70.74 248	85.26 66	95.19 69	64.92 86	97.29 79	87.51 61	93.01 56

testing3		70.38 299	70.83 284	69.03 366	85.82 259	43.93 397	90.72 224	90.56 211	68.06 277	60.24 331	86.82 240	64.83 87	84.12 371	26.33 407	64.10 319	79.04 376

casdiffmvs_mvg		85.66 65	85.18 71	87.09 52	88.22 202	69.35 58	93.74 89	91.89 155	81.47 41	80.10 119	91.45 163	64.80 88	96.35 135	87.23 67	87.69 121	95.58 56
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
miper_ehance_all_eth		77.60 217	76.44 214	81.09 247	85.70 262	64.41 183	90.65 226	88.64 294	72.31 199	67.37 278	82.52 285	64.77 89	92.64 282	70.67 208	65.30 303	86.24 287

Test_1112_low_res		79.56 180	78.60 181	82.43 206	88.24 201	60.39 289	92.09 159	87.99 311	72.10 207	71.84 215	87.42 229	64.62 90	93.04 260	65.80 258	77.30 223	93.85 145

test2506		83.29 113	82.92 112	84.37 152	88.39 195	63.18 223	92.01 164	91.35 181	77.66 110	78.49 142	91.42 164	64.58 91	95.09 189	73.19 180	89.23 102	94.85 91

DeepC-MVS_fast	79.48 2	87.95 22	88.00 26	87.79 31	95.86 27	68.32 80	95.74 21	94.11 61	83.82 18	83.49 81	96.19 36	64.53 92	98.44 31	83.42 105	94.88 25	96.61 18
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MG-MVS		87.11 35	86.27 48	89.62 8	97.79 1	76.27 4	94.96 44	94.49 45	78.74 94	83.87 79	92.94 128	64.34 93	96.94 110	75.19 167	94.09 38	95.66 53

casdiffmvs		85.37 70	84.87 77	86.84 59	88.25 200	69.07 62	93.04 118	91.76 162	81.27 48	80.84 110	92.07 151	64.23 94	96.06 150	84.98 87	87.43 125	95.39 62
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
cl22		77.94 213	76.78 210	81.42 235	87.57 219	64.93 172	90.67 225	88.86 285	72.45 195	67.63 272	82.68 284	64.07 95	92.91 269	71.79 197	65.30 303	86.44 283

tpm		78.58 202	77.03 206	83.22 190	85.94 257	64.56 174	83.21 329	91.14 192	78.31 98	73.67 190	79.68 330	64.01 96	92.09 299	66.07 255	71.26 266	93.03 168

CDS-MVSNet		81.43 146	80.74 144	83.52 179	86.26 249	64.45 179	92.09 159	90.65 209	75.83 135	73.95 189	89.81 194	63.97 97	92.91 269	71.27 202	82.82 169	93.20 162
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS_Test		84.16 96	83.20 105	87.05 54	91.56 120	69.82 45	89.99 250	92.05 144	77.77 107	82.84 88	86.57 242	63.93 98	96.09 146	74.91 172	89.18 104	95.25 77

APD-MVS		85.93 58	85.99 56	85.76 98	95.98 26	65.21 163	93.59 96	92.58 125	66.54 290	86.17 54	95.88 43	63.83 99	97.00 100	86.39 75	92.94 57	95.06 83
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mvs_anonymous		81.36 147	79.99 158	85.46 106	90.39 147	68.40 78	86.88 303	90.61 210	74.41 151	70.31 235	84.67 262	63.79 100	92.32 294	73.13 181	85.70 143	95.67 52

PVSNet_Blended_VisFu		83.97 99	83.50 93	85.39 109	90.02 153	66.59 132	93.77 87	91.73 163	77.43 116	77.08 158	89.81 194	63.77 101	96.97 107	79.67 135	88.21 115	92.60 179

baseline		85.01 77	84.44 82	86.71 64	88.33 197	68.73 71	90.24 241	91.82 161	81.05 51	81.18 104	92.50 137	63.69 102	96.08 149	84.45 93	86.71 135	95.32 69

myMVS_eth3d		72.58 287	72.74 265	72.10 354	87.87 211	49.45 372	88.07 282	89.01 278	72.91 184	63.11 314	88.10 216	63.63 103	85.54 365	32.73 399	69.23 276	81.32 355

CDPH-MVS		85.71 63	85.46 66	86.46 74	94.75 34	67.19 112	93.89 78	92.83 113	70.90 243	83.09 86	95.28 61	63.62 104	97.36 74	80.63 127	94.18 37	94.84 94

HyFIR lowres test		81.03 154	79.56 165	85.43 107	87.81 214	68.11 89	90.18 242	90.01 237	70.65 249	72.95 196	86.06 249	63.61 105	94.50 216	75.01 170	79.75 199	93.67 148

sasdasda		86.85 39	86.25 50	88.66 20	91.80 113	71.92 16	93.54 98	91.71 165	80.26 60	87.55 41	95.25 65	63.59 106	96.93 112	88.18 54	84.34 154	97.11 9

canonicalmvs		86.85 39	86.25 50	88.66 20	91.80 113	71.92 16	93.54 98	91.71 165	80.26 60	87.55 41	95.25 65	63.59 106	96.93 112	88.18 54	84.34 154	97.11 9

c3_l		76.83 232	75.47 227	80.93 251	85.02 274	64.18 193	90.39 234	88.11 308	71.66 222	66.65 286	81.64 298	63.58 108	92.56 283	69.31 220	62.86 326	86.04 293

SteuartSystems-ACMMP		86.82 43	86.90 41	86.58 70	90.42 145	66.38 135	96.09 17	93.87 65	77.73 108	84.01 78	95.66 47	63.39 109	97.94 40	87.40 64	93.55 50	95.42 60
Skip Steuart: Steuart Systems R&D Blog.
test_fmvsmconf0.1_n		85.71 63	86.08 55	84.62 143	80.83 322	62.33 243	93.84 83	88.81 286	83.50 21	87.00 47	96.01 41	63.36 110	96.93 112	94.04 14	87.29 126	94.61 107

EI-MVSNet-Vis-set		83.77 104	83.67 89	84.06 160	92.79 84	63.56 211	91.76 179	94.81 32	79.65 72	77.87 146	94.09 105	63.35 111	97.90 42	79.35 138	79.36 202	90.74 220

UniMVSNet (Re)		77.58 218	76.78 210	79.98 271	84.11 289	60.80 272	91.76 179	93.17 99	76.56 129	69.93 242	84.78 261	63.32 112	92.36 291	64.89 267	62.51 331	86.78 277

PVSNet_BlendedMVS		83.38 112	83.43 97	83.22 190	93.76 50	67.53 105	94.06 66	93.61 78	79.13 84	81.00 108	85.14 257	63.19 113	97.29 79	87.08 69	73.91 246	84.83 316

PVSNet_Blended		86.73 44	86.86 42	86.31 81	93.76 50	67.53 105	96.33 16	93.61 78	82.34 32	81.00 108	93.08 124	63.19 113	97.29 79	87.08 69	91.38 80	94.13 130

UWE-MVS		80.81 158	81.01 141	80.20 264	89.33 169	57.05 330	91.91 170	94.71 36	75.67 136	75.01 177	89.37 198	63.13 115	91.44 317	67.19 242	82.80 171	92.12 197

PAPM_NR		82.97 120	81.84 128	86.37 78	94.10 44	66.76 127	87.66 292	92.84 112	69.96 256	74.07 187	93.57 117	63.10 116	97.50 67	70.66 209	90.58 90	94.85 91

nrg030		80.93 155	79.86 160	84.13 159	83.69 294	68.83 68	93.23 111	91.20 187	75.55 138	75.06 176	88.22 215	63.04 117	94.74 201	81.88 115	66.88 294	88.82 245

fmvsm_s_conf0.5_n		86.39 49	86.91 40	84.82 129	87.36 226	63.54 213	94.74 48	90.02 236	82.52 29	90.14 27	96.92 14	62.93 118	97.84 46	95.28 8	82.26 174	93.07 167

MGCFI-Net		85.59 67	85.73 62	85.17 120	91.41 127	62.44 239	92.87 126	91.31 182	79.65 72	86.99 48	95.14 71	62.90 119	96.12 144	87.13 68	84.13 161	96.96 13

EI-MVSNet-UG-set		83.14 117	82.96 109	83.67 176	92.28 93	63.19 222	91.38 194	94.68 38	79.22 81	76.60 161	93.75 111	62.64 120	97.76 48	78.07 151	78.01 213	90.05 229

DeepC-MVS	77.85 3	85.52 69	85.24 70	86.37 78	88.80 185	66.64 129	92.15 155	93.68 76	81.07 50	76.91 159	93.64 115	62.59 121	98.44 31	85.50 80	92.84 59	94.03 136
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EIA-MVS		84.84 80	84.88 76	84.69 138	91.30 129	62.36 242	93.85 80	92.04 145	79.45 75	79.33 130	94.28 100	62.42 122	96.35 135	80.05 132	91.25 83	95.38 63

fmvsm_s_conf0.5_n_a		85.75 62	86.09 54	84.72 136	85.73 261	63.58 210	93.79 86	89.32 260	81.42 45	90.21 25	96.91 15	62.41 123	97.67 53	94.48 11	80.56 193	92.90 173

CS-MVS		85.80 61	86.65 46	83.27 188	92.00 106	58.92 310	95.31 31	91.86 157	79.97 65	84.82 69	95.40 56	62.26 124	95.51 178	86.11 77	92.08 68	95.37 64

MVS_111021_HR		86.19 53	85.80 60	87.37 44	93.17 69	69.79 47	93.99 72	93.76 70	79.08 86	78.88 137	93.99 108	62.25 125	98.15 36	85.93 79	91.15 84	94.15 129

PHI-MVS		86.83 41	86.85 43	86.78 63	93.47 62	65.55 156	95.39 30	95.10 23	71.77 219	85.69 60	96.52 26	62.07 126	98.77 23	86.06 78	95.60 12	96.03 43

MP-MVS		85.02 76	84.97 75	85.17 120	92.60 88	64.27 190	93.24 110	92.27 133	73.13 178	79.63 125	94.43 89	61.90 127	97.17 88	85.00 86	92.56 61	94.06 135
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
jason		86.40 48	86.17 52	87.11 51	86.16 252	70.54 32	95.71 24	92.19 140	82.00 35	84.58 71	94.34 96	61.86 128	95.53 177	87.76 58	90.89 86	95.27 74
jason: jason.
fmvsm_s_conf0.1_n		85.61 66	85.93 57	84.68 139	82.95 305	63.48 215	94.03 71	89.46 254	81.69 38	89.86 28	96.74 22	61.85 129	97.75 49	94.74 10	82.01 180	92.81 175

SPE-MVS-test		86.14 54	87.01 38	83.52 179	92.63 87	59.36 306	95.49 27	91.92 152	80.09 64	85.46 63	95.53 53	61.82 130	95.77 160	86.77 73	93.37 52	95.41 61

PAPR		85.15 74	84.47 81	87.18 49	96.02 25	68.29 81	91.85 174	93.00 108	76.59 128	79.03 133	95.00 72	61.59 131	97.61 60	78.16 150	89.00 107	95.63 54

IS-MVSNet		80.14 170	79.41 169	82.33 210	87.91 209	60.08 294	91.97 168	88.27 304	72.90 186	71.44 223	91.73 159	61.44 132	93.66 251	62.47 285	86.53 137	93.24 159

cl____		76.07 239	74.67 235	80.28 261	85.15 270	61.76 255	90.12 243	88.73 289	71.16 237	65.43 291	81.57 300	61.15 133	92.95 264	66.54 248	62.17 333	86.13 291

DIV-MVS_self_test		76.07 239	74.67 235	80.28 261	85.14 271	61.75 256	90.12 243	88.73 289	71.16 237	65.42 292	81.60 299	61.15 133	92.94 268	66.54 248	62.16 335	86.14 289

EI-MVSNet		78.97 191	78.22 186	81.25 238	85.33 265	62.73 235	89.53 258	93.21 95	72.39 198	72.14 211	90.13 190	60.99 135	94.72 202	67.73 236	72.49 256	86.29 285

IterMVS-LS		76.49 235	75.18 232	80.43 258	84.49 282	62.74 234	90.64 227	88.80 287	72.40 197	65.16 294	81.72 296	60.98 136	92.27 295	67.74 235	64.65 314	86.29 285
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.1_n_a		84.76 81	84.84 78	84.53 145	80.23 332	63.50 214	92.79 128	88.73 289	80.46 56	89.84 29	96.65 25	60.96 137	97.57 63	93.80 16	80.14 195	92.53 182

ETV-MVS		86.01 56	86.11 53	85.70 101	90.21 150	67.02 120	93.43 106	91.92 152	81.21 49	84.13 77	94.07 107	60.93 138	95.63 168	89.28 47	89.81 98	94.46 117

tpm cat1		75.30 255	72.21 273	84.58 144	88.52 188	67.77 97	78.16 368	88.02 310	61.88 334	68.45 261	76.37 357	60.65 139	94.03 238	53.77 323	74.11 243	91.93 200

TAMVS		80.37 165	79.45 168	83.13 192	85.14 271	63.37 216	91.23 203	90.76 204	74.81 149	72.65 201	88.49 206	60.63 140	92.95 264	69.41 218	81.95 181	93.08 166

ZNCC-MVS		85.33 71	85.08 73	86.06 86	93.09 72	65.65 152	93.89 78	93.41 90	73.75 167	79.94 121	94.68 83	60.61 141	98.03 38	82.63 111	93.72 46	94.52 113

thres100view900		78.37 205	77.01 207	82.46 205	91.89 111	63.21 221	91.19 207	96.33 1	72.28 201	70.45 232	87.89 221	60.31 142	95.32 182	45.16 358	77.58 218	88.83 243

thres600view7		78.00 210	76.66 212	82.03 225	91.93 108	63.69 206	91.30 200	96.33 1	72.43 196	70.46 231	87.89 221	60.31 142	94.92 197	42.64 370	76.64 228	87.48 263

CHOSEN 1792x2688		84.98 78	83.45 96	89.57 11	89.94 155	75.14 6	92.07 161	92.32 131	81.87 36	75.68 168	88.27 211	60.18 144	98.60 27	80.46 129	90.27 95	94.96 88

h-mvs33		83.01 119	82.56 119	84.35 153	89.34 167	62.02 249	92.72 131	93.76 70	81.45 42	82.73 91	92.25 147	60.11 145	97.13 93	87.69 59	62.96 325	93.91 141

hse-mvs2		81.12 152	81.11 139	81.16 241	86.52 244	57.48 325	89.40 261	91.16 189	81.45 42	82.73 91	90.49 179	60.11 145	94.58 207	87.69 59	60.41 352	91.41 208

tfpn200view9		78.79 197	77.43 198	82.88 195	92.21 96	64.49 176	92.05 162	96.28 4	73.48 173	71.75 217	88.26 212	60.07 147	95.32 182	45.16 358	77.58 218	88.83 243

thres400		78.68 199	77.43 198	82.43 206	92.21 96	64.49 176	92.05 162	96.28 4	73.48 173	71.75 217	88.26 212	60.07 147	95.32 182	45.16 358	77.58 218	87.48 263

diffmvs		84.28 90	83.83 87	85.61 103	87.40 224	68.02 91	90.88 216	89.24 263	80.54 54	81.64 98	92.52 136	59.83 149	94.52 215	87.32 65	85.11 147	94.29 120
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS		84.66 83	82.86 114	90.06 2	90.93 136	74.56 7	87.91 286	95.54 14	68.55 274	72.35 210	94.71 82	59.78 150	98.90 20	81.29 123	94.69 32	96.74 16

thres200		79.66 178	78.33 183	83.66 177	92.54 90	65.82 150	93.06 116	96.31 3	74.90 148	73.30 193	88.66 204	59.67 151	95.61 170	47.84 347	78.67 209	89.56 238

Effi-MVS+		83.82 102	82.76 115	86.99 56	89.56 163	69.40 53	91.35 197	86.12 334	72.59 190	83.22 85	92.81 134	59.60 152	96.01 154	81.76 116	87.80 120	95.56 57

eth_miper_zixun_eth		75.96 246	74.40 243	80.66 253	84.66 278	63.02 225	89.28 263	88.27 304	71.88 213	65.73 289	81.65 297	59.45 153	92.81 272	68.13 230	60.53 349	86.14 289

ACMMP_NAP		86.05 55	85.80 60	86.80 62	91.58 119	67.53 105	91.79 176	93.49 85	74.93 147	84.61 70	95.30 60	59.42 154	97.92 41	86.13 76	94.92 20	94.94 90

GST-MVS		84.63 84	84.29 84	85.66 102	92.82 81	65.27 161	93.04 118	93.13 101	73.20 176	78.89 134	94.18 103	59.41 155	97.85 45	81.45 119	92.48 63	93.86 144

UA-Net		80.02 173	79.65 163	81.11 243	89.33 169	57.72 321	86.33 307	89.00 281	77.44 115	81.01 107	89.15 201	59.33 156	95.90 155	61.01 292	84.28 158	89.73 235

NR-MVSNet		76.05 242	74.59 238	80.44 257	82.96 303	62.18 247	90.83 218	91.73 163	77.12 118	60.96 327	86.35 244	59.28 157	91.80 304	60.74 293	61.34 344	87.35 267

MP-MVS-pluss		85.24 72	85.13 72	85.56 104	91.42 124	65.59 154	91.54 186	92.51 127	74.56 150	80.62 112	95.64 48	59.15 158	97.00 100	86.94 71	93.80 43	94.07 134
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
reproduce-ours		83.51 109	83.33 103	84.06 160	92.18 98	60.49 285	90.74 222	92.04 145	64.35 305	83.24 82	95.59 51	59.05 159	97.27 83	83.61 101	89.17 105	94.41 118

our_new_method		83.51 109	83.33 103	84.06 160	92.18 98	60.49 285	90.74 222	92.04 145	64.35 305	83.24 82	95.59 51	59.05 159	97.27 83	83.61 101	89.17 105	94.41 118

HFP-MVS		84.73 82	84.40 83	85.72 100	93.75 52	65.01 169	93.50 101	93.19 98	72.19 203	79.22 131	94.93 75	59.04 161	97.67 53	81.55 117	92.21 64	94.49 116

mamv4		65.18 338	67.43 308	58.44 384	77.88 364	49.36 375	69.40 392	70.99 397	48.31 390	57.78 349	85.53 254	59.01 162	51.88 422	73.67 179	64.32 316	74.07 392

MSLP-MVS++		86.27 51	85.91 58	87.35 45	92.01 105	68.97 66	95.04 40	92.70 116	79.04 89	81.50 99	96.50 28	58.98 163	96.78 118	83.49 104	93.93 41	96.29 35

Patchmatch-test		65.86 333	60.94 348	80.62 256	83.75 293	58.83 311	58.91 411	75.26 385	44.50 399	50.95 376	77.09 351	58.81 164	87.90 348	35.13 390	64.03 320	95.12 81

reproduce_model		83.15 116	82.96 109	83.73 171	92.02 102	59.74 298	90.37 235	92.08 143	63.70 312	82.86 87	95.48 54	58.62 165	97.17 88	83.06 107	88.42 113	94.26 121

EPNet_dtu		78.80 196	79.26 173	77.43 308	88.06 205	49.71 370	91.96 169	91.95 151	77.67 109	76.56 162	91.28 168	58.51 166	90.20 330	56.37 312	80.95 189	92.39 184
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		60.86 356	60.24 349	62.71 381	81.57 316	46.43 389	75.70 378	85.88 336	57.98 355	48.95 383	69.53 385	58.42 167	76.53 397	28.25 406	35.87 404	65.15 405

test_fmvsmvis_n_1920		83.80 103	83.48 94	84.77 133	82.51 308	63.72 203	91.37 195	83.99 357	81.42 45	77.68 148	95.74 46	58.37 168	97.58 61	93.38 18	86.87 129	93.00 170

EC-MVSNet		84.53 85	85.04 74	83.01 193	89.34 167	61.37 264	94.42 52	91.09 194	77.91 104	83.24 82	94.20 102	58.37 168	95.40 179	85.35 81	91.41 79	92.27 192

VNet		86.20 52	85.65 63	87.84 30	93.92 47	69.99 38	95.73 23	95.94 7	78.43 97	86.00 56	93.07 125	58.22 170	97.00 100	85.22 82	84.33 156	96.52 23

TESTMET0.1,1		82.41 129	81.98 127	83.72 173	88.08 204	63.74 201	92.70 133	93.77 69	79.30 79	77.61 150	87.57 227	58.19 171	94.08 231	73.91 178	86.68 136	93.33 158

原ACMM1				84.42 149	93.21 67	64.27 190		93.40 91	65.39 298	79.51 126	92.50 137	58.11 172	96.69 120	65.27 265	93.96 40	92.32 187

sam_mvs1												57.85 173				94.68 102

CR-MVSNet		73.79 271	70.82 286	82.70 200	83.15 301	67.96 92	70.25 388	84.00 355	73.67 171	69.97 240	72.41 373	57.82 174	89.48 337	52.99 326	73.13 250	90.64 222

Patchmtry		67.53 325	63.93 333	78.34 296	82.12 312	64.38 184	68.72 393	84.00 355	48.23 391	59.24 336	72.41 373	57.82 174	89.27 338	46.10 355	56.68 365	81.36 354

patchmatchnet-post											67.62 390	57.62 176	90.25 325

PCF-MVS	73.15 9	79.29 185	77.63 195	84.29 155	86.06 253	65.96 146	87.03 299	91.10 193	69.86 258	69.79 243	90.64 174	57.54 177	96.59 122	64.37 270	82.29 173	90.32 225
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Fast-Effi-MVS+		81.14 150	80.01 157	84.51 147	90.24 149	65.86 148	94.12 65	89.15 269	73.81 166	75.37 174	88.26 212	57.26 178	94.53 214	66.97 245	84.92 148	93.15 163

miper_lstm_enhance		73.05 276	71.73 279	77.03 313	83.80 292	58.32 316	81.76 338	88.88 283	69.80 259	61.01 326	78.23 340	57.19 179	87.51 356	65.34 264	59.53 354	85.27 313

PatchT		69.11 309	65.37 323	80.32 259	82.07 313	63.68 207	67.96 398	87.62 316	50.86 382	69.37 244	65.18 393	57.09 180	88.53 343	41.59 373	66.60 296	88.74 246

testdata				81.34 237	89.02 179	57.72 321		89.84 241	58.65 353	85.32 65	94.09 105	57.03 181	93.28 257	69.34 219	90.56 91	93.03 168

PatchmatchNet		77.46 219	74.63 237	85.96 89	89.55 164	70.35 34	79.97 359	89.55 252	72.23 202	70.94 225	76.91 353	57.03 181	92.79 274	54.27 320	81.17 187	94.74 99
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test_yl		84.28 90	83.16 106	87.64 34	94.52 37	69.24 59	95.78 18	95.09 24	69.19 266	81.09 105	92.88 131	57.00 183	97.44 69	81.11 125	81.76 182	96.23 38

DCV-MVSNet		84.28 90	83.16 106	87.64 34	94.52 37	69.24 59	95.78 18	95.09 24	69.19 266	81.09 105	92.88 131	57.00 183	97.44 69	81.11 125	81.76 182	96.23 38

region2R		84.36 88	84.03 86	85.36 111	93.54 59	64.31 188	93.43 106	92.95 109	72.16 206	78.86 138	94.84 79	56.97 185	97.53 65	81.38 121	92.11 67	94.24 123

新几何1				84.73 135	92.32 92	64.28 189		91.46 178	59.56 349	79.77 123	92.90 129	56.95 186	96.57 124	63.40 275	92.91 58	93.34 156

WR-MVS		76.76 233	75.74 225	79.82 277	84.60 279	62.27 246	92.60 140	92.51 127	76.06 132	67.87 269	85.34 255	56.76 187	90.24 328	62.20 286	63.69 324	86.94 275

HPM-MVS		83.25 114	82.95 111	84.17 158	92.25 94	62.88 232	90.91 213	91.86 157	70.30 252	77.12 156	93.96 109	56.75 188	96.28 137	82.04 114	91.34 82	93.34 156
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		82.71 125	82.38 122	83.73 171	89.25 172	59.58 301	92.24 152	94.89 29	77.96 102	79.86 122	92.38 142	56.70 189	97.05 95	77.26 155	80.86 190	94.55 109

ACMMPR		84.37 87	84.06 85	85.28 115	93.56 58	64.37 185	93.50 101	93.15 100	72.19 203	78.85 139	94.86 78	56.69 190	97.45 68	81.55 117	92.20 65	94.02 137

FMVSNet3		77.73 216	76.04 220	82.80 196	91.20 132	68.99 65	91.87 172	91.99 149	73.35 175	67.04 280	83.19 279	56.62 191	92.14 296	59.80 300	69.34 273	87.28 269

Patchmatch-RL test		68.17 319	64.49 330	79.19 288	71.22 387	53.93 349	70.07 390	71.54 396	69.22 265	56.79 353	62.89 398	56.58 192	88.61 340	69.53 217	52.61 375	95.03 86

dongtai		55.18 367	55.46 366	54.34 392	76.03 374	36.88 410	76.07 375	84.61 349	51.28 379	43.41 400	64.61 396	56.56 193	67.81 410	18.09 415	28.50 415	58.32 408

test_post											23.01 421	56.49 194	92.67 279

RPMNet		70.42 298	65.68 319	84.63 142	83.15 301	67.96 92	70.25 388	90.45 212	46.83 394	69.97 240	65.10 394	56.48 195	95.30 185	35.79 389	73.13 250	90.64 222

DU-MVS		76.86 229	75.84 223	79.91 274	82.96 303	60.26 290	91.26 201	91.54 173	76.46 130	68.88 253	86.35 244	56.16 196	92.13 297	66.38 251	62.55 329	87.35 267

Baseline_NR-MVSNet		73.99 268	72.83 263	77.48 307	80.78 323	59.29 307	91.79 176	84.55 350	68.85 270	68.99 251	80.70 314	56.16 196	92.04 300	62.67 283	60.98 346	81.11 357

API-MVS		82.28 131	80.53 151	87.54 41	96.13 22	70.59 31	93.63 94	91.04 200	65.72 297	75.45 173	92.83 133	56.11 198	98.89 21	64.10 271	89.75 101	93.15 163

MTAPA		83.91 100	83.38 101	85.50 105	91.89 111	65.16 165	81.75 339	92.23 134	75.32 142	80.53 114	95.21 68	56.06 199	97.16 91	84.86 89	92.55 62	94.18 126

JIA-IIPM		66.06 332	62.45 342	76.88 317	81.42 319	54.45 348	57.49 412	88.67 292	49.36 386	63.86 307	46.86 410	56.06 199	90.25 325	49.53 336	68.83 279	85.95 296

v148		76.19 237	74.47 242	81.36 236	80.05 334	64.44 180	91.75 181	90.23 227	73.68 170	67.13 279	80.84 313	55.92 201	93.86 248	68.95 225	61.73 340	85.76 303

WR-MVS_H		70.59 296	69.94 293	72.53 348	81.03 320	51.43 360	87.35 296	92.03 148	67.38 283	60.23 332	80.70 314	55.84 202	83.45 379	46.33 354	58.58 359	82.72 341

test_fmvsmconf0.01_n		83.70 107	83.52 91	84.25 157	75.26 375	61.72 257	92.17 154	87.24 322	82.36 31	84.91 68	95.41 55	55.60 203	96.83 117	92.85 22	85.87 142	94.21 124

AUN-MVS		78.37 205	77.43 198	81.17 240	86.60 243	57.45 326	89.46 260	91.16 189	74.11 157	74.40 182	90.49 179	55.52 204	94.57 209	74.73 175	60.43 351	91.48 206

XVS		83.87 101	83.47 95	85.05 122	93.22 65	63.78 199	92.92 123	92.66 120	73.99 159	78.18 143	94.31 98	55.25 205	97.41 71	79.16 140	91.58 76	93.95 139

X-MVStestdata		76.86 229	74.13 248	85.05 122	93.22 65	63.78 199	92.92 123	92.66 120	73.99 159	78.18 143	10.19 426	55.25 205	97.41 71	79.16 140	91.58 76	93.95 139

BH-w/o		80.49 163	79.30 172	84.05 163	90.83 140	64.36 187	93.60 95	89.42 257	74.35 153	69.09 247	90.15 189	55.23 207	95.61 170	64.61 268	86.43 139	92.17 195

CP-MVS		83.71 106	83.40 100	84.65 140	93.14 70	63.84 197	94.59 50	92.28 132	71.03 241	77.41 152	94.92 76	55.21 208	96.19 141	81.32 122	90.70 88	93.91 141

PGM-MVS		83.25 114	82.70 117	84.92 125	92.81 83	64.07 194	90.44 231	92.20 138	71.28 235	77.23 155	94.43 89	55.17 209	97.31 78	79.33 139	91.38 80	93.37 155

tpmvs		72.88 280	69.76 296	82.22 215	90.98 135	67.05 118	78.22 367	88.30 302	63.10 321	64.35 304	74.98 364	55.09 210	94.27 223	43.25 364	69.57 272	85.34 311

v8		75.35 254	73.26 259	81.61 231	80.67 325	66.82 124	89.54 257	89.27 262	71.65 223	63.30 313	80.30 322	54.99 211	94.06 233	67.33 240	62.33 332	83.94 322

sam_mvs												54.91 212

EPMVS		78.49 204	75.98 221	86.02 87	91.21 131	69.68 51	80.23 354	91.20 187	75.25 143	72.48 206	78.11 341	54.65 213	93.69 250	57.66 309	83.04 167	94.69 101

ab-mvs		80.18 169	78.31 184	85.80 96	88.44 192	65.49 159	83.00 333	92.67 119	71.82 217	77.36 153	85.01 258	54.50 214	96.59 122	76.35 160	75.63 234	95.32 69

KD-MVS_2432*1600		69.03 310	66.37 314	77.01 314	85.56 263	61.06 268	81.44 343	90.25 225	67.27 284	58.00 346	76.53 355	54.49 215	87.63 354	48.04 344	35.77 405	82.34 347

miper_refine_blended		69.03 310	66.37 314	77.01 314	85.56 263	61.06 268	81.44 343	90.25 225	67.27 284	58.00 346	76.53 355	54.49 215	87.63 354	48.04 344	35.77 405	82.34 347

DP-MVS Recon		82.73 123	81.65 130	85.98 88	97.31 4	67.06 117	95.15 36	91.99 149	69.08 269	76.50 163	93.89 110	54.48 217	98.20 35	70.76 207	85.66 144	92.69 176

GeoE		78.90 193	77.43 198	83.29 187	88.95 181	62.02 249	92.31 149	86.23 332	70.24 253	71.34 224	89.27 199	54.43 218	94.04 236	63.31 277	80.81 192	93.81 146

XXY-MVS		77.94 213	76.44 214	82.43 206	82.60 307	64.44 180	92.01 164	91.83 160	73.59 172	70.00 239	85.82 251	54.43 218	94.76 199	69.63 215	68.02 287	88.10 257

MDTV_nov1_ep13_2view						59.90 296	80.13 356		67.65 281	72.79 198		54.33 220		59.83 299		92.58 180

fmvsm_s_conf0.5_n_2		85.06 75	85.60 64	83.44 185	86.92 240	60.53 284	94.41 53	87.31 320	83.30 22	88.72 35	96.72 23	54.28 221	97.75 49	94.07 13	84.68 153	92.04 198

Test By Simon												54.21 222

MAR-MVS		84.18 95	83.43 97	86.44 75	96.25 21	65.93 147	94.28 58	94.27 57	74.41 151	79.16 132	95.61 49	53.99 223	98.88 22	69.62 216	93.26 54	94.50 115
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
test-LLR		80.10 171	79.56 165	81.72 229	86.93 238	61.17 265	92.70 133	91.54 173	71.51 232	75.62 169	86.94 238	53.83 224	92.38 289	72.21 194	84.76 151	91.60 203

test0.0.03 1		72.76 281	72.71 267	72.88 346	80.25 331	47.99 379	91.22 204	89.45 255	71.51 232	62.51 322	87.66 224	53.83 224	85.06 369	50.16 333	67.84 290	85.58 304

v2v482		77.42 220	75.65 226	82.73 198	80.38 328	67.13 116	91.85 174	90.23 227	75.09 145	69.37 244	83.39 277	53.79 226	94.44 217	71.77 198	65.00 309	86.63 281

SR-MVS		82.81 122	82.58 118	83.50 182	93.35 63	61.16 267	92.23 153	91.28 186	64.48 304	81.27 102	95.28 61	53.71 227	95.86 156	82.87 109	88.77 110	93.49 153

pcd_1.5k_mvsjas		4.46 398	5.95 401	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	53.55 228	0.00 431	0.00 430	0.00 428	0.00 427

PS-MVSNAJss		77.26 222	76.31 216	80.13 266	80.64 326	59.16 308	90.63 229	91.06 198	72.80 187	68.58 259	84.57 264	53.55 228	93.96 241	72.97 182	71.96 260	87.27 270

PS-MVSNAJ		88.14 18	87.61 31	89.71 7	92.06 101	76.72 1	95.75 20	93.26 94	83.86 17	89.55 31	96.06 40	53.55 228	97.89 43	91.10 36	93.31 53	94.54 111

mPP-MVS		82.96 121	82.44 121	84.52 146	92.83 79	62.92 230	92.76 129	91.85 159	71.52 231	75.61 171	94.24 101	53.48 231	96.99 103	78.97 143	90.73 87	93.64 150

xiu_mvs_v2_base		87.92 23	87.38 35	89.55 12	91.41 127	76.43 3	95.74 21	93.12 102	83.53 20	89.55 31	95.95 42	53.45 232	97.68 51	91.07 37	92.62 60	94.54 111

test_post1							78.95 361				20.70 424	53.05 233	91.50 316	60.43 295

MDTV_nov1_ep13			72.61 268		89.06 178	68.48 76	80.33 352	90.11 231	71.84 216	71.81 216	75.92 361	53.01 234	93.92 243	48.04 344	73.38 248

FA-MVS(test-final)		79.12 188	77.23 204	84.81 132	90.54 143	63.98 196	81.35 345	91.71 165	71.09 240	74.85 179	82.94 280	52.85 235	97.05 95	67.97 232	81.73 184	93.41 154

test222					89.77 158	61.60 259	89.55 256	89.42 257	56.83 364	77.28 154	92.43 141	52.76 236			91.14 85	93.09 165

fmvsm_s_conf0.1_n_2		84.40 86	84.78 79	83.27 188	85.25 268	60.41 287	94.13 64	85.69 340	83.05 24	87.99 38	96.37 30	52.75 237	97.68 51	93.75 17	84.05 162	91.71 202

v1144		76.73 234	74.88 234	82.27 212	80.23 332	66.60 131	91.68 183	90.21 229	73.69 169	69.06 249	81.89 293	52.73 238	94.40 218	69.21 221	65.23 306	85.80 300

v10		74.77 261	72.54 270	81.46 234	80.33 330	66.71 128	89.15 267	89.08 275	70.94 242	63.08 316	79.86 327	52.52 239	94.04 236	65.70 259	62.17 333	83.64 325

CLD-MVS		82.73 123	82.35 123	83.86 167	87.90 210	67.65 101	95.45 28	92.18 141	85.06 10	72.58 203	92.27 145	52.46 240	95.78 158	84.18 95	79.06 205	88.16 256
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
TranMVSNet+NR-MVSNet		75.86 247	74.52 241	79.89 275	82.44 309	60.64 282	91.37 195	91.37 180	76.63 127	67.65 271	86.21 247	52.37 241	91.55 311	61.84 288	60.81 347	87.48 263

VPA-MVSNet		79.03 189	78.00 189	82.11 223	85.95 255	64.48 178	93.22 112	94.66 39	75.05 146	74.04 188	84.95 259	52.17 242	93.52 253	74.90 173	67.04 293	88.32 255

APD-MVS_3200maxsize		81.64 143	81.32 133	82.59 204	92.36 91	58.74 312	91.39 192	91.01 201	63.35 316	79.72 124	94.62 85	51.82 243	96.14 143	79.71 134	87.93 118	92.89 174

dp		75.01 259	72.09 274	83.76 168	89.28 171	66.22 141	79.96 360	89.75 244	71.16 237	67.80 270	77.19 350	51.81 244	92.54 284	50.39 331	71.44 265	92.51 183

mvsmamba		81.55 144	80.72 145	84.03 164	91.42 124	66.93 122	83.08 330	89.13 271	78.55 96	67.50 273	87.02 237	51.79 245	90.07 333	87.48 62	90.49 92	95.10 82

v144192		76.05 242	74.03 249	82.12 220	79.50 340	66.55 133	91.39 192	89.71 250	72.30 200	68.17 262	81.33 305	51.75 246	94.03 238	67.94 233	64.19 317	85.77 301

BH-untuned		78.68 199	77.08 205	83.48 183	89.84 156	63.74 201	92.70 133	88.59 295	71.57 229	66.83 284	88.65 205	51.75 246	95.39 180	59.03 303	84.77 150	91.32 212

HQP2-MVS												51.63 248

HQP-MVS		81.14 150	80.64 148	82.64 202	87.54 220	63.66 208	94.06 66	91.70 168	79.80 68	74.18 183	90.30 183	51.63 248	95.61 170	77.63 153	78.90 206	88.63 247

dmvs_testset		65.55 336	66.45 312	62.86 380	79.87 335	22.35 426	76.55 372	71.74 394	77.42 117	55.85 355	87.77 223	51.39 250	80.69 393	31.51 405	65.92 300	85.55 306

V42		76.46 236	74.55 240	82.19 217	79.14 346	67.82 96	90.26 240	89.42 257	73.75 167	68.63 258	81.89 293	51.31 251	94.09 230	71.69 200	64.84 310	84.66 317

RRT-MVS		82.61 127	81.16 134	86.96 57	91.10 133	68.75 70	87.70 291	92.20 138	76.97 119	72.68 199	87.10 236	51.30 252	96.41 133	83.56 103	87.84 119	95.74 51

SR-MVS-dyc-post		81.06 153	80.70 146	82.15 218	92.02 102	58.56 314	90.90 214	90.45 212	62.76 323	78.89 134	94.46 87	51.26 253	95.61 170	78.77 146	86.77 133	92.28 189

CL-MVSNet_self_test		69.92 302	68.09 306	75.41 325	73.25 382	55.90 339	90.05 246	89.90 239	69.96 256	61.96 325	76.54 354	51.05 254	87.64 353	49.51 337	50.59 380	82.70 343

TransMVSNet (Re)		70.07 301	67.66 307	77.31 311	80.62 327	59.13 309	91.78 178	84.94 346	65.97 294	60.08 333	80.44 319	50.78 255	91.87 302	48.84 340	45.46 388	80.94 359

HQP_MVS		80.34 166	79.75 162	82.12 220	86.94 236	62.42 240	93.13 114	91.31 182	78.81 92	72.53 204	89.14 202	50.66 256	95.55 175	76.74 156	78.53 211	88.39 253

plane_prior6					87.23 228	62.32 244						50.66 256

ACMMP		81.49 145	80.67 147	83.93 166	91.71 116	62.90 231	92.13 156	92.22 137	71.79 218	71.68 219	93.49 119	50.32 258	96.96 108	78.47 148	84.22 160	91.93 200
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
MVS_111021_LR		82.02 137	81.52 131	83.51 181	88.42 193	62.88 232	89.77 253	88.93 282	76.78 124	75.55 172	93.10 122	50.31 259	95.38 181	83.82 100	87.02 128	92.26 193

1314		80.70 159	78.95 177	85.94 90	87.77 217	67.56 103	87.91 286	92.55 126	72.17 205	67.44 274	93.09 123	50.27 260	97.04 98	71.68 201	87.64 122	93.23 160

CP-MVSNet		70.50 297	69.91 294	72.26 351	80.71 324	51.00 364	87.23 298	90.30 222	67.84 278	59.64 334	82.69 283	50.23 261	82.30 387	51.28 328	59.28 355	83.46 330

LCM-MVSNet-Re		72.93 278	71.84 277	76.18 322	88.49 189	48.02 378	80.07 357	70.17 398	73.96 162	52.25 368	80.09 326	49.98 262	88.24 346	67.35 238	84.23 159	92.28 189

Vis-MVSNet		80.92 156	79.98 159	83.74 169	88.48 190	61.80 253	93.44 105	88.26 306	73.96 162	77.73 147	91.76 157	49.94 263	94.76 199	65.84 257	90.37 94	94.65 105
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
v1192		75.98 244	73.92 251	82.15 218	79.73 336	66.24 140	91.22 204	89.75 244	72.67 189	68.49 260	81.42 303	49.86 264	94.27 223	67.08 243	65.02 308	85.95 296

test-mter		79.96 174	79.38 171	81.72 229	86.93 238	61.17 265	92.70 133	91.54 173	73.85 164	75.62 169	86.94 238	49.84 265	92.38 289	72.21 194	84.76 151	91.60 203

MonoMVSNet		76.99 227	75.08 233	82.73 198	83.32 299	63.24 219	86.47 306	86.37 328	79.08 86	66.31 287	79.30 334	49.80 266	91.72 306	79.37 137	65.70 301	93.23 160

cdsmvs_eth3d_5k		19.86 393	26.47 392	0.00 412	0.00 435	0.00 437	0.00 423	93.45 86	0.00 430	0.00 431	95.27 63	49.56 267	0.00 431	0.00 430	0.00 428	0.00 427

3Dnovator+	73.60 7	82.10 136	80.60 150	86.60 68	90.89 138	66.80 126	95.20 34	93.44 87	74.05 158	67.42 275	92.49 139	49.46 268	97.65 57	70.80 206	91.68 74	95.33 67

MVP-Stereo		77.12 225	76.23 217	79.79 278	81.72 315	66.34 137	89.29 262	90.88 202	70.56 250	62.01 324	82.88 281	49.34 269	94.13 228	65.55 262	93.80 43	78.88 377
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
RE-MVS-def			80.48 152		92.02 102	58.56 314	90.90 214	90.45 212	62.76 323	78.89 134	94.46 87	49.30 270		78.77 146	86.77 133	92.28 189

OMC-MVS		78.67 201	77.91 192	80.95 250	85.76 260	57.40 327	88.49 277	88.67 292	73.85 164	72.43 208	92.10 150	49.29 271	94.55 213	72.73 188	77.89 214	90.91 219

VPNet		78.82 195	77.53 197	82.70 200	84.52 281	66.44 134	93.93 75	92.23 134	80.46 56	72.60 202	88.38 209	49.18 272	93.13 259	72.47 192	63.97 322	88.55 250

CVMVSNet		74.04 267	74.27 245	73.33 342	85.33 265	43.94 396	89.53 258	88.39 299	54.33 372	70.37 233	90.13 190	49.17 273	84.05 373	61.83 289	79.36 202	91.99 199

v1921920		75.63 252	73.49 257	82.06 224	79.38 341	66.35 136	91.07 212	89.48 253	71.98 208	67.99 263	81.22 308	49.16 274	93.90 244	66.56 247	64.56 315	85.92 298

pm-mvs1		72.89 279	71.09 283	78.26 299	79.10 347	57.62 323	90.80 219	89.30 261	67.66 280	62.91 318	81.78 295	49.11 275	92.95 264	60.29 297	58.89 357	84.22 320

pmmvs4		73.92 269	71.81 278	80.25 263	79.17 344	65.24 162	87.43 295	87.26 321	67.64 282	63.46 311	83.91 272	48.96 276	91.53 315	62.94 280	65.49 302	83.96 321

TAPA-MVS	70.22 12	74.94 260	73.53 256	79.17 289	90.40 146	52.07 356	89.19 266	89.61 251	62.69 325	70.07 237	92.67 135	48.89 277	94.32 219	38.26 384	79.97 196	91.12 217
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
3Dnovator	73.91 6	82.69 126	80.82 143	88.31 26	89.57 162	71.26 22	92.60 140	94.39 52	78.84 91	67.89 268	92.48 140	48.42 278	98.52 28	68.80 227	94.40 36	95.15 79

CPTT-MVS		79.59 179	79.16 174	80.89 252	91.54 122	59.80 297	92.10 158	88.54 297	60.42 342	72.96 195	93.28 121	48.27 279	92.80 273	78.89 145	86.50 138	90.06 228

GBi-Net		75.65 250	73.83 252	81.10 244	88.85 182	65.11 166	90.01 247	90.32 218	70.84 244	67.04 280	80.25 323	48.03 280	91.54 312	59.80 300	69.34 273	86.64 278

test1		75.65 250	73.83 252	81.10 244	88.85 182	65.11 166	90.01 247	90.32 218	70.84 244	67.04 280	80.25 323	48.03 280	91.54 312	59.80 300	69.34 273	86.64 278

FMVSNet2		76.07 239	74.01 250	82.26 214	88.85 182	67.66 100	91.33 198	91.61 171	70.84 244	65.98 288	82.25 289	48.03 280	92.00 301	58.46 305	68.73 281	87.10 272

LFMVS		84.34 89	82.73 116	89.18 13	94.76 33	73.25 11	94.99 43	91.89 155	71.90 211	82.16 95	93.49 119	47.98 283	97.05 95	82.55 112	84.82 149	97.25 8

SDMVSNet		80.26 167	78.88 178	84.40 150	89.25 172	67.63 102	85.35 310	93.02 105	76.77 125	70.84 227	87.12 234	47.95 284	96.09 146	85.04 85	74.55 237	89.48 239

QAPM		79.95 175	77.39 202	87.64 34	89.63 161	71.41 20	93.30 109	93.70 75	65.34 300	67.39 277	91.75 158	47.83 285	98.96 16	57.71 308	89.81 98	92.54 181

HPM-MVS_fast		80.25 168	79.55 167	82.33 210	91.55 121	59.95 295	91.32 199	89.16 268	65.23 301	74.71 180	93.07 125	47.81 286	95.74 161	74.87 174	88.23 114	91.31 213

CANet_DTU		84.09 97	83.52 91	85.81 95	90.30 148	66.82 124	91.87 172	89.01 278	85.27 9	86.09 55	93.74 112	47.71 287	96.98 104	77.90 152	89.78 100	93.65 149

v1240		75.21 257	72.98 262	81.88 226	79.20 343	66.00 144	90.75 221	89.11 273	71.63 227	67.41 276	81.22 308	47.36 288	93.87 246	65.46 263	64.72 313	85.77 301

PEN-MVS		69.46 307	68.56 301	72.17 353	79.27 342	49.71 370	86.90 302	89.24 263	67.24 287	59.08 339	82.51 286	47.23 289	83.54 378	48.42 342	57.12 361	83.25 333

dmvs_re		76.93 228	75.36 229	81.61 231	87.78 216	60.71 279	80.00 358	87.99 311	79.42 76	69.02 250	89.47 197	46.77 290	94.32 219	63.38 276	74.45 240	89.81 232

CNLPA		74.31 264	72.30 272	80.32 259	91.49 123	61.66 258	90.85 217	80.72 370	56.67 365	63.85 308	90.64 174	46.75 291	90.84 320	53.79 322	75.99 233	88.47 252

114514_t		79.17 187	77.67 193	83.68 175	95.32 29	65.53 157	92.85 127	91.60 172	63.49 314	67.92 265	90.63 176	46.65 292	95.72 166	67.01 244	83.54 163	89.79 233

PS-CasMVS		69.86 304	69.13 299	72.07 355	80.35 329	50.57 366	87.02 300	89.75 244	67.27 284	59.19 338	82.28 288	46.58 293	82.24 388	50.69 330	59.02 356	83.39 332

DTE-MVSNet		68.46 316	67.33 310	71.87 357	77.94 362	49.00 376	86.16 308	88.58 296	66.36 292	58.19 343	82.21 290	46.36 294	83.87 376	44.97 361	55.17 368	82.73 340

test1111		80.84 157	80.02 156	83.33 186	87.87 211	60.76 275	92.62 138	86.86 325	77.86 105	75.73 167	91.39 166	46.35 295	94.70 205	72.79 186	88.68 111	94.52 113

ECVR-MVS		81.29 148	80.38 154	84.01 165	88.39 195	61.96 251	92.56 145	86.79 326	77.66 110	76.63 160	91.42 164	46.34 296	95.24 186	74.36 176	89.23 102	94.85 91

PMMVS		81.98 138	82.04 125	81.78 227	89.76 159	56.17 336	91.13 209	90.69 205	77.96 102	80.09 120	93.57 117	46.33 297	94.99 193	81.41 120	87.46 124	94.17 127

OPM-MVS		79.00 190	78.09 187	81.73 228	83.52 297	63.83 198	91.64 185	90.30 222	76.36 131	71.97 214	89.93 193	46.30 298	95.17 188	75.10 168	77.70 216	86.19 288
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
BH-RMVSNet		79.46 184	77.65 194	84.89 126	91.68 117	65.66 151	93.55 97	88.09 309	72.93 183	73.37 192	91.12 170	46.20 299	96.12 144	56.28 313	85.61 145	92.91 172

FE-MVS		75.97 245	73.02 261	84.82 129	89.78 157	65.56 155	77.44 370	91.07 197	64.55 303	72.66 200	79.85 328	46.05 300	96.69 120	54.97 317	80.82 191	92.21 194

TR-MVS		78.77 198	77.37 203	82.95 194	90.49 144	60.88 271	93.67 91	90.07 232	70.08 255	74.51 181	91.37 167	45.69 301	95.70 167	60.12 298	80.32 194	92.29 188

IterMVS-SCA-FT		71.55 292	69.97 292	76.32 320	81.48 317	60.67 281	87.64 293	85.99 335	66.17 293	59.50 335	78.88 335	45.53 302	83.65 377	62.58 284	61.93 336	84.63 319

SCA		75.82 248	72.76 264	85.01 124	86.63 242	70.08 37	81.06 347	89.19 266	71.60 228	70.01 238	77.09 351	45.53 302	90.25 325	60.43 295	73.27 249	94.68 102

IterMVS		72.65 286	70.83 284	78.09 301	82.17 311	62.96 227	87.64 293	86.28 330	71.56 230	60.44 330	78.85 336	45.42 304	86.66 360	63.30 278	61.83 337	84.65 318
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Syy-MVS		69.65 305	69.52 297	70.03 362	87.87 211	43.21 398	88.07 282	89.01 278	72.91 184	63.11 314	88.10 216	45.28 305	85.54 365	22.07 412	69.23 276	81.32 355

WB-MVSnew		77.14 224	76.18 219	80.01 270	86.18 251	63.24 219	91.26 201	94.11 61	71.72 221	73.52 191	87.29 232	45.14 306	93.00 262	56.98 310	79.42 200	83.80 324

Effi-MVS+-dtu		76.14 238	75.28 231	78.72 294	83.22 300	55.17 343	89.87 251	87.78 315	75.42 140	67.98 264	81.43 302	45.08 307	92.52 285	75.08 169	71.63 261	88.48 251

XVG-OURS-SEG-HR		74.70 262	73.08 260	79.57 283	78.25 358	57.33 328	80.49 350	87.32 318	63.22 318	68.76 256	90.12 192	44.89 308	91.59 310	70.55 210	74.09 244	89.79 233

v7n		71.31 293	68.65 300	79.28 287	76.40 370	60.77 274	86.71 304	89.45 255	64.17 308	58.77 342	78.24 339	44.59 309	93.54 252	57.76 307	61.75 339	83.52 328

pmmvs5		73.35 273	71.52 280	78.86 293	78.64 354	60.61 283	91.08 210	86.90 323	67.69 279	63.32 312	83.64 273	44.33 310	90.53 322	62.04 287	66.02 299	85.46 308

OpenMVS	70.45 11	78.54 203	75.92 222	86.41 77	85.93 258	71.68 18	92.74 130	92.51 127	66.49 291	64.56 299	91.96 152	43.88 311	98.10 37	54.61 318	90.65 89	89.44 241

AdaColmap		78.94 192	77.00 208	84.76 134	96.34 17	65.86 148	92.66 137	87.97 313	62.18 328	70.56 229	92.37 143	43.53 312	97.35 75	64.50 269	82.86 168	91.05 218

tfpnnormal		70.10 300	67.36 309	78.32 297	83.45 298	60.97 270	88.85 271	92.77 114	64.85 302	60.83 328	78.53 337	43.52 313	93.48 254	31.73 402	61.70 341	80.52 364

mvsany_test1		68.77 312	68.56 301	69.39 364	73.57 381	45.88 392	80.93 348	60.88 412	59.65 348	71.56 220	90.26 185	43.22 314	75.05 399	74.26 177	62.70 328	87.25 271

test_djsdf		73.76 272	72.56 269	77.39 309	77.00 368	53.93 349	89.07 268	90.69 205	65.80 295	63.92 306	82.03 292	43.14 315	92.67 279	72.83 184	68.53 282	85.57 305

GA-MVS		78.33 207	76.23 217	84.65 140	83.65 295	66.30 138	91.44 187	90.14 230	76.01 133	70.32 234	84.02 270	42.50 316	94.72 202	70.98 204	77.00 226	92.94 171

PLC	68.80 14	75.23 256	73.68 255	79.86 276	92.93 76	58.68 313	90.64 227	88.30 302	60.90 339	64.43 303	90.53 177	42.38 317	94.57 209	56.52 311	76.54 229	86.33 284
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
D2MVS		73.80 270	72.02 275	79.15 291	79.15 345	62.97 226	88.58 276	90.07 232	72.94 182	59.22 337	78.30 338	42.31 318	92.70 278	65.59 261	72.00 259	81.79 352

Fast-Effi-MVS+-dtu		75.04 258	73.37 258	80.07 267	80.86 321	59.52 302	91.20 206	85.38 341	71.90 211	65.20 293	84.84 260	41.46 319	92.97 263	66.50 250	72.96 252	87.73 260

sd_testset		77.08 226	75.37 228	82.20 216	89.25 172	62.11 248	82.06 337	89.09 274	76.77 125	70.84 227	87.12 234	41.43 320	95.01 192	67.23 241	74.55 237	89.48 239

MS-PatchMatch		77.90 215	76.50 213	82.12 220	85.99 254	69.95 41	91.75 181	92.70 116	73.97 161	62.58 321	84.44 266	41.11 321	95.78 158	63.76 274	92.17 66	80.62 363

our_test_3		68.29 318	64.69 327	79.11 292	78.92 348	64.85 173	88.40 279	85.06 344	60.32 344	52.68 366	76.12 359	40.81 322	89.80 336	44.25 363	55.65 366	82.67 345

XVG-OURS		74.25 265	72.46 271	79.63 281	78.45 356	57.59 324	80.33 352	87.39 317	63.86 310	68.76 256	89.62 196	40.50 323	91.72 306	69.00 224	74.25 242	89.58 236

VDD-MVS		83.06 118	81.81 129	86.81 61	90.86 139	67.70 99	95.40 29	91.50 176	75.46 139	81.78 97	92.34 144	40.09 324	97.13 93	86.85 72	82.04 179	95.60 55

DP-MVS		69.90 303	66.48 311	80.14 265	95.36 28	62.93 228	89.56 255	76.11 379	50.27 384	57.69 350	85.23 256	39.68 325	95.73 162	33.35 394	71.05 267	81.78 353

ppachtmachnet_test		67.72 322	63.70 334	79.77 279	78.92 348	66.04 143	88.68 274	82.90 365	60.11 346	55.45 356	75.96 360	39.19 326	90.55 321	39.53 379	52.55 376	82.71 342

ADS-MVSNet2		66.90 328	63.44 336	77.26 312	88.06 205	60.70 280	68.01 396	75.56 383	57.57 356	64.48 300	69.87 383	38.68 327	84.10 372	40.87 375	67.89 288	86.97 273

ADS-MVSNet		68.54 315	64.38 332	81.03 248	88.06 205	66.90 123	68.01 396	84.02 354	57.57 356	64.48 300	69.87 383	38.68 327	89.21 339	40.87 375	67.89 288	86.97 273

test_cas_vis1_n_1920		80.45 164	80.61 149	79.97 273	78.25 358	57.01 332	94.04 70	88.33 301	79.06 88	82.81 90	93.70 113	38.65 329	91.63 309	90.82 40	79.81 197	91.27 215

LPG-MVS_test		75.82 248	74.58 239	79.56 284	84.31 286	59.37 304	90.44 231	89.73 247	69.49 261	64.86 295	88.42 207	38.65 329	94.30 221	72.56 190	72.76 253	85.01 314

LGP-MVS_train				79.56 284	84.31 286	59.37 304		89.73 247	69.49 261	64.86 295	88.42 207	38.65 329	94.30 221	72.56 190	72.76 253	85.01 314

VDDNet		80.50 162	78.26 185	87.21 47	86.19 250	69.79 47	94.48 51	91.31 182	60.42 342	79.34 129	90.91 172	38.48 332	96.56 125	82.16 113	81.05 188	95.27 74

ACMP	71.68 10	75.58 253	74.23 246	79.62 282	84.97 275	59.64 299	90.80 219	89.07 276	70.39 251	62.95 317	87.30 231	38.28 333	93.87 246	72.89 183	71.45 264	85.36 310
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n_1920		81.66 142	82.01 126	80.64 254	82.24 310	55.09 344	94.76 47	86.87 324	81.67 39	84.40 73	94.63 84	38.17 334	94.67 206	91.98 31	83.34 165	92.16 196

UGNet		79.87 176	78.68 179	83.45 184	89.96 154	61.51 260	92.13 156	90.79 203	76.83 123	78.85 139	86.33 246	38.16 335	96.17 142	67.93 234	87.17 127	92.67 177
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
anonymousdsp		71.14 294	69.37 298	76.45 319	72.95 383	54.71 346	84.19 317	88.88 283	61.92 333	62.15 323	79.77 329	38.14 336	91.44 317	68.90 226	67.45 291	83.21 334

xiu_mvs_v1_base_debu		82.16 133	81.12 136	85.26 117	86.42 245	68.72 72	92.59 142	90.44 215	73.12 179	84.20 74	94.36 91	38.04 337	95.73 162	84.12 96	86.81 130	91.33 209

xiu_mvs_v1_base		82.16 133	81.12 136	85.26 117	86.42 245	68.72 72	92.59 142	90.44 215	73.12 179	84.20 74	94.36 91	38.04 337	95.73 162	84.12 96	86.81 130	91.33 209

xiu_mvs_v1_base_debi		82.16 133	81.12 136	85.26 117	86.42 245	68.72 72	92.59 142	90.44 215	73.12 179	84.20 74	94.36 91	38.04 337	95.73 162	84.12 96	86.81 130	91.33 209

PVSNet_0	68.08 15	71.81 289	68.32 305	82.27 212	84.68 277	62.31 245	88.68 274	90.31 221	75.84 134	57.93 348	80.65 317	37.85 340	94.19 226	69.94 213	29.05 414	90.31 226

Anonymous20231206		67.53 325	65.78 317	72.79 347	74.95 376	47.59 381	88.23 280	87.32 318	61.75 336	58.07 345	77.29 348	37.79 341	87.29 358	42.91 366	63.71 323	83.48 329

ACMM	69.62 13	74.34 263	72.73 266	79.17 289	84.25 288	57.87 319	90.36 236	89.93 238	63.17 320	65.64 290	86.04 250	37.79 341	94.10 229	65.89 256	71.52 263	85.55 306
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
cascas		78.18 208	75.77 224	85.41 108	87.14 231	69.11 61	92.96 122	91.15 191	66.71 289	70.47 230	86.07 248	37.49 343	96.48 130	70.15 212	79.80 198	90.65 221

LS3D		69.17 308	66.40 313	77.50 306	91.92 109	56.12 337	85.12 311	80.37 372	46.96 392	56.50 354	87.51 228	37.25 344	93.71 249	32.52 401	79.40 201	82.68 344

MDA-MVSNet_test_wron		63.78 346	60.16 350	74.64 331	78.15 360	60.41 287	83.49 322	84.03 353	56.17 368	39.17 405	71.59 379	37.22 345	83.24 382	42.87 368	48.73 382	80.26 367

YYNet1		63.76 347	60.14 351	74.62 332	78.06 361	60.19 293	83.46 324	83.99 357	56.18 367	39.25 404	71.56 380	37.18 346	83.34 380	42.90 367	48.70 383	80.32 366

FMVSNet5		68.04 320	65.66 320	75.18 328	84.43 284	57.89 318	83.54 321	86.26 331	61.83 335	53.64 364	73.30 369	37.15 347	85.08 368	48.99 339	61.77 338	82.56 346

test20.03		63.83 345	62.65 341	67.38 373	70.58 392	39.94 405	86.57 305	84.17 352	63.29 317	51.86 370	77.30 347	37.09 348	82.47 385	38.87 383	54.13 372	79.73 370

PVSNet	73.49 8	80.05 172	78.63 180	84.31 154	90.92 137	64.97 170	92.47 146	91.05 199	79.18 82	72.43 208	90.51 178	37.05 349	94.06 233	68.06 231	86.00 140	93.90 143

EU-MVSNet		64.01 344	63.01 338	67.02 374	74.40 379	38.86 409	83.27 326	86.19 333	45.11 397	54.27 360	81.15 311	36.91 350	80.01 395	48.79 341	57.02 362	82.19 350

Anonymous20231211		73.08 274	70.39 290	81.13 242	90.62 142	63.33 217	91.40 190	90.06 234	51.84 378	64.46 302	80.67 316	36.49 351	94.07 232	63.83 273	64.17 318	85.98 295

FMVSNet1		72.71 283	69.91 294	81.10 244	83.60 296	65.11 166	90.01 247	90.32 218	63.92 309	63.56 310	80.25 323	36.35 352	91.54 312	54.46 319	66.75 295	86.64 278

Anonymous20240529		76.84 231	74.15 247	84.88 127	91.02 134	64.95 171	93.84 83	91.09 194	53.57 373	73.00 194	87.42 229	35.91 353	97.32 77	69.14 223	72.41 258	92.36 185

WB-MVS		46.23 375	44.94 377	50.11 395	62.13 408	21.23 428	76.48 373	55.49 414	45.89 395	35.78 406	61.44 403	35.54 354	72.83 403	9.96 422	21.75 417	56.27 410

CMPMVS	48.56 21	66.77 329	64.41 331	73.84 339	70.65 391	50.31 367	77.79 369	85.73 339	45.54 396	44.76 395	82.14 291	35.40 355	90.14 331	63.18 279	74.54 239	81.07 358
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs6		67.57 324	64.76 326	76.00 323	72.82 385	53.37 351	88.71 273	86.78 327	53.19 374	57.58 351	78.03 342	35.33 356	92.41 288	55.56 315	54.88 370	82.21 349

PatchMatch-RL		72.06 288	69.98 291	78.28 298	89.51 165	55.70 340	83.49 322	83.39 362	61.24 337	63.72 309	82.76 282	34.77 357	93.03 261	53.37 325	77.59 217	86.12 292

LTVRE_ROB	59.60 19	66.27 331	63.54 335	74.45 333	84.00 291	51.55 359	67.08 400	83.53 359	58.78 352	54.94 358	80.31 321	34.54 358	93.23 258	40.64 377	68.03 286	78.58 380
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
SSC-MVS		44.51 377	43.35 379	47.99 399	61.01 411	18.90 430	74.12 381	54.36 415	43.42 402	34.10 410	60.02 404	34.42 359	70.39 406	9.14 424	19.57 418	54.68 411

UniMVSNet_ETH3D		72.74 282	70.53 289	79.36 286	78.62 355	56.64 334	85.01 312	89.20 265	63.77 311	64.84 297	84.44 266	34.05 360	91.86 303	63.94 272	70.89 268	89.57 237

F-COLMAP		70.66 295	68.44 303	77.32 310	86.37 248	55.91 338	88.00 284	86.32 329	56.94 363	57.28 352	88.07 218	33.58 361	92.49 286	51.02 329	68.37 283	83.55 326

pmmvs-eth3d		65.53 337	62.32 343	75.19 327	69.39 395	59.59 300	82.80 334	83.43 360	62.52 326	51.30 374	72.49 371	32.86 362	87.16 359	55.32 316	50.73 379	78.83 378

MDA-MVSNet-bldmvs		61.54 353	57.70 358	73.05 344	79.53 339	57.00 333	83.08 330	81.23 367	57.57 356	34.91 409	72.45 372	32.79 363	86.26 363	35.81 388	41.95 393	75.89 389

MIMVSNet		71.64 290	68.44 303	81.23 239	81.97 314	64.44 180	73.05 382	88.80 287	69.67 260	64.59 298	74.79 366	32.79 363	87.82 350	53.99 321	76.35 230	91.42 207

UnsupCasMVSNet_eth		65.79 334	63.10 337	73.88 338	70.71 390	50.29 368	81.09 346	89.88 240	72.58 191	49.25 382	74.77 367	32.57 365	87.43 357	55.96 314	41.04 395	83.90 323

N_pmnet		50.55 371	49.11 373	54.88 390	77.17 367	4.02 434	84.36 315	2.00 432	48.59 387	45.86 391	68.82 386	32.22 366	82.80 384	31.58 403	51.38 378	77.81 385

test_0402		64.54 341	61.09 347	74.92 330	84.10 290	60.75 276	87.95 285	79.71 374	52.03 376	52.41 367	77.20 349	32.21 367	91.64 308	23.14 410	61.03 345	72.36 398

DSMNet-mixed		56.78 364	54.44 368	63.79 378	63.21 405	29.44 421	64.43 403	64.10 408	42.12 405	51.32 373	71.60 378	31.76 368	75.04 400	36.23 386	65.20 307	86.87 276

MSDG		69.54 306	65.73 318	80.96 249	85.11 273	63.71 204	84.19 317	83.28 363	56.95 362	54.50 359	84.03 269	31.50 369	96.03 152	42.87 368	69.13 278	83.14 336

RPSCF		64.24 343	61.98 345	71.01 360	76.10 372	45.00 393	75.83 377	75.94 380	46.94 393	58.96 340	84.59 263	31.40 370	82.00 389	47.76 348	60.33 353	86.04 293

tt0805		73.07 275	70.73 287	80.07 267	78.37 357	57.05 330	87.78 289	92.18 141	61.23 338	67.04 280	86.49 243	31.35 371	94.58 207	65.06 266	67.12 292	88.57 249

jajsoiax		73.05 276	71.51 281	77.67 304	77.46 365	54.83 345	88.81 272	90.04 235	69.13 268	62.85 319	83.51 275	31.16 372	92.75 275	70.83 205	69.80 269	85.43 309

MVS-HIRNet		60.25 358	55.55 365	74.35 334	84.37 285	56.57 335	71.64 386	74.11 387	34.44 408	45.54 393	42.24 416	31.11 373	89.81 334	40.36 378	76.10 232	76.67 388

SixPastTwentyTwo		64.92 339	61.78 346	74.34 335	78.74 352	49.76 369	83.42 325	79.51 375	62.86 322	50.27 377	77.35 346	30.92 374	90.49 323	45.89 356	47.06 385	82.78 338

mmtdpeth		68.33 317	66.37 314	74.21 337	82.81 306	51.73 357	84.34 316	80.42 371	67.01 288	71.56 220	68.58 387	30.52 375	92.35 292	75.89 162	36.21 403	78.56 381

KD-MVS_self_test		60.87 355	58.60 355	67.68 371	66.13 401	39.93 406	75.63 379	84.70 347	57.32 360	49.57 380	68.45 388	29.55 376	82.87 383	48.09 343	47.94 384	80.25 368

mvs_tets		72.71 283	71.11 282	77.52 305	77.41 366	54.52 347	88.45 278	89.76 243	68.76 273	62.70 320	83.26 278	29.49 377	92.71 276	70.51 211	69.62 271	85.34 311

Anonymous202405211		77.96 212	75.33 230	85.87 92	93.73 53	64.52 175	94.85 45	85.36 342	62.52 326	76.11 164	90.18 186	29.43 378	97.29 79	68.51 229	77.24 225	95.81 49

K. test v3		63.09 348	59.61 353	73.53 341	76.26 371	49.38 374	83.27 326	77.15 378	64.35 305	47.77 387	72.32 375	28.73 379	87.79 351	49.93 335	36.69 402	83.41 331

UnsupCasMVSNet_bld		61.60 352	57.71 357	73.29 343	68.73 396	51.64 358	78.61 363	89.05 277	57.20 361	46.11 388	61.96 401	28.70 380	88.60 341	50.08 334	38.90 400	79.63 371

lessismore_v0				73.72 340	72.93 384	47.83 380		61.72 411		45.86 391	73.76 368	28.63 381	89.81 334	47.75 349	31.37 410	83.53 327

MVStest1		51.35 370	46.89 374	64.74 376	65.06 403	51.10 363	67.33 399	72.58 390	30.20 412	35.30 407	74.82 365	27.70 382	69.89 407	24.44 409	24.57 416	73.22 394

new-patchmatchnet		59.30 361	56.48 363	67.79 370	65.86 402	44.19 394	82.47 335	81.77 366	59.94 347	43.65 399	66.20 392	27.67 383	81.68 390	39.34 380	41.40 394	77.50 386

ACMH	63.93 17	68.62 313	64.81 325	80.03 269	85.22 269	63.25 218	87.72 290	84.66 348	60.83 340	51.57 372	79.43 333	27.29 384	94.96 194	41.76 371	64.84 310	81.88 351
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OurMVSNet-221017-0		64.68 340	62.17 344	72.21 352	76.08 373	47.35 382	80.67 349	81.02 368	56.19 366	51.60 371	79.66 331	27.05 385	88.56 342	53.60 324	53.63 373	80.71 362

ACMH+	65.35 16	67.65 323	64.55 328	76.96 316	84.59 280	57.10 329	88.08 281	80.79 369	58.59 354	53.00 365	81.09 312	26.63 386	92.95 264	46.51 352	61.69 342	80.82 360

OpenMVS_ROB	61.12 18	66.39 330	62.92 339	76.80 318	76.51 369	57.77 320	89.22 264	83.41 361	55.48 369	53.86 363	77.84 343	26.28 387	93.95 242	34.90 391	68.76 280	78.68 379

test_fmvs1		74.07 266	73.69 254	75.22 326	78.91 350	47.34 383	89.06 270	74.69 386	63.68 313	79.41 128	91.59 162	24.36 388	87.77 352	85.22 82	76.26 231	90.55 224

COLMAP_ROB	57.96 20	62.98 349	59.65 352	72.98 345	81.44 318	53.00 353	83.75 320	75.53 384	48.34 389	48.81 384	81.40 304	24.14 389	90.30 324	32.95 396	60.52 350	75.65 390
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MIMVSNet1		60.16 359	57.33 360	68.67 367	69.71 393	44.13 395	78.92 362	84.21 351	55.05 370	44.63 396	71.85 377	23.91 390	81.54 391	32.63 400	55.03 369	80.35 365

testgi		64.48 342	62.87 340	69.31 365	71.24 386	40.62 403	85.49 309	79.92 373	65.36 299	54.18 361	83.49 276	23.74 391	84.55 370	41.60 372	60.79 348	82.77 339

ITE_SJBPF				70.43 361	74.44 378	47.06 386		77.32 377	60.16 345	54.04 362	83.53 274	23.30 392	84.01 374	43.07 365	61.58 343	80.21 369

mvs5depth		61.03 354	57.65 359	71.18 358	67.16 399	47.04 387	72.74 383	77.49 376	57.47 359	60.52 329	72.53 370	22.84 393	88.38 344	49.15 338	38.94 399	78.11 384

EG-PatchMatch MVS		68.55 314	65.41 322	77.96 302	78.69 353	62.93 228	89.86 252	89.17 267	60.55 341	50.27 377	77.73 345	22.60 394	94.06 233	47.18 350	72.65 255	76.88 387

tmp_tt		22.26 392	23.75 394	17.80 408	5.23 432	12.06 433	35.26 419	39.48 426	2.82 426	18.94 417	44.20 415	22.23 395	24.64 427	36.30 385	9.31 424	16.69 421

USDC		67.43 327	64.51 329	76.19 321	77.94 362	55.29 342	78.38 365	85.00 345	73.17 177	48.36 385	80.37 320	21.23 396	92.48 287	52.15 327	64.02 321	80.81 361

Anonymous20240521		62.09 350	59.08 354	71.10 359	67.19 398	48.72 377	83.91 319	85.23 343	50.38 383	47.84 386	71.22 382	20.74 397	85.51 367	46.47 353	58.75 358	79.06 375

test_vis1_n		71.63 291	70.73 287	74.31 336	69.63 394	47.29 384	86.91 301	72.11 392	63.21 319	75.18 175	90.17 187	20.40 398	85.76 364	84.59 92	74.42 241	89.87 231

XVG-ACMP-BASELINE		68.04 320	65.53 321	75.56 324	74.06 380	52.37 354	78.43 364	85.88 336	62.03 331	58.91 341	81.21 310	20.38 399	91.15 319	60.69 294	68.18 284	83.16 335

test_fmvs1_n		72.69 285	71.92 276	74.99 329	71.15 388	47.08 385	87.34 297	75.67 381	63.48 315	78.08 145	91.17 169	20.16 400	87.87 349	84.65 91	75.57 235	90.01 230

AllTest		61.66 351	58.06 356	72.46 349	79.57 337	51.42 361	80.17 355	68.61 401	51.25 380	45.88 389	81.23 306	19.86 401	86.58 361	38.98 381	57.01 363	79.39 372

TestCases				72.46 349	79.57 337	51.42 361		68.61 401	51.25 380	45.88 389	81.23 306	19.86 401	86.58 361	38.98 381	57.01 363	79.39 372

test_vis1_rt		59.09 362	57.31 361	64.43 377	68.44 397	46.02 391	83.05 332	48.63 421	51.96 377	49.57 380	63.86 397	16.30 403	80.20 394	71.21 203	62.79 327	67.07 404

pmmvs3		55.51 365	51.50 371	67.53 372	57.90 413	50.93 365	80.37 351	73.66 388	40.63 406	44.15 398	64.75 395	16.30 403	78.97 396	44.77 362	40.98 397	72.69 396

test_fmvs2		65.78 335	64.84 324	68.60 368	66.54 400	41.71 400	83.27 326	69.81 399	54.38 371	67.91 266	84.54 265	15.35 405	81.22 392	75.65 164	66.16 298	82.88 337

TDRefinement		55.28 366	51.58 370	66.39 375	59.53 412	46.15 390	76.23 374	72.80 389	44.60 398	42.49 401	76.28 358	15.29 406	82.39 386	33.20 395	43.75 390	70.62 400

new_pmnet		49.31 372	46.44 375	57.93 385	62.84 406	40.74 402	68.47 395	62.96 410	36.48 407	35.09 408	57.81 405	14.97 407	72.18 404	32.86 398	46.44 386	60.88 407

TinyColmap		60.32 357	56.42 364	72.00 356	78.78 351	53.18 352	78.36 366	75.64 382	52.30 375	41.59 403	75.82 362	14.76 408	88.35 345	35.84 387	54.71 371	74.46 391

EGC-MVSNET		42.35 378	38.09 381	55.11 389	74.57 377	46.62 388	71.63 387	55.77 413	0.04 427	0.24 428	62.70 399	14.24 409	74.91 401	17.59 416	46.06 387	43.80 413

LF4IMVS		54.01 368	52.12 369	59.69 383	62.41 407	39.91 407	68.59 394	68.28 403	42.96 403	44.55 397	75.18 363	14.09 410	68.39 409	41.36 374	51.68 377	70.78 399

ttmdpeth		53.34 369	49.96 372	63.45 379	62.07 409	40.04 404	72.06 384	65.64 406	42.54 404	51.88 369	77.79 344	13.94 411	76.48 398	32.93 397	30.82 413	73.84 393

PM-MVS		59.40 360	56.59 362	67.84 369	63.63 404	41.86 399	76.76 371	63.22 409	59.01 351	51.07 375	72.27 376	11.72 412	83.25 381	61.34 290	50.28 381	78.39 382

mvsany_test3		48.86 373	46.35 376	56.41 386	46.00 421	31.67 417	62.26 405	47.25 422	43.71 401	45.54 393	68.15 389	10.84 413	64.44 418	57.95 306	35.44 407	73.13 395

ambc				69.61 363	61.38 410	41.35 401	49.07 417	85.86 338		50.18 379	66.40 391	10.16 414	88.14 347	45.73 357	44.20 389	79.32 374

FPMVS		45.64 376	43.10 380	53.23 393	51.42 418	36.46 411	64.97 402	71.91 393	29.13 413	27.53 413	61.55 402	9.83 415	65.01 416	16.00 419	55.58 367	58.22 409

ANet_high		40.27 382	35.20 385	55.47 388	34.74 429	34.47 414	63.84 404	71.56 395	48.42 388	18.80 418	41.08 417	9.52 416	64.45 417	20.18 413	8.66 425	67.49 403

test_method		38.59 383	35.16 386	48.89 397	54.33 414	21.35 427	45.32 418	53.71 416	7.41 424	28.74 412	51.62 408	8.70 417	52.87 421	33.73 392	32.89 409	72.47 397

EMVS		23.76 391	23.20 395	25.46 407	41.52 427	16.90 432	60.56 408	38.79 428	14.62 422	8.99 426	20.24 425	7.35 418	45.82 425	7.25 426	9.46 423	13.64 423

test_f		46.58 374	43.45 378	55.96 387	45.18 422	32.05 416	61.18 406	49.49 420	33.39 409	42.05 402	62.48 400	7.00 419	65.56 414	47.08 351	43.21 392	70.27 401

test_fmvs3		56.82 363	54.86 367	62.69 382	53.59 415	35.47 412	75.87 376	65.64 406	43.91 400	55.10 357	71.43 381	6.91 420	74.40 402	68.64 228	52.63 374	78.20 383

E-PMN		24.61 389	24.00 393	26.45 406	43.74 424	18.44 431	60.86 407	39.66 425	15.11 421	9.53 425	22.10 422	6.52 421	46.94 424	8.31 425	10.14 422	13.98 422

DeepMVS_CX				34.71 405	51.45 417	24.73 425		28.48 431	31.46 411	17.49 421	52.75 407	5.80 422	42.60 426	18.18 414	19.42 419	36.81 418

Gipuma		34.91 385	31.44 388	45.30 400	70.99 389	39.64 408	19.85 422	72.56 391	20.10 418	16.16 422	21.47 423	5.08 423	71.16 405	13.07 420	43.70 391	25.08 420
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
APD_test1		40.50 380	37.31 383	50.09 396	51.88 416	35.27 413	59.45 410	52.59 417	21.64 416	26.12 414	57.80 406	4.56 424	66.56 412	22.64 411	39.09 398	48.43 412

LCM-MVSNet		40.54 379	35.79 384	54.76 391	36.92 428	30.81 418	51.41 415	69.02 400	22.07 415	24.63 415	45.37 412	4.56 424	65.81 413	33.67 393	34.50 408	67.67 402

PMMVS2		37.93 384	33.61 387	50.92 394	46.31 420	24.76 424	60.55 409	50.05 418	28.94 414	20.93 416	47.59 409	4.41 426	65.13 415	25.14 408	18.55 420	62.87 406

test_vis3_rt		40.46 381	37.79 382	48.47 398	44.49 423	33.35 415	66.56 401	32.84 429	32.39 410	29.65 411	39.13 419	3.91 427	68.65 408	50.17 332	40.99 396	43.40 414

testf1		32.77 386	29.47 389	42.67 402	41.89 425	30.81 418	52.07 413	43.45 423	15.45 419	18.52 419	44.82 413	2.12 428	58.38 419	16.05 417	30.87 411	38.83 415

APD_test2		32.77 386	29.47 389	42.67 402	41.89 425	30.81 418	52.07 413	43.45 423	15.45 419	18.52 419	44.82 413	2.12 428	58.38 419	16.05 417	30.87 411	38.83 415

PMVS	26.43 22	31.84 388	28.16 391	42.89 401	25.87 431	27.58 422	50.92 416	49.78 419	21.37 417	14.17 423	40.81 418	2.01 430	66.62 411	9.61 423	38.88 401	34.49 419
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	24.84 23	24.35 390	19.77 396	38.09 404	34.56 430	26.92 423	26.57 420	38.87 427	11.73 423	11.37 424	27.44 420	1.37 431	50.42 423	11.41 421	14.60 421	36.93 417
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		11.30 394	10.95 397	12.33 409	48.05 419	19.89 429	25.89 421	1.92 433	3.58 425	3.12 427	1.37 427	0.64 432	15.77 428	6.23 427	7.77 426	1.35 424

test123		6.92 397	9.21 400	0.08 410	0.03 434	0.05 435	81.65 341	0.01 435	0.02 429	0.14 430	0.85 429	0.03 433	0.02 429	0.12 429	0.00 428	0.16 425

testmvs		7.23 396	9.62 399	0.06 411	0.04 433	0.02 436	84.98 313	0.02 434	0.03 428	0.18 429	1.21 428	0.01 434	0.02 429	0.14 428	0.01 427	0.13 426

mmdepth		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 428	0.00 427

monomultidepth		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 428	0.00 427

test_blank		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 428	0.00 427

uanet_test		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 428	0.00 427

DCPMVS		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 428	0.00 427

sosnet-low-res		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 428	0.00 427

sosnet		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 428	0.00 427

uncertanet		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 428	0.00 427

Regformer		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 428	0.00 427

ab-mvs-re		7.91 395	10.55 398	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	94.95 73	0.00 435	0.00 431	0.00 430	0.00 428	0.00 427

uanet		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 428	0.00 427

WAC-MVS						49.45 372								31.56 404

FOURS1					93.95 46	61.77 254	93.96 73	91.92 152	62.14 330	86.57 50

MSC_two_6792asdad				89.60 9	97.31 4	73.22 12		95.05 27					99.07 13	92.01 29	94.77 26	96.51 24

No_MVS				89.60 9	97.31 4	73.22 12		95.05 27					99.07 13	92.01 29	94.77 26	96.51 24

eth-test2					0.00 435

eth-test					0.00 435

IU-MVS					96.46 11	69.91 42		95.18 21	80.75 53	95.28 1				92.34 26	95.36 14	96.47 28

save fliter					93.84 49	67.89 95	95.05 39	92.66 120	78.19 99

test_0728_SECOND				88.70 18	96.45 12	70.43 33	96.64 10	94.37 53					99.15 2	91.91 32	94.90 22	96.51 24

GSMVS																94.68 102

test_part2					96.29 19	68.16 88				90.78 18

MTGPA								92.23 134

MTMP							93.77 87	32.52 430

gm-plane-assit					88.42 193	67.04 119			78.62 95		91.83 156		97.37 73	76.57 158

test9_res														89.41 44	94.96 19	95.29 71

agg_prior2														86.41 74	94.75 30	95.33 67

agg_prior					94.16 43	66.97 121		93.31 92		84.49 72			96.75 119

test_prior4						67.18 114	93.92 76

test_prior				86.42 76	94.71 35	67.35 109		93.10 103					96.84 116			95.05 84

旧先验2							92.00 167		59.37 350	87.54 43			93.47 255	75.39 166

新几何2							91.41 188

无先验							92.71 132	92.61 124	62.03 331				97.01 99	66.63 246		93.97 138

原ACMM2							92.01 164

testdata2													96.09 146	61.26 291

testdata1							89.21 265		77.55 113

plane_prior7					86.94 236	61.51 260

plane_prior5								91.31 182					95.55 175	76.74 156	78.53 211	88.39 253

plane_prior4											89.14 202

plane_prior3						61.95 252			79.09 85	72.53 204

plane_prior2							93.13 114		78.81 92

plane_prior1					87.15 230

plane_prior						62.42 240	93.85 80		79.38 77						78.80 208

n2								0.00 436

nn								0.00 436

door-mid								66.01 405

test11								93.01 106

door								66.57 404

HQP5-MVS						63.66 208

HQP-NCC					87.54 220		94.06 66		79.80 68	74.18 183

ACMP_Plane					87.54 220		94.06 66		79.80 68	74.18 183

BP-MVS														77.63 153

HQP4-MVS										74.18 183			95.61 170			88.63 247

HQP3-MVS								91.70 168							78.90 206

NP-MVS					87.41 223	63.04 224					90.30 183

ACMMP++_ref															71.63 261

ACMMP++															69.72 270

High-resolution multi-view benchmark