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	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

LTVRE_ROB	86.82 1	91.55 3	94.43 3	88.19 10	83.19 114	86.35 66	93.60 39	78.79 18	95.48 3	91.79 2	93.08 28	97.21 20	86.34 3	97.06 2	96.27 3	95.46 23	95.56 3
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
COLMAP_ROB	85.66 2	91.85 2	95.01 2	88.16 11	88.98 52	92.86 2	95.51 19	72.17 64	94.95 4	91.27 3	94.11 17	97.77 11	84.22 8	96.49 4	95.27 5	96.79 2	93.60 12
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
3Dnovator+	83.71 3	88.13 45	90.00 51	85.94 29	86.82 72	91.06 13	94.26 35	75.39 46	88.85 43	85.76 37	85.74 132	86.92 172	78.02 46	93.03 40	92.21 34	95.39 25	92.21 35

DeepC-MVS	83.59 4	90.37 12	92.56 18	87.82 14	91.26 27	92.33 3	94.72 30	80.04 9	90.01 32	84.61 42	93.33 24	94.22 100	80.59 27	92.90 43	92.52 28	95.69 21	92.57 28
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DeepC-MVS_fast	81.78 5	87.38 50	89.64 52	84.75 41	89.89 42	90.70 23	92.74 46	74.45 50	86.02 74	82.16 64	86.05 129	91.99 133	75.84 66	91.16 64	90.44 49	93.41 51	91.09 44
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DeepPCF-MVS	81.61 6	87.95 48	90.29 50	85.22 38	87.48 66	90.01 32	93.79 36	73.54 54	88.93 41	83.89 45	89.40 83	90.84 146	80.26 32	90.62 73	90.19 54	92.36 71	92.03 36

ACMM	80.67 7	90.67 7	92.46 19	88.57 7	91.35 22	89.93 33	96.34 11	77.36 30	90.17 29	86.88 29	87.32 111	96.63 26	83.32 13	95.79 10	94.49 9	96.19 9	92.91 26
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP	80.00 8	90.12 16	92.30 26	87.58 18	90.83 34	91.10 12	94.96 28	76.06 40	87.47 56	85.33 39	88.91 93	97.65 14	82.13 19	95.31 17	93.44 19	96.14 10	92.22 34
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PMVS	79.51 9	90.23 14	92.67 14	87.39 20	90.16 39	88.75 43	93.64 38	75.78 44	90.00 33	83.70 47	92.97 30	92.22 126	86.13 4	97.01 3	96.79 2	94.94 28	90.96 46
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
3Dnovator	79.41 10	82.21 98	86.07 86	77.71 111	79.31 162	84.61 74	87.18 102	61.02 179	85.65 77	76.11 108	85.07 137	85.38 185	70.96 106	87.22 107	86.47 86	91.66 79	88.12 73

ACMH+	79.05 11	89.62 26	93.08 8	85.58 32	88.58 57	89.26 40	92.18 48	74.23 52	93.55 8	82.66 57	92.32 38	98.35 7	80.29 30	95.28 18	92.34 31	95.52 22	90.43 49

ACMH	78.40 12	88.94 38	92.62 16	84.65 42	86.45 75	87.16 61	91.47 51	68.79 89	95.49 2	89.74 6	93.55 21	98.50 2	77.96 47	94.14 31	89.57 63	93.49 47	89.94 53
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TAPA-MVS	78.00 13	85.88 59	88.37 62	82.96 61	84.69 88	88.62 44	90.62 60	64.22 136	89.15 40	88.05 14	78.83 176	93.71 104	76.20 62	90.11 82	88.22 73	94.00 41	89.97 52
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PCF-MVS	76.59 14	84.11 75	85.27 100	82.76 65	86.12 79	88.30 46	91.24 53	69.10 84	82.36 115	84.45 43	77.56 188	90.40 151	72.91 89	85.88 120	83.88 117	92.72 64	88.53 67
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PLC	76.06 15	85.38 65	87.46 73	82.95 62	85.79 82	88.84 42	88.86 85	68.70 90	87.06 62	83.60 48	79.02 171	90.05 152	77.37 53	90.88 71	89.66 60	93.37 52	86.74 80
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
OpenMVS	75.38 16	78.44 149	81.39 158	74.99 143	80.46 150	79.85 119	79.99 174	58.31 199	77.34 160	73.85 126	77.19 191	82.33 198	68.60 121	84.67 139	81.95 136	88.72 123	86.40 83

IB-MVS	71.28 17	75.21 174	77.00 183	73.12 157	76.76 187	77.45 150	83.05 147	58.92 195	63.01 230	64.31 182	59.99 247	87.57 170	68.64 118	86.26 118	82.34 133	87.05 145	82.36 121
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
CMPMVS	55.74 18	71.56 201	76.26 192	66.08 213	68.11 231	63.91 232	63.17 250	50.52 238	68.79 207	75.49 113	70.78 230	85.67 182	63.54 162	81.58 175	77.20 181	75.63 222	85.86 85
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MVE	41.12 19	51.80 252	60.92 246	41.16 251	35.21 261	34.14 261	48.45 262	41.39 249	69.11 205	19.53 261	63.33 243	73.80 225	63.56 161	67.19 240	61.51 242	38.85 259	57.38 248
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
casdiffseed414692147		82.71 95	86.24 83	78.60 103	84.08 98	81.22 107	85.85 120	66.16 114	83.98 98	76.07 109	90.85 62	97.20 21	70.51 109	85.74 121	82.14 134	88.92 118	82.56 118

gbinet_0.2-2-1-0.02		73.88 181	76.94 185	70.31 178	76.23 198	74.72 180	77.93 190	57.54 204	72.77 186	64.37 181	80.14 163	85.20 186	60.60 173	76.92 202	71.41 213	85.16 183	77.45 173

0.3-1-1-0.015		61.14 238	60.59 247	61.78 228	65.65 244	67.14 222	69.76 236	48.31 240	51.00 253	53.98 219	56.11 251	56.81 250	53.29 218	63.79 250	63.19 235	79.66 213	66.07 221

0.4-1-1-0.1		62.35 234	62.12 243	62.60 223	66.85 238	68.23 217	70.78 231	49.40 239	52.78 251	54.44 218	59.25 249	57.42 247	53.76 216	65.41 246	64.40 233	80.41 211	67.37 218

0.4-1-1-0.2		60.88 239	60.45 248	61.38 229	65.29 245	66.73 224	69.11 242	48.01 242	50.14 256	53.73 226	57.22 250	57.01 249	52.91 222	63.57 251	62.64 236	79.23 216	65.82 222

wanda-best-256-512		72.50 196	75.48 199	69.03 191	75.29 205	72.66 194	75.85 206	55.31 215	73.43 177	63.41 186	78.69 177	86.04 179	59.27 185	74.34 216	69.81 220	85.06 184	73.37 200

usedtu_dtu_shiyan2		73.14 190	78.83 169	66.49 208	80.89 147	69.55 212	78.12 189	67.67 103	89.65 35	49.76 239	80.90 161	95.49 64	45.72 239	78.37 195	74.56 200	76.81 221	63.31 231

usedtu_dtu_shiyan1		73.59 183	77.49 179	69.05 190	76.40 197	72.84 193	75.67 216	60.47 182	74.12 176	59.35 199	79.02 171	88.33 166	56.25 201	77.46 199	77.81 173	86.14 164	72.84 204

blended_shiyan8		73.23 186	76.36 191	69.57 184	75.91 201	73.04 190	76.56 202	55.74 209	74.84 173	63.75 183	79.69 168	86.62 175	59.80 176	75.17 211	71.00 214	85.67 177	74.20 192

E5new		81.18 116	84.50 117	77.29 117	82.38 130	78.21 138	86.06 116	62.76 159	86.68 66	78.24 95	90.75 63	95.93 50	67.54 130	82.06 166	77.51 177	86.77 149	80.40 142

FE-blended-shiyan7		72.50 196	75.48 199	69.03 191	75.29 205	72.66 194	75.85 206	55.31 215	73.43 177	63.41 186	78.69 177	86.04 179	59.27 185	74.34 216	69.81 220	85.06 184	73.37 200

E6new		81.99 102	85.39 96	78.02 108	82.48 125	78.47 131	87.03 108	63.34 150	87.93 50	79.62 81	92.12 40	97.12 22	68.62 119	83.40 149	78.53 165	87.05 145	80.13 153

blended_shiyan6		73.23 186	76.38 190	69.56 185	75.93 200	73.03 191	76.58 201	55.73 210	74.84 173	63.74 184	79.66 169	86.74 174	59.75 177	75.14 212	70.97 215	85.65 178	74.26 189

usedtu_blend_shiyan5		67.09 219	67.69 225	66.40 209	75.29 205	72.66 194	69.07 243	55.31 215	73.43 177	53.98 219	53.29 252	56.81 250	59.69 178	74.34 216	69.81 220	85.06 184	73.46 198

blend_shiyan4		63.43 227	63.66 237	63.17 222	62.30 248	71.99 201	65.44 247	52.82 231	48.52 257	53.98 219	53.29 252	56.81 250	59.69 178	71.98 228	69.57 225	84.81 191	73.46 198

E6		81.99 102	85.39 96	78.02 108	82.48 125	78.47 131	87.03 108	63.34 150	87.93 50	79.62 81	92.12 40	97.12 22	68.62 119	83.40 149	78.53 165	87.05 145	80.13 153

E5		81.18 116	84.50 117	77.29 117	82.38 130	78.21 138	86.06 116	62.76 159	86.68 66	78.24 95	90.75 63	95.93 50	67.54 130	82.06 166	77.51 177	86.77 149	80.40 142

FE-MVSNET3		67.68 217	67.80 224	67.53 203	75.29 205	72.66 194	75.85 206	55.31 215	73.43 177	53.98 219	53.29 252	56.81 250	59.69 178	74.34 216	69.81 220	85.06 184	74.26 189

E4		81.47 109	84.83 110	77.55 114	82.40 128	78.25 136	86.41 114	62.92 157	87.20 60	78.63 91	91.12 58	96.50 29	68.00 126	82.58 162	77.96 170	86.93 148	80.22 150

E3new		80.80 120	83.95 132	77.13 119	82.13 134	78.06 140	86.04 118	62.57 162	85.02 86	77.97 99	89.98 73	95.83 53	67.49 133	81.75 172	77.19 182	86.56 155	79.82 156

FE-MVSNET2		78.59 146	83.83 136	72.48 158	78.67 169	75.81 165	79.06 184	63.78 145	85.63 78	65.66 178	87.12 116	96.22 40	59.04 189	83.72 147	82.07 135	88.67 125	76.26 177

E2		79.77 131	82.52 152	76.56 127	81.77 139	77.80 146	85.49 125	62.14 168	81.45 129	77.16 103	88.03 103	94.73 89	66.75 140	80.40 187	76.02 193	86.07 166	79.22 162

E3		80.80 120	83.95 132	77.13 119	82.13 134	78.05 141	86.03 119	62.56 163	85.00 88	77.99 98	89.99 72	95.83 53	67.50 132	81.75 172	77.19 182	86.56 155	79.81 157

TestfortrainingZip							94.55 31	72.48 62		73.73 128						91.99 75

viewdifsd2359ckpt07		78.49 148	83.75 138	72.35 159	80.46 150	75.49 171	83.92 142	53.96 225	85.53 80	67.94 168	91.12 58	96.06 43	66.18 146	81.43 178	75.39 198	81.62 209	81.26 131

viewdifsd2359ckpt09		82.38 96	85.92 89	78.26 106	81.46 143	83.33 86	87.76 93	66.85 107	80.47 142	72.93 134	86.68 121	94.75 88	71.25 101	86.58 113	86.23 91	89.30 112	83.41 107

viewdifsd2359ckpt13		80.07 126	83.42 143	76.17 129	80.95 146	79.07 126	85.14 133	61.42 175	80.41 143	74.78 120	87.22 114	94.70 90	68.23 123	82.60 160	78.34 167	86.49 157	81.63 128

viewcassd2359sk11		80.26 125	83.21 145	76.82 123	81.93 137	77.91 144	85.75 121	62.34 167	83.17 103	77.53 101	89.00 89	95.26 73	67.11 138	81.06 180	76.55 190	86.29 162	79.50 160

viewdifsd2359ckpt11		78.29 150	84.30 122	71.27 167	78.48 171	74.68 183	82.25 155	55.40 213	82.45 111	60.97 197	91.34 52	96.58 28	65.48 151	85.14 128	78.70 163	85.05 189	81.21 132

viewmacassd2359aftdt		81.04 119	85.39 96	75.95 130	80.71 148	77.95 143	85.29 132	58.82 196	86.88 64	76.27 106	91.34 52	96.35 35	68.32 122	84.35 142	79.13 162	86.32 161	81.73 127

viewmsd2359difaftdt		78.29 150	84.30 122	71.27 167	78.48 171	74.69 182	82.25 155	55.40 213	82.45 111	60.98 196	91.34 52	96.59 27	65.48 151	85.14 128	78.70 163	85.05 189	81.21 132

diffmvs_AUTHOR		77.61 155	82.84 150	71.49 166	76.16 199	74.80 178	81.22 163	57.90 202	79.89 147	68.06 165	90.49 66	94.78 87	62.29 168	81.77 171	77.04 185	83.33 203	81.14 136

FE-MVSNET		75.03 176	80.98 159	68.08 198	73.53 212	71.43 203	75.74 214	59.74 189	81.81 120	58.16 202	82.47 153	93.51 110	55.42 207	83.18 151	80.51 149	85.90 171	73.94 193

viewmambaseed2359dif		76.20 165	80.07 163	71.68 165	76.99 185	73.91 187	80.81 167	59.23 192	74.86 172	66.65 174	86.44 123	93.44 111	62.91 166	79.19 193	73.77 203	83.49 200	78.89 164

viewmanbaseed2359cas		79.90 129	83.96 131	75.17 139	80.25 153	77.62 148	84.62 137	58.25 200	83.22 102	74.92 117	89.50 81	95.33 71	67.20 135	83.05 152	77.84 172	85.76 175	81.18 134

ME-MVS		88.45 43	92.03 33	84.27 48	89.33 47	90.77 21	94.55 31	72.48 62	89.22 39	76.86 104	93.91 20	95.41 67	80.41 28	92.07 50	90.28 52	91.99 75	92.56 29

MGCFI-Net		79.42 137	85.64 95	72.15 162	82.80 122	82.09 98	76.92 198	65.46 125	86.31 71	57.48 204	78.15 182	91.38 141	59.10 188	88.23 100	84.47 113	91.14 90	88.88 64

sasdasda		81.22 114	86.04 87	75.60 133	83.17 115	83.18 87	80.29 171	65.82 121	85.97 75	67.98 166	77.74 185	91.51 138	65.17 153	88.62 93	86.15 93	91.17 88	89.09 60

WB-MVS		72.91 194	82.95 147	61.21 230	68.59 229	73.96 186	73.65 223	61.48 174	90.88 20	42.55 247	94.18 16	95.80 56	53.02 221	85.42 126	75.73 196	67.97 242	64.65 225

dmvs_re		68.11 215	70.60 216	65.21 218	77.91 180	63.73 233	76.72 199	59.65 190	55.93 246	47.79 242	59.79 248	79.91 204	49.72 232	82.48 163	76.98 187	79.48 214	75.41 184

TPM-MVS					86.18 78	83.43 85	87.57 96			78.77 89	69.75 235	84.63 189	62.24 169			89.88 102	88.48 68
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
FA-MVS(training)		78.93 145	80.63 161	76.93 121	79.79 158	75.57 170	85.44 126	61.95 170	77.19 161	78.97 87	84.82 140	82.47 195	66.43 145	84.09 144	80.13 154	89.02 116	80.15 152

test2506		75.32 173	76.87 186	73.50 152	84.55 92	80.37 114	79.63 180	73.23 57	82.64 108	55.41 213	76.87 194	45.42 264	59.61 183	90.35 78	86.46 87	88.58 128	75.98 179

test1111		79.67 133	84.40 119	74.16 148	85.29 85	79.56 123	81.16 164	73.13 59	84.65 92	56.08 209	88.38 98	86.14 178	60.49 174	89.78 84	85.59 100	88.79 121	76.68 175

ECVR-MVS		79.31 141	84.20 127	73.60 150	84.55 92	80.37 114	79.63 180	73.23 57	82.64 108	55.98 210	87.50 107	86.85 173	59.61 183	90.35 78	86.46 87	88.58 128	75.26 186

DVP-MVS++		90.50 10	94.18 4	86.21 27	92.52 7	90.29 29	95.29 22	76.02 41	94.24 5	82.82 54	95.84 5	97.56 15	76.82 56	93.13 38	91.20 44	93.78 45	97.01 1

GeoE		81.92 105	83.87 134	79.66 95	84.64 89	79.87 118	89.75 76	65.90 119	76.12 165	75.87 111	84.62 143	92.23 125	71.96 96	86.83 111	83.60 120	89.83 104	83.81 102

test_method		22.69 255	26.99 257	17.67 255	2.13 263	4.31 264	27.50 263	4.53 259	37.94 258	24.52 260	36.20 259	51.40 262	15.26 257	29.86 258	17.09 258	32.07 261	12.16 259

pmnet_mix02		62.60 232	70.81 215	53.02 245	66.56 239	50.44 252	62.81 251	46.84 244	79.13 154	43.76 246	87.45 108	90.75 148	39.85 246	70.48 233	57.09 247	58.27 251	60.32 241

RE-MVS-def										87.10 28

SED-MVS		88.96 37	92.37 22	84.99 40	88.64 56	89.65 38	95.11 25	75.98 42	90.73 24	80.15 77	94.21 15	94.51 96	76.59 57	92.94 41	91.17 45	93.46 50	93.37 22

SF-MVS		87.85 49	90.95 45	84.22 50	88.17 61	87.90 55	90.80 58	71.80 67	89.28 36	82.70 56	89.90 75	95.37 70	77.91 48	91.69 55	90.04 55	93.95 44	92.47 30

9.14												89.43 156

uanet_test		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

ET-MVSNet_ETH3D		74.71 178	74.19 206	75.31 137	79.22 164	75.29 172	82.70 151	64.05 139	65.45 219	70.96 148	77.15 192	57.70 246	65.89 147	84.40 141	81.65 140	89.03 115	77.67 172

UniMVSNet_ETH3D		85.39 64	91.12 44	78.71 100	90.48 37	83.72 80	81.76 159	82.41 6	93.84 6	64.43 180	95.41 7	98.76 1	63.72 160	93.63 33	89.74 58	89.47 110	82.74 116

EIA-MVS		78.57 147	77.90 175	79.35 98	87.24 70	80.71 111	86.16 115	64.03 140	62.63 234	73.49 130	73.60 216	76.12 220	73.83 83	88.49 95	84.93 107	91.36 83	78.78 166

ETV-MVS		79.01 144	77.98 174	80.22 92	86.69 73	79.73 121	88.80 86	68.27 96	63.22 229	71.56 143	70.25 233	73.63 226	73.66 85	90.30 80	86.77 85	92.33 72	81.95 124

CS-MVS		83.57 81	84.79 112	82.14 69	83.83 106	81.48 102	87.29 100	66.54 109	72.73 187	80.05 78	84.04 146	93.12 116	80.35 29	89.50 85	86.34 89	94.76 34	86.32 84

DVP-MVS		89.40 27	92.69 13	85.56 34	89.01 51	89.85 34	93.72 37	75.42 45	92.28 11	80.49 72	94.36 13	94.87 83	81.46 24	92.49 49	91.42 41	93.27 53	93.54 17
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
SR-MVS					91.82 13			80.80 7				95.53 63

DPM-MVS		81.42 110	82.11 154	80.62 87	87.54 65	85.30 72	90.18 73	68.96 86	81.00 136	79.15 86	70.45 231	83.29 192	67.67 129	82.81 157	83.46 121	90.19 97	88.48 68

thisisatest0530		75.54 172	75.95 197	75.05 140	75.08 209	73.56 188	82.15 157	60.31 183	69.17 203	69.32 154	79.02 171	58.78 245	72.17 92	83.88 145	83.08 128	91.30 85	84.20 98

Anonymous202405211			84.68 114		83.92 103	79.45 124	79.03 185	67.79 100	82.01 118		88.77 96	92.58 120	55.93 203	86.68 112	84.26 114	88.92 118	78.98 163

DCV-MVSNet		80.04 127	85.67 94	73.48 153	82.91 119	81.11 109	80.44 170	66.06 115	85.01 87	62.53 192	78.84 175	94.43 98	58.51 192	88.66 92	85.91 96	90.41 95	85.73 87

tttt0517		75.86 170	76.23 193	75.42 135	75.55 204	74.06 185	82.73 150	60.31 183	69.24 202	70.24 151	79.18 170	58.79 244	72.17 92	84.49 140	83.08 128	91.54 80	84.80 91

our_test_3					73.27 214	70.91 205	83.26 145

thisisatest0515		81.18 116	84.32 121	77.52 116	76.73 193	74.84 177	85.06 134	61.37 176	81.05 135	73.95 125	88.79 95	89.25 159	75.49 69	85.98 119	84.78 109	92.53 68	85.56 89

SMA-MVS		90.13 15	92.26 27	87.64 17	91.68 16	90.44 27	95.22 24	77.34 32	90.79 23	87.80 16	90.42 69	92.05 131	79.05 36	93.89 32	93.59 18	94.77 32	94.62 5
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
DPE-MVS		89.81 22	92.34 24	86.86 23	89.69 44	91.00 16	95.53 18	76.91 33	88.18 48	83.43 53	93.48 22	95.19 75	81.07 26	92.75 45	92.07 36	94.55 36	93.74 11
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
thres100view900		69.86 206	72.97 213	66.24 210	77.97 178	72.49 199	73.29 224	59.12 193	66.81 211	50.82 237	67.30 238	75.67 222	50.54 231	78.24 197	79.40 158	85.71 176	70.88 207

tfpnnormal		77.16 157	84.26 124	68.88 193	81.02 145	75.02 174	76.52 203	63.30 152	87.29 58	52.40 230	91.24 57	93.97 101	54.85 210	85.46 125	81.08 143	85.18 182	75.76 182

tfpn200view9		72.01 199	75.40 201	68.06 199	77.97 178	76.44 159	77.04 196	62.67 161	66.81 211	50.82 237	67.30 238	75.67 222	52.46 228	85.06 131	82.64 131	87.41 141	73.86 194

CHOSEN 280x420		56.32 249	58.85 255	53.36 244	51.63 255	39.91 259	69.12 241	38.61 251	56.29 245	36.79 256	48.84 256	62.59 236	63.39 164	73.61 224	67.66 228	60.61 247	63.07 233

CANet		82.84 91	84.60 115	80.78 82	87.30 68	85.20 73	90.23 71	69.00 85	72.16 191	78.73 90	84.49 144	90.70 149	69.54 115	87.65 102	86.17 92	89.87 103	85.84 86

Fast-Effi-MVS+-dtu		76.92 158	77.18 181	76.62 125	79.55 159	79.17 125	84.80 135	77.40 29	64.46 224	68.75 160	70.81 229	86.57 176	63.36 165	81.74 174	81.76 139	85.86 172	75.78 181

Effi-MVS+-dtu		82.04 101	83.39 144	80.48 90	85.48 84	86.57 65	88.40 88	68.28 95	69.04 206	73.13 133	76.26 199	91.11 145	74.74 76	88.40 96	87.76 75	92.84 63	84.57 94

CANet_DTU		75.04 175	78.45 170	71.07 170	77.27 183	77.96 142	83.88 143	58.00 201	64.11 225	68.67 161	75.65 206	88.37 165	53.92 215	82.05 168	81.11 142	84.67 192	79.88 155

MGCNet		85.73 60	87.94 70	83.14 58	88.68 55	87.98 53	93.34 41	70.74 73	79.78 149	82.37 58	88.32 99	89.44 155	71.34 99	90.61 74	89.64 61	92.40 70	89.79 54

MSP-MVS		88.51 42	91.36 41	85.19 39	90.63 36	92.01 4	95.29 22	77.52 27	90.48 27	80.21 76	90.21 70	96.08 42	76.38 60	88.30 98	91.42 41	91.12 91	91.01 45
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
IterMVS-SCA-FT		77.23 156	79.18 168	74.96 144	76.67 194	79.85 119	75.58 218	61.34 177	73.10 181	73.79 127	86.23 126	79.61 205	79.00 37	80.28 188	75.50 197	83.41 202	79.70 158

TSAR-MVS + MP.		89.67 24	92.25 28	86.65 25	91.53 18	90.98 17	96.15 13	73.30 56	87.88 53	81.83 66	92.92 31	95.15 78	82.23 18	93.58 34	92.25 33	94.87 29	93.01 25
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
OPM-MVS		89.82 21	92.24 29	86.99 22	90.86 33	89.35 39	95.07 27	75.91 43	91.16 16	86.87 30	91.07 60	97.29 18	79.13 35	93.32 35	91.99 37	94.12 40	91.49 41
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMMP_NAP		89.86 19	91.96 34	87.42 19	91.00 30	90.08 31	96.00 15	76.61 36	89.28 36	87.73 17	90.04 71	91.80 135	78.71 39	94.36 28	93.82 17	94.48 37	94.32 6

ambc			88.38 61		91.62 17	87.97 54	84.48 139		88.64 46	87.93 15	87.38 110	94.82 86	74.53 77	89.14 90	83.86 119	85.94 170	86.84 79

SPE-MVS-test		83.59 80	84.86 109	82.10 70	83.04 117	81.05 110	91.58 50	67.48 105	72.52 188	78.42 93	84.75 141	91.82 134	78.62 42	91.98 51	87.54 77	93.48 48	84.35 96

Effi-MVS+		82.33 97	83.87 134	80.52 89	84.51 95	81.32 104	87.53 97	68.05 98	74.94 171	79.67 80	82.37 157	92.31 124	72.21 91	85.06 131	86.91 82	91.18 87	84.20 98

new-patchmatchnet		62.59 233	73.79 209	49.53 249	76.98 186	53.57 246	53.46 259	54.64 220	85.43 82	28.81 258	91.94 42	96.41 34	25.28 255	76.80 203	53.66 253	57.99 252	58.69 244

pmmvs6		80.46 122	88.34 64	71.26 169	81.96 136	77.51 149	77.54 192	68.83 88	93.72 7	55.92 211	93.94 19	98.03 9	55.94 202	89.21 89	85.61 99	87.36 142	80.38 144

pmmvs5		68.91 210	74.35 205	62.56 225	67.45 235	66.78 223	71.70 227	51.47 235	67.17 210	56.25 208	82.41 155	88.59 164	47.21 238	73.21 226	74.23 201	81.30 210	68.03 217

Fast-Effi-MVS+		81.42 110	83.82 137	78.62 102	82.24 132	80.62 112	87.72 94	63.51 148	73.01 182	74.75 121	83.80 149	92.70 119	73.44 87	88.15 101	85.26 103	90.05 98	83.17 108

Anonymous20231211		79.37 138	85.78 91	71.89 163	82.87 121	79.66 122	78.77 187	63.93 144	83.36 100	59.39 198	90.54 65	94.66 92	56.46 199	87.38 104	84.12 115	89.92 101	80.74 139

pmmvs-eth3d		79.64 134	82.06 155	76.83 122	80.05 155	72.64 198	87.47 98	66.59 108	80.83 137	73.50 129	89.32 85	93.20 113	67.78 127	80.78 183	81.64 141	85.58 179	76.01 178

GG-mvs-BLEND		41.63 254	60.36 249	19.78 254	0.14 266	66.04 226	55.66 258	0.17 263	57.64 244	2.42 266	51.82 255	69.42 231	0.28 262	64.11 249	58.29 245	60.02 248	55.18 249

Anonymous20231206		67.28 218	73.41 211	60.12 232	76.45 196	63.61 234	74.21 221	56.52 206	76.35 162	42.23 248	75.81 205	90.47 150	41.51 245	74.52 213	69.97 219	69.83 237	63.17 232

MTAPA										89.37 9		94.85 84

MTMP										90.54 5		95.16 77

gm-plane-assit		71.56 201	69.99 217	73.39 154	84.43 96	73.21 189	90.42 70	51.36 236	84.08 95	76.00 110	91.30 55	37.09 265	59.01 190	73.65 223	70.24 218	79.09 218	60.37 240

train_agg		86.67 54	87.73 71	85.43 35	91.51 19	82.72 91	94.47 33	74.22 53	81.71 121	81.54 70	89.20 87	92.87 117	78.33 44	90.12 81	88.47 70	92.51 69	89.04 62

gg-mvs-nofinetune		72.68 195	75.21 203	69.73 182	81.48 141	69.04 214	70.48 232	76.67 35	86.92 63	67.80 170	88.06 102	64.67 234	42.12 244	77.60 198	73.65 204	79.81 212	66.57 219

SCA		68.54 213	67.52 226	69.73 182	67.79 232	75.04 173	76.96 197	68.94 87	66.41 213	67.86 169	74.03 213	60.96 237	65.55 150	68.99 237	65.67 231	71.30 233	61.54 239

MS-PatchMatch		71.18 204	73.99 208	67.89 202	77.16 184	71.76 202	77.18 195	56.38 207	67.35 209	55.04 216	74.63 211	75.70 221	62.38 167	76.62 205	75.97 194	79.22 217	75.90 180

Patchmatch-RL test							4.13 266

tmp_tt				13.54 256	16.73 262	6.42 263	8.49 265	2.36 260	28.69 260	27.44 259	18.40 260	13.51 267	3.70 259	33.23 257	36.26 257	22.54 263

canonicalmvs		81.22 114	86.04 87	75.60 133	83.17 115	83.18 87	80.29 171	65.82 121	85.97 75	67.98 166	77.74 185	91.51 138	65.17 153	88.62 93	86.15 93	91.17 88	89.09 60

anonymousdsp		85.62 61	90.53 47	79.88 93	64.64 246	76.35 160	96.28 12	53.53 228	85.63 78	81.59 69	92.81 32	97.71 12	86.88 2	94.56 25	92.83 24	96.35 6	93.84 9

v144192		83.43 84	84.97 106	81.63 76	83.43 110	81.23 106	89.42 81	66.04 117	81.45 129	86.40 34	91.46 50	95.70 60	75.76 67	82.14 164	80.23 153	88.74 122	82.57 117

v1921920		83.49 83	84.94 107	81.80 73	83.78 107	81.20 108	89.50 79	65.91 118	81.64 123	87.18 24	91.70 47	95.39 69	75.85 65	81.56 176	80.27 152	88.60 126	82.80 114

FC-MVSNet-train		79.20 142	86.29 82	70.94 173	84.06 99	77.67 147	85.68 122	64.11 138	82.90 106	52.22 232	92.57 37	93.69 105	49.52 233	88.30 98	86.93 81	90.03 99	81.95 124

UA-Net		89.02 33	91.44 40	86.20 28	94.88 1	89.84 35	94.76 29	77.45 28	85.41 83	74.79 119	88.83 94	88.90 162	78.67 41	96.06 7	95.45 4	96.66 3	95.58 2

v1192		83.61 79	85.23 101	81.72 74	84.05 100	82.15 97	89.54 78	66.20 112	81.38 131	86.76 32	91.79 46	96.03 45	74.88 75	81.81 170	80.92 145	88.91 120	82.50 119

FC-MVSNet-test		75.91 169	83.59 141	66.95 206	76.63 195	69.07 213	85.33 130	64.97 129	84.87 90	41.95 249	93.17 26	87.04 171	47.78 236	91.09 67	85.56 101	85.06 184	74.34 187

v1144		83.22 86	85.01 104	81.14 78	83.76 108	81.60 101	88.95 84	65.58 124	81.89 119	85.80 36	91.68 48	95.84 52	74.04 81	82.12 165	80.56 148	88.70 124	81.41 130

sosnet-low-res		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

HFP-MVS		90.32 13	92.37 22	87.94 13	91.46 21	90.91 18	95.69 17	79.49 12	89.94 34	83.50 50	89.06 88	94.44 97	81.68 22	94.17 30	94.19 13	95.81 17	93.87 7

v148		79.33 140	82.32 153	75.84 132	80.14 154	75.74 166	81.98 158	57.06 205	81.51 127	79.36 85	89.42 82	96.42 33	71.32 100	81.54 177	75.29 199	85.20 181	76.32 176

sosnet		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

v7n		87.11 51	90.46 49	83.19 57	85.22 86	83.69 81	90.03 75	68.20 97	91.01 19	86.71 33	94.80 10	98.46 4	77.69 49	91.10 66	85.98 95	91.30 85	88.19 70

DI_MVS_pp		77.64 154	79.64 165	75.31 137	79.87 157	76.89 157	81.55 162	63.64 146	76.21 164	72.03 140	85.59 133	82.97 194	66.63 141	79.27 192	77.78 174	88.14 134	78.76 167

HPM-MVS++		88.74 40	89.54 53	87.80 15	92.58 6	85.69 70	95.10 26	78.01 22	87.08 61	87.66 19	87.89 104	92.07 129	80.28 31	90.97 70	91.41 43	93.17 57	91.69 38

XVS					91.28 25	91.23 8	96.89 2			87.14 25		94.53 93				95.84 15

v1240		83.57 81	84.94 107	81.97 71	84.05 100	81.27 105	89.46 80	66.06 115	81.31 132	87.50 20	91.88 45	95.46 66	76.25 61	81.16 179	80.51 149	88.52 131	82.98 112

pm-mvs1		78.21 152	85.68 93	69.50 187	80.38 152	75.73 167	76.25 204	65.04 128	87.59 55	54.47 217	93.16 27	95.99 49	54.20 212	86.37 116	82.98 130	86.64 152	77.96 171

X-MVStestdata					91.28 25	91.23 8	96.89 2			87.14 25		94.53 93				95.84 15

X-MVS		89.36 28	90.73 46	87.77 16	91.50 20	91.23 8	96.76 4	78.88 17	87.29 58	87.14 25	78.98 174	94.53 93	76.47 58	95.25 19	94.28 11	95.85 14	93.55 16

v8		82.20 99	84.56 116	79.45 96	82.42 127	81.65 100	87.26 101	64.27 135	79.36 152	81.70 68	91.04 61	95.75 58	73.30 88	82.82 156	79.18 160	87.74 138	82.09 122

v10		83.17 88	85.22 102	80.78 82	83.26 113	82.99 89	88.66 87	66.49 110	79.24 153	83.60 48	91.46 50	95.47 65	74.12 79	82.60 160	80.66 146	88.53 130	84.11 100

v2v482		82.20 99	84.26 124	79.81 94	82.67 124	80.18 117	87.67 95	63.96 143	81.69 122	84.73 41	91.27 56	96.33 38	72.05 95	81.94 169	79.56 157	87.79 137	78.84 165

V42		79.59 136	83.59 141	74.93 145	69.61 226	77.05 156	86.59 112	55.84 208	78.42 157	77.29 102	89.84 77	95.08 80	74.12 79	83.05 152	80.11 155	86.12 165	81.59 129

SD-MVS		89.91 18	92.23 30	87.19 21	91.31 24	89.79 36	94.31 34	75.34 47	89.26 38	81.79 67	92.68 33	95.08 80	83.88 11	93.10 39	92.69 25	96.54 4	93.02 24
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
GA-MVS		75.01 177	76.39 189	73.39 154	78.37 173	75.66 168	80.03 173	58.40 198	70.51 197	75.85 112	83.24 150	76.14 219	63.75 159	77.28 201	76.62 189	83.97 196	75.30 185

MSLP-MVS++		86.29 58	89.10 56	83.01 59	85.71 83	89.79 36	87.04 107	74.39 51	85.17 85	78.92 88	77.59 187	93.57 107	82.60 17	93.23 36	91.88 39	89.42 111	92.46 31

APDe-MVS		89.85 20	92.91 10	86.29 26	90.47 38	91.34 7	96.04 14	76.41 39	91.11 17	78.50 92	93.44 23	95.82 55	81.55 23	93.16 37	91.90 38	94.77 32	93.58 15
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
TSAR-MVS + COLMAP		85.51 62	88.36 63	82.19 68	86.05 80	87.69 56	90.50 67	70.60 74	86.40 69	82.33 59	89.69 79	92.52 121	74.01 82	87.53 103	86.84 84	89.63 106	87.80 75

CVMVSNet		75.65 171	77.62 178	73.35 156	71.95 219	69.89 209	83.04 148	60.84 181	69.12 204	68.76 159	79.92 167	78.93 208	73.64 86	81.02 181	81.01 144	81.86 208	83.43 105

TSAR-MVS + ACMM		89.14 29	92.11 32	85.67 31	89.27 48	90.61 25	90.98 54	79.48 13	88.86 42	79.80 79	93.01 29	93.53 109	83.17 15	92.75 45	92.45 29	91.32 84	93.59 13

pmmvs4		75.92 168	77.48 180	74.10 149	78.21 176	70.94 204	84.06 140	64.78 130	75.13 170	68.47 163	84.12 145	83.32 191	64.74 157	75.93 210	79.14 161	84.31 194	73.77 195

EU-MVSNet		76.48 162	80.53 162	71.75 164	67.62 233	70.30 207	81.74 160	54.06 224	75.47 168	71.01 147	80.10 164	93.17 115	73.67 84	83.73 146	77.85 171	82.40 205	83.07 109

test-LLR		62.15 235	59.46 253	65.29 217	79.07 165	52.66 248	69.46 239	62.93 155	50.76 254	53.81 224	63.11 244	58.91 242	52.87 223	66.54 243	62.34 238	73.59 224	61.87 236

TESTMET0.1,1		57.21 245	59.46 253	54.60 243	50.95 256	52.66 248	69.46 239	26.91 256	50.76 254	53.81 224	63.11 244	58.91 242	52.87 223	66.54 243	62.34 238	73.59 224	61.87 236

test-mter		59.39 242	61.59 244	56.82 237	53.21 254	54.82 244	73.12 226	26.57 257	53.19 250	56.31 207	64.71 241	60.47 238	56.36 200	68.69 238	64.27 234	75.38 223	65.00 223

ACMMPR		91.30 4	92.88 11	89.46 4	91.92 11	91.61 5	96.60 5	79.46 14	90.08 31	88.53 13	89.54 80	95.57 61	84.25 7	95.24 20	94.27 12	95.97 11	93.85 8

testgi		68.20 214	76.05 195	59.04 233	79.99 156	67.32 221	81.16 164	51.78 234	84.91 89	39.36 254	73.42 217	95.19 75	32.79 253	76.54 207	70.40 217	69.14 239	64.55 226

test20.03		69.91 205	76.20 194	62.58 224	84.01 102	67.34 220	75.67 216	65.88 120	79.98 146	40.28 253	82.65 152	89.31 158	39.63 247	77.41 200	73.28 205	69.98 236	63.40 230

thres600view7		74.34 180	78.43 171	69.56 185	80.47 149	76.28 161	78.65 188	62.56 163	77.39 159	52.53 228	74.03 213	76.78 217	55.90 204	85.06 131	85.19 104	87.25 143	74.29 188

ADS-MVSNet		56.89 246	61.09 245	52.00 247	59.48 250	48.10 254	58.02 255	54.37 223	72.82 184	49.19 240	75.32 208	65.97 233	37.96 248	59.34 255	54.66 251	52.99 257	51.42 252

MP-MVS		90.84 6	91.95 35	89.55 3	92.92 4	90.90 19	96.56 6	79.60 11	86.83 65	88.75 12	89.00 89	94.38 99	84.01 9	94.94 24	94.34 10	95.45 24	93.24 23
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
testmvs		0.93 257	1.37 259	0.41 258	0.36 265	0.36 266	0.62 267	0.39 261	1.48 261	0.18 268	2.41 261	1.31 269	0.41 261	1.25 261	1.08 260	0.48 264	1.68 260

thres400		73.13 191	76.99 184	68.62 194	79.46 160	74.93 176	77.23 194	61.23 178	75.54 167	52.31 231	72.20 220	77.10 215	54.89 208	82.92 154	82.62 132	86.57 154	73.66 197

test123		1.06 256	1.41 258	0.64 257	0.39 264	0.48 265	0.52 268	0.25 262	1.11 262	1.37 267	2.01 262	1.98 268	0.87 260	1.43 260	1.27 259	0.46 265	1.62 261

thres200		72.41 198	76.00 196	68.21 197	78.28 174	76.28 161	74.94 219	62.56 163	72.14 192	51.35 236	69.59 236	76.51 218	54.89 208	85.06 131	80.51 149	87.25 143	71.92 205

test0.0.03 1		61.79 237	65.33 231	57.65 236	79.07 165	64.09 231	68.51 244	62.93 155	61.59 237	33.71 257	61.58 246	71.58 230	33.43 252	70.95 232	68.68 227	68.26 241	58.82 243

pmmvs3		62.72 231	68.71 221	55.74 239	50.74 257	57.10 241	70.05 234	28.82 255	61.57 238	57.39 205	71.19 227	85.73 181	53.96 214	73.36 225	69.43 226	73.47 226	62.55 234

EMVS		58.97 244	62.63 242	54.70 242	66.26 243	48.71 253	61.74 252	42.71 247	72.80 185	46.00 244	73.01 219	71.66 228	57.91 195	80.41 186	50.68 256	53.55 256	41.11 257

E-PMN		59.07 243	62.79 240	54.72 241	67.01 237	47.81 255	60.44 254	43.40 246	72.95 183	44.63 245	70.42 232	73.17 227	58.73 191	80.97 182	51.98 254	54.14 255	42.26 256

PGM-MVS		90.42 11	91.58 38	89.05 5	91.77 14	91.06 13	96.51 7	78.94 16	85.41 83	87.67 18	87.02 117	95.26 73	83.62 12	95.01 23	93.94 15	95.79 19	93.40 20

MCST-MVS		84.79 71	86.48 79	82.83 64	87.30 68	87.03 63	90.46 69	69.33 83	83.14 104	82.21 63	81.69 160	92.14 128	75.09 73	87.27 106	84.78 109	92.58 65	89.30 59

MVS_Test		76.72 160	79.40 167	73.60 150	78.85 168	74.99 175	79.91 175	61.56 173	69.67 200	72.44 136	85.98 130	90.78 147	63.50 163	78.30 196	75.74 195	85.33 180	80.31 149

MDA-MVSNet-bldmvs		76.51 161	82.87 149	69.09 189	50.71 258	74.72 180	84.05 141	60.27 185	81.62 124	71.16 146	88.21 101	91.58 136	69.62 114	92.78 44	77.48 179	78.75 219	73.69 196

CDPH-MVS		86.66 55	88.52 60	84.48 45	89.61 45	88.27 47	92.86 45	72.69 61	80.55 140	82.71 55	86.92 119	93.32 112	75.55 68	91.00 69	89.85 57	93.47 49	89.71 55

casdiffmvs		79.93 128	84.11 129	75.05 140	81.41 144	78.99 128	82.95 149	62.90 158	81.53 125	68.60 162	91.94 42	96.03 45	65.84 148	82.89 155	77.07 184	88.59 127	80.34 148
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
diffmvs		76.74 159	81.61 157	71.06 171	75.64 203	74.45 184	80.68 169	57.57 203	77.48 158	67.62 171	88.95 91	93.94 102	61.98 170	79.74 189	76.18 191	82.85 204	80.50 141
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline2		68.71 212	68.34 222	69.14 188	75.69 202	69.70 211	76.60 200	55.53 212	60.13 239	62.07 194	66.76 240	60.35 239	60.77 172	76.53 208	74.03 202	84.19 195	70.88 207

baseline1		69.62 207	73.55 210	65.02 220	78.95 167	70.39 206	71.38 230	62.03 169	70.97 196	47.95 241	78.47 181	68.19 232	47.77 237	79.65 191	76.94 188	82.05 206	70.27 209

PMMVS2		48.13 253	64.06 234	29.55 253	44.06 260	36.69 260	51.95 260	29.97 254	74.75 175	8.90 265	76.02 203	91.24 144	7.53 258	73.78 222	55.91 248	34.87 260	40.01 258

PM-MVS		80.42 124	83.63 140	76.67 124	78.04 177	72.37 200	87.14 103	60.18 186	80.13 144	71.75 142	86.12 128	93.92 103	77.08 54	86.56 114	85.12 105	85.83 173	81.18 134

PS-CasMVS		89.07 32	93.23 7	84.21 51	92.44 8	88.23 49	90.54 64	82.95 3	90.50 26	75.31 115	95.80 6	98.37 6	71.16 102	96.30 5	93.32 21	92.88 61	90.11 51

UniMVSNet_NR-MVSNet		84.62 72	88.00 68	80.68 86	88.18 60	83.83 78	87.06 105	76.47 38	81.46 128	70.49 149	93.24 25	95.56 62	68.13 124	90.43 75	88.47 70	93.78 45	83.02 110

PEN-MVS		88.86 39	92.92 9	84.11 53	92.92 4	88.05 52	90.83 57	82.67 5	91.04 18	74.83 118	95.97 3	98.47 3	70.38 110	95.70 13	92.43 30	93.05 60	88.78 66

TransMVSNet (Re)		79.05 143	86.66 77	70.18 180	83.32 112	75.99 163	77.54 192	63.98 142	90.68 25	55.84 212	94.80 10	96.06 43	53.73 217	86.27 117	83.22 127	86.65 151	79.61 159

DTE-MVSNet		88.99 35	92.77 12	84.59 43	93.31 2	88.10 50	90.96 55	83.09 2	91.38 14	76.21 107	96.03 2	98.04 8	70.78 108	95.65 14	92.32 32	93.18 56	87.84 74

DU-MVS		84.88 70	88.27 65	80.92 80	88.30 58	83.59 82	87.06 105	78.35 19	80.64 138	70.49 149	92.67 34	96.91 24	68.13 124	91.79 52	89.29 66	93.20 55	83.02 110

UniMVSNet (Re)		84.95 69	88.53 59	80.78 82	87.82 64	84.21 76	88.03 90	76.50 37	81.18 133	69.29 155	92.63 36	96.83 25	69.07 117	91.23 63	89.60 62	93.97 43	84.00 101

CP-MVSNet		88.71 41	92.63 15	84.13 52	92.39 9	88.09 51	90.47 68	82.86 4	88.79 44	75.16 116	94.87 9	97.68 13	71.05 104	96.16 6	93.18 23	92.85 62	89.64 56

WR-MVS_H		88.99 35	93.28 6	83.99 54	91.92 11	89.13 41	91.95 49	83.23 1	90.14 30	71.92 141	95.85 4	98.01 10	71.83 97	95.82 9	93.19 22	93.07 59	90.83 48

WR-MVS		89.79 23	93.66 5	85.27 37	91.32 23	88.27 47	93.49 40	79.86 10	92.75 9	75.37 114	96.86 1	98.38 5	75.10 72	95.93 8	94.07 14	96.46 5	89.39 58

NR-MVSNet		82.89 90	87.43 74	77.59 113	83.91 104	83.59 82	87.10 104	78.35 19	80.64 138	68.85 158	92.67 34	96.50 29	54.19 213	87.19 109	88.68 69	93.16 58	82.75 115

Baseline_NR-MVSNet		82.79 92	86.51 78	78.44 105	88.30 58	75.62 169	87.81 92	74.97 48	81.53 125	66.84 173	94.71 12	96.46 31	66.90 139	91.79 52	83.37 126	85.83 173	82.09 122

TranMVSNet+NR-MVSNet		85.23 67	89.38 54	80.39 91	88.78 54	83.77 79	87.40 99	76.75 34	85.47 81	68.99 157	95.18 8	97.55 16	67.13 137	91.61 57	89.13 67	93.26 54	82.95 113

TSAR-MVS + GP.		85.32 66	87.41 75	82.89 63	90.07 41	85.69 70	89.07 83	72.99 60	82.45 111	74.52 123	85.09 136	87.67 169	79.24 34	91.11 65	90.41 50	91.45 81	89.45 57

mPP-MVS					93.05 3							95.77 57

SixPastTwentyTwo		89.14 29	92.19 31	85.58 32	84.62 90	82.56 94	90.53 65	71.93 66	91.95 12	85.89 35	94.22 14	97.25 19	85.42 5	95.73 12	91.71 40	95.08 27	91.89 37

casdiffmvs_mvg		81.50 108	85.70 92	76.60 126	82.68 123	80.54 113	83.50 144	64.49 134	83.40 99	72.53 135	92.15 39	95.40 68	65.84 148	84.69 138	81.89 138	90.59 94	81.86 126
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
LGP-MVS_train		90.56 9	92.38 21	88.43 9	90.88 32	91.15 11	95.35 21	77.65 25	86.26 73	87.23 23	90.45 68	97.35 17	83.20 14	95.44 16	93.41 20	96.28 8	92.63 27

baseline		69.33 209	75.37 202	62.28 226	66.54 240	66.67 225	73.95 222	48.07 241	66.10 214	59.26 200	82.45 154	86.30 177	54.44 211	74.42 215	73.25 206	71.42 231	78.43 170

EPNet_dtu		71.90 200	73.03 212	70.59 175	78.28 174	61.64 236	82.44 153	64.12 137	63.26 228	69.74 152	71.47 223	82.41 196	51.89 229	78.83 194	78.01 168	77.07 220	75.60 183
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CHOSEN 1792x2688		68.80 211	71.09 214	66.13 212	69.11 228	68.89 215	78.98 186	54.68 219	61.63 236	56.69 206	71.56 222	78.39 210	67.69 128	72.13 227	72.01 210	69.63 238	73.02 203

EPNet		79.36 139	79.44 166	79.27 99	89.51 46	77.20 154	88.35 89	77.35 31	68.27 208	74.29 124	76.31 197	79.22 206	59.63 182	85.02 135	85.45 102	86.49 157	84.61 92
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
APD-MVS		89.14 29	91.25 43	86.67 24	91.73 15	91.02 15	95.50 20	77.74 24	84.04 97	79.47 84	91.48 49	94.85 84	81.14 25	92.94 41	92.20 35	94.47 38	92.24 33
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CNVR-MVS		86.93 52	88.98 57	84.54 44	90.11 40	87.41 59	93.23 43	73.47 55	86.31 71	82.25 61	82.96 151	92.15 127	76.04 63	91.69 55	90.69 47	92.17 74	91.64 40

NCCC		86.74 53	87.97 69	85.31 36	90.64 35	87.25 60	93.27 42	74.59 49	86.50 68	83.72 46	75.92 204	92.39 123	77.08 54	91.72 54	90.68 48	92.57 67	91.30 43

CP-MVS		91.09 5	92.33 25	89.65 2	92.16 10	90.41 28	96.46 10	80.38 8	88.26 47	89.17 10	87.00 118	96.34 37	83.95 10	95.77 11	94.72 7	95.81 17	93.78 10

NP-MVS									78.65 156

EG-PatchMatch MVS		84.35 73	87.55 72	80.62 87	86.38 76	82.24 96	86.75 110	64.02 141	84.24 93	78.17 97	89.38 84	95.03 82	78.78 38	89.95 83	86.33 90	89.59 107	85.65 88

tpm cat1		64.79 226	62.74 241	67.17 204	74.61 211	65.91 227	76.18 205	59.32 191	64.88 223	66.41 176	71.21 226	53.56 260	59.17 187	61.53 252	58.16 246	67.33 243	63.95 227

SteuartSystems-ACMMP		90.00 17	91.73 36	87.97 12	91.21 29	90.29 29	96.51 7	78.00 23	86.33 70	85.32 40	88.23 100	94.67 91	82.08 20	95.13 22	93.88 16	94.72 35	93.59 13
Skip Steuart: Steuart Systems R&D Blog.
CostFormer		66.81 221	66.94 227	66.67 207	72.79 217	68.25 216	79.55 183	55.57 211	65.52 218	62.77 190	76.98 193	60.09 240	56.73 198	65.69 245	62.35 237	72.59 227	69.71 212

CR-MVSNet		69.56 208	68.34 222	70.99 172	72.78 218	67.63 218	64.47 248	67.74 101	59.93 240	72.30 137	80.10 164	56.77 254	65.04 155	71.64 229	72.91 207	83.61 199	69.40 213

Patchmtry						56.88 243	64.47 248	67.74 101		72.30 137

PatchT		66.25 222	66.76 228	65.67 216	55.87 253	60.75 237	70.17 233	59.00 194	59.80 242	72.30 137	78.68 179	54.12 259	65.04 155	71.64 229	72.91 207	71.63 230	69.40 213

tpmrst		59.42 241	60.02 251	58.71 234	67.56 234	53.10 247	66.99 245	51.88 233	63.80 227	57.68 203	76.73 195	56.49 256	48.73 234	56.47 256	55.55 249	59.43 250	58.02 246

tpm		62.79 230	63.25 238	62.26 227	70.09 225	53.78 245	71.65 228	47.31 243	65.72 217	76.70 105	80.62 162	56.40 257	48.11 235	64.20 248	58.54 244	59.70 249	63.47 229

DELS-MVS		79.71 132	83.74 139	75.01 142	79.31 162	82.68 92	84.79 136	60.06 187	75.43 169	69.09 156	86.13 127	89.38 157	67.16 136	85.12 130	83.87 118	89.65 105	83.57 104
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
RPMNet		67.02 220	63.99 235	70.56 176	71.55 221	67.63 218	75.81 209	69.44 81	59.93 240	63.24 188	64.32 242	47.51 263	59.68 181	70.37 234	69.64 224	83.64 198	68.49 216

MVSTER		68.08 216	69.73 218	66.16 211	66.33 242	70.06 208	75.71 215	52.36 232	55.18 249	58.64 201	70.23 234	56.72 255	57.34 196	79.68 190	76.03 192	86.61 153	80.20 151

CPTT-MVS		89.63 25	90.52 48	88.59 6	90.95 31	90.74 22	95.71 16	79.13 15	87.70 54	85.68 38	80.05 166	95.74 59	84.77 6	94.28 29	92.68 26	95.28 26	92.45 32

GBi-Net		73.17 188	77.64 176	67.95 200	76.76 187	77.36 151	75.77 211	64.57 131	62.99 231	51.83 233	76.05 200	77.76 212	52.73 225	85.57 122	83.39 123	86.04 167	80.37 145

PVSNet_Blended_VisFu		83.00 89	84.16 128	81.65 75	82.17 133	86.01 67	88.03 90	71.23 70	76.05 166	79.54 83	83.88 147	83.44 190	77.49 52	87.38 104	84.93 107	91.41 82	87.40 78

PVSNet_BlendedMVS		76.45 163	78.12 172	74.49 146	76.76 187	78.46 133	79.65 178	63.26 153	65.42 220	73.15 131	75.05 209	88.96 160	66.51 143	82.73 158	77.66 175	87.61 139	78.60 168

PVSNet_Blended		76.45 163	78.12 172	74.49 146	76.76 187	78.46 133	79.65 178	63.26 153	65.42 220	73.15 131	75.05 209	88.96 160	66.51 143	82.73 158	77.66 175	87.61 139	78.60 168

FMVSNet5		56.37 248	60.14 250	51.98 248	60.83 249	59.58 238	66.85 246	42.37 248	52.68 252	41.33 251	47.09 257	54.68 258	35.28 250	73.88 221	70.77 216	65.24 246	62.26 235

test1		73.17 188	77.64 176	67.95 200	76.76 187	77.36 151	75.77 211	64.57 131	62.99 231	51.83 233	76.05 200	77.76 212	52.73 225	85.57 122	83.39 123	86.04 167	80.37 145

new_pmnet		52.29 251	63.16 239	39.61 252	58.89 251	44.70 257	48.78 261	34.73 253	65.88 216	17.85 262	73.42 217	80.00 203	23.06 256	67.00 241	62.28 240	54.36 254	48.81 253

FMVSNet3		71.40 203	75.20 204	66.97 205	75.00 210	76.59 158	74.29 220	64.57 131	62.99 231	51.83 233	76.05 200	77.76 212	51.49 230	76.58 206	77.03 186	84.62 193	79.43 161

dps		65.14 223	64.50 233	65.89 215	71.41 222	65.81 228	71.44 229	61.59 172	58.56 243	61.43 195	75.45 207	52.70 261	58.06 194	69.57 236	64.65 232	71.39 232	64.77 224

FMVSNet2		74.43 179	79.70 164	68.27 196	76.76 187	77.36 151	75.77 211	65.36 126	72.28 189	52.97 227	81.92 158	85.61 183	52.73 225	80.66 184	79.73 156	86.04 167	80.37 145

FMVSNet1		78.20 153	84.83 110	70.46 177	78.62 170	79.03 127	77.90 191	67.53 104	83.02 105	55.10 215	87.19 115	93.18 114	55.65 205	85.57 122	83.39 123	87.98 135	82.40 120

N_pmnet		54.95 250	65.90 229	42.18 250	66.37 241	43.86 258	57.92 256	39.79 250	79.54 151	17.24 263	86.31 124	87.91 168	25.44 254	64.68 247	51.76 255	46.33 258	47.23 254

UGNet		79.62 135	85.91 90	72.28 161	73.52 213	83.91 77	86.64 111	69.51 79	79.85 148	62.57 191	85.82 131	89.63 153	53.18 219	88.39 97	87.35 78	88.28 133	86.43 82
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
EC-MVSNet		83.70 78	84.77 113	82.46 67	87.47 67	82.79 90	85.50 124	72.00 65	69.81 199	77.66 100	85.02 138	89.63 153	78.14 45	90.40 76	87.56 76	94.00 41	88.16 71

MDTV_nov1_ep13_2view		72.96 193	75.59 198	69.88 181	71.15 223	64.86 229	82.31 154	54.45 222	76.30 163	78.32 94	86.52 122	91.58 136	61.35 171	76.80 203	66.83 230	71.70 228	66.26 220

MDTV_nov1_ep13		64.96 224	64.77 232	65.18 219	67.08 236	62.46 235	75.80 210	51.10 237	62.27 235	69.74 152	74.12 212	62.65 235	55.64 206	68.19 239	62.16 241	71.70 228	61.57 238

MIMVSNet1		73.40 184	81.85 156	63.55 221	72.90 216	64.37 230	84.58 138	53.60 227	90.84 21	53.92 223	87.75 105	96.10 41	45.31 240	85.37 127	79.32 159	70.98 235	69.18 215

MIMVSNet		63.02 228	69.02 220	56.01 238	68.20 230	59.26 239	70.01 235	53.79 226	71.56 194	41.26 252	71.38 224	82.38 197	36.38 249	71.43 231	67.32 229	66.45 245	59.83 242

IterMVS-LS		79.79 130	82.56 151	76.56 127	81.83 138	77.85 145	79.90 176	69.42 82	78.93 155	71.21 145	90.47 67	85.20 186	70.86 107	80.54 185	80.57 147	86.15 163	84.36 95
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CDS-MVSNet		73.07 192	77.02 182	68.46 195	81.62 140	72.89 192	79.56 182	70.78 72	69.56 201	52.52 229	77.37 190	81.12 201	42.60 242	84.20 143	83.93 116	83.65 197	70.07 211
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IterMVS		73.62 182	76.53 188	70.23 179	71.83 220	77.18 155	80.69 168	53.22 229	72.23 190	66.62 175	85.21 135	78.96 207	69.54 115	76.28 209	71.63 211	79.45 215	74.25 191
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MVS_111021_LR		83.20 87	85.33 99	80.73 85	82.88 120	78.23 137	89.61 77	65.23 127	82.08 117	81.19 71	85.31 134	92.04 132	75.22 70	89.50 85	85.90 97	90.24 96	84.23 97

HQP-MVS		85.02 68	86.41 81	83.40 55	89.19 49	86.59 64	91.28 52	71.60 69	82.79 107	83.48 51	78.65 180	93.54 108	72.55 90	86.49 115	85.89 98	92.28 73	90.95 47

QAPM		80.43 123	84.34 120	75.86 131	79.40 161	82.06 99	79.86 177	61.94 171	83.28 101	74.73 122	81.74 159	85.44 184	70.97 105	84.99 136	84.71 111	88.29 132	88.14 72

Vis-MVSNet		83.32 85	88.12 67	77.71 111	77.91 180	83.44 84	90.58 61	69.49 80	81.11 134	67.10 172	89.85 76	91.48 140	71.71 98	91.34 60	89.37 64	89.48 109	90.26 50
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MVS-HIRNet		59.74 240	58.74 256	60.92 231	57.74 252	45.81 256	56.02 257	58.69 197	55.69 247	65.17 179	70.86 228	71.66 228	56.75 197	61.11 253	53.74 252	71.17 234	52.28 251

HyFIR lowres test		73.29 185	74.14 207	72.30 160	73.08 215	78.33 135	83.12 146	62.41 166	63.81 226	62.13 193	76.67 196	78.50 209	71.09 103	74.13 220	77.47 180	81.98 207	70.10 210

EPMVS		56.62 247	59.77 252	52.94 246	62.41 247	50.55 251	60.66 253	52.83 230	65.15 222	41.80 250	77.46 189	57.28 248	42.68 241	59.81 254	54.82 250	57.23 253	53.35 250

TAMVS		63.02 228	69.30 219	55.70 240	70.12 224	56.89 242	69.63 237	45.13 245	70.23 198	38.00 255	77.79 183	75.15 224	42.60 242	74.48 214	72.81 209	68.70 240	57.75 247

IS_MVSNet		81.72 106	85.01 104	77.90 110	86.19 77	82.64 93	85.56 123	70.02 76	80.11 145	63.52 185	87.28 112	81.18 200	67.26 134	91.08 68	89.33 65	94.82 31	83.42 106

RPSCF		88.05 47	92.61 17	82.73 66	84.24 97	88.40 45	90.04 74	66.29 111	91.46 13	82.29 60	88.93 92	96.01 47	79.38 33	95.15 21	94.90 6	94.15 39	93.40 20

Vis-MVSNet (Re-imp)		76.15 166	80.84 160	70.68 174	83.66 109	74.80 178	81.66 161	69.59 77	80.48 141	46.94 243	87.44 109	80.63 202	53.14 220	86.87 110	84.56 112	89.12 114	71.12 206

MVS_111021_HR		83.95 76	86.10 85	81.44 77	84.62 90	80.29 116	90.51 66	68.05 98	84.07 96	80.38 74	84.74 142	91.37 142	74.23 78	90.37 77	87.25 79	90.86 93	84.59 93

CSCG		88.12 46	91.45 39	84.23 49	88.12 62	90.59 26	90.57 62	68.60 91	91.37 15	83.45 52	89.94 74	95.14 79	78.71 39	91.45 59	88.21 74	95.96 12	93.44 19

PatchMatch-RL		76.05 167	76.64 187	75.36 136	77.84 182	69.87 210	81.09 166	63.43 149	71.66 193	68.34 164	71.70 221	81.76 199	74.98 74	84.83 137	83.44 122	86.45 159	73.22 202

TDRefinement		93.16 1	95.57 1	90.36 1	88.79 53	93.57 1	97.27 1	78.23 21	95.55 1	93.00 1	93.98 18	96.01 47	87.53 1	97.69 1	96.81 1	97.33 1	95.34 4

USDC		81.39 112	83.07 146	79.43 97	81.48 141	78.95 129	82.62 152	66.17 113	87.45 57	90.73 4	82.40 156	93.65 106	66.57 142	83.63 148	77.97 169	89.00 117	77.45 173

EPP-MVSNet		82.76 93	86.47 80	78.45 104	86.00 81	84.47 75	85.39 128	68.42 93	84.17 94	62.97 189	89.26 86	76.84 216	72.13 94	92.56 48	90.40 51	95.76 20	87.56 77

PMMVS		61.98 236	65.61 230	57.74 235	45.03 259	51.76 250	69.54 238	35.05 252	55.49 248	55.32 214	68.23 237	78.39 210	58.09 193	70.21 235	71.56 212	83.42 201	63.66 228

ACMMP		90.63 8	92.40 20	88.56 8	91.24 28	91.60 6	96.49 9	77.53 26	87.89 52	86.87 30	87.24 113	96.46 31	82.87 16	95.59 15	94.50 8	96.35 6	93.51 18
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
CNLPA		85.50 63	88.58 58	81.91 72	84.55 92	87.52 58	90.89 56	63.56 147	88.18 48	84.06 44	83.85 148	91.34 143	76.46 59	91.27 61	89.00 68	91.96 77	88.88 64

PatchmatchNet		64.81 225	63.74 236	66.06 214	69.21 227	58.62 240	73.16 225	60.01 188	65.92 215	66.19 177	76.27 198	59.09 241	60.45 175	66.58 242	61.47 243	67.33 243	58.24 245
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
PHI-MVS		86.37 57	88.14 66	84.30 47	86.65 74	87.56 57	90.76 59	70.16 75	82.55 110	89.65 7	84.89 139	92.40 122	75.97 64	90.88 71	89.70 59	92.58 65	89.03 63

OMC-MVS		88.16 44	91.34 42	84.46 46	86.85 71	90.63 24	93.01 44	67.00 106	90.35 28	87.40 21	86.86 120	96.35 35	77.66 50	92.63 47	90.84 46	94.84 30	91.68 39

AdaColmap		84.15 74	85.14 103	83.00 60	89.08 50	87.14 62	90.56 63	70.90 71	82.40 114	80.41 73	73.82 215	84.69 188	75.19 71	91.58 58	89.90 56	91.87 78	86.48 81

DeepMVS_CX						17.78 262	20.40 264	6.69 258	31.41 259	9.80 264	38.61 258	34.88 266	33.78 251	28.41 259		23.59 262	45.77 255

TinyColmap		83.79 77	86.12 84	81.07 79	83.42 111	81.44 103	85.42 127	68.55 92	88.71 45	89.46 8	87.60 106	92.72 118	70.34 111	89.29 88	81.94 137	89.20 113	81.12 137

MAR-MVS		81.98 104	82.92 148	80.88 81	85.18 87	85.85 68	89.13 82	69.52 78	71.21 195	82.25 61	71.28 225	88.89 163	69.69 112	88.71 91	86.96 80	89.52 108	87.57 76
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
MSDG		81.39 112	84.23 126	78.09 107	82.40 128	82.47 95	85.31 131	60.91 180	79.73 150	80.26 75	86.30 125	88.27 167	69.67 113	87.20 108	84.98 106	89.97 100	80.67 140

LS3D		89.02 33	91.69 37	85.91 30	89.72 43	90.81 20	92.56 47	71.69 68	90.83 22	87.24 22	89.71 78	92.07 129	78.37 43	94.43 27	92.59 27	95.86 13	91.35 42

CLD-MVS		82.75 94	87.22 76	77.54 115	88.01 63	85.76 69	90.23 71	54.52 221	82.28 116	82.11 65	88.48 97	95.27 72	63.95 158	89.41 87	88.29 72	86.45 159	81.01 138
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
FPMVS		81.56 107	84.04 130	78.66 101	82.92 118	75.96 164	86.48 113	65.66 123	84.67 91	71.47 144	77.78 184	83.22 193	77.57 51	91.24 62	90.21 53	87.84 136	85.21 90

Gipuma		86.47 56	89.25 55	83.23 56	83.88 105	78.78 130	85.35 129	68.42 93	92.69 10	89.03 11	91.94 42	96.32 39	81.80 21	94.45 26	86.86 83	90.91 92	83.69 103
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015

High-resolution multi-view benchmark