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.

DeepC-MVS	78.47 2	84.81 26	86.03 30	83.37 19	89.29 33	90.38 13	88.61 28	76.50 1	86.25 23	77.22 26	75.12 42	80.28 46	77.59 22	88.39 10	88.17 6	91.02 8	93.66 19
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SED-MVS		88.85 2	91.59 3	85.67 2	90.54 15	92.29 3	91.71 3	76.40 2	92.41 3	83.24 2	92.50 4	90.64 4	81.10 3	89.53 3	88.02 7	91.00 10	95.73 3

DVP-MVS++		89.14 1	91.86 1	85.97 1	92.55 2	92.38 1	91.69 4	76.31 3	93.31 1	83.11 3	92.44 5	91.18 1	81.17 2	89.55 2	87.93 8	91.01 9	96.21 1

DVP-MVS		88.67 3	91.62 2	85.22 4	90.47 17	92.36 2	90.69 11	76.15 4	93.08 2	82.75 4	92.19 7	90.71 3	80.45 7	89.27 6	87.91 9	90.82 14	95.84 2
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
HPM-MVS++		87.09 10	88.92 14	84.95 6	92.61 1	87.91 41	90.23 17	76.06 5	88.85 13	81.20 9	87.33 14	87.93 13	79.47 10	88.59 9	88.23 5	90.15 36	93.60 21

DPE-MVS		88.63 4	91.29 4	85.53 3	90.87 8	92.20 4	91.98 2	76.00 6	90.55 9	82.09 6	93.85 2	90.75 2	81.25 1	88.62 8	87.59 15	90.96 11	95.48 4
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		88.09 6	90.84 5	84.88 8	90.00 24	91.80 6	91.63 5	75.80 7	91.99 4	81.23 8	92.54 3	89.18 7	80.89 4	87.99 16	87.91 9	89.70 47	94.51 7
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
SF-MVS		87.47 9	89.70 9	84.86 9	91.26 6	91.10 9	90.90 8	75.65 8	89.21 10	81.25 7	91.12 9	88.93 8	78.82 11	87.42 21	86.23 31	91.28 3	93.90 14

APD-MVS		86.84 13	88.91 15	84.41 11	90.66 11	90.10 14	90.78 9	75.64 9	87.38 17	78.72 20	90.68 11	86.82 18	80.15 8	87.13 26	86.45 30	90.51 23	93.83 15
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CNVR-MVS		86.36 15	88.19 18	84.23 12	91.33 5	89.84 16	90.34 13	75.56 10	87.36 18	78.97 19	81.19 30	86.76 19	78.74 12	89.30 5	88.58 2	90.45 29	94.33 11

NCCC		85.34 20	86.59 26	83.88 16	91.48 4	88.88 26	89.79 19	75.54 11	86.67 21	77.94 25	76.55 36	84.99 26	78.07 17	88.04 13	87.68 13	90.46 28	93.31 22

APDe-MVS		88.00 7	90.50 7	85.08 5	90.95 7	91.58 7	92.03 1	75.53 12	91.15 5	80.10 16	92.27 6	88.34 12	80.80 6	88.00 15	86.99 19	91.09 5	95.16 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SMA-MVS		87.56 8	90.17 8	84.52 10	91.71 3	90.57 10	90.77 10	75.19 13	90.67 8	80.50 14	86.59 18	88.86 9	78.09 16	89.92 1	89.41 1	90.84 13	95.19 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
TestfortrainingZip							91.33 6	75.06 14		80.35 15						91.03 6

ME-MVS		88.11 5	90.84 5	84.92 7	90.52 16	91.48 8	91.33 6	75.06 14	90.82 7	80.74 10	94.25 1	90.29 5	80.86 5	87.82 17	86.80 23	91.03 6	94.45 8

SD-MVS		86.96 11	89.45 10	84.05 15	90.13 20	89.23 24	89.77 20	74.59 16	89.17 11	80.70 11	89.93 12	89.67 6	78.47 13	87.57 20	86.79 24	90.67 20	93.76 17
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
SteuartSystems-ACMMP		85.99 17	88.31 17	83.27 21	90.73 10	89.84 16	90.27 16	74.31 17	84.56 30	75.88 33	87.32 15	85.04 25	77.31 24	89.01 7	88.46 3	91.14 4	93.96 13
Skip Steuart: Steuart Systems R&D Blog.
HFP-MVS		86.15 16	87.95 19	84.06 14	90.80 9	89.20 25	89.62 21	74.26 18	87.52 15	80.63 12	86.82 17	84.19 30	78.22 15	87.58 19	87.19 17	90.81 15	93.13 26

DeepC-MVS_fast	78.24 3	84.27 30	85.50 32	82.85 23	90.46 18	89.24 23	87.83 35	74.24 19	84.88 26	76.23 31	75.26 41	81.05 44	77.62 21	88.02 14	87.62 14	90.69 19	92.41 29
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MP-MVS		85.50 19	87.40 22	83.28 20	90.65 12	89.51 21	89.16 25	74.11 20	83.70 35	78.06 24	85.54 21	84.89 29	77.31 24	87.40 23	87.14 18	90.41 30	93.65 20
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ACMMP_NAP		86.52 14	89.01 12	83.62 17	90.28 19	90.09 15	90.32 15	74.05 21	88.32 14	79.74 17	87.04 16	85.59 24	76.97 29	89.35 4	88.44 4	90.35 32	94.27 12

ACMMPR		85.52 18	87.53 21	83.17 22	90.13 20	89.27 22	89.30 22	73.97 22	86.89 20	77.14 27	86.09 19	83.18 33	77.74 20	87.42 21	87.20 16	90.77 16	92.63 27

CP-MVS		84.74 27	86.43 28	82.77 24	89.48 31	88.13 40	88.64 27	73.93 23	84.92 25	76.77 29	81.94 28	83.50 32	77.29 26	86.92 31	86.49 29	90.49 24	93.14 25

MCST-MVS		85.13 23	86.62 25	83.39 18	90.55 14	89.82 18	89.29 23	73.89 24	84.38 31	76.03 32	79.01 33	85.90 22	78.47 13	87.81 18	86.11 34	92.11 1	93.29 23

X-MVS		83.23 34	85.20 34	80.92 35	89.71 28	88.68 28	88.21 34	73.60 25	82.57 41	71.81 48	77.07 34	81.92 38	71.72 59	86.98 29	86.86 21	90.47 25	92.36 30

SR-MVS					88.99 35			73.57 26				87.54 15

train_agg		84.86 25	87.21 24	82.11 27	90.59 13	85.47 57	89.81 18	73.55 27	83.95 32	73.30 41	89.84 13	87.23 16	75.61 34	86.47 34	85.46 39	89.78 42	92.06 33

TSAR-MVS + MP.		86.88 12	89.23 11	84.14 13	89.78 27	88.67 31	90.59 12	73.46 28	88.99 12	80.52 13	91.26 8	88.65 10	79.91 9	86.96 30	86.22 32	90.59 22	93.83 15
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
DPM-MVS		83.30 33	84.33 36	82.11 27	89.56 29	88.49 34	90.33 14	73.24 29	83.85 33	76.46 30	72.43 53	82.65 34	73.02 49	86.37 36	86.91 20	90.03 38	89.62 54

DeepPCF-MVS	79.04 1	85.30 21	88.93 13	81.06 33	88.77 37	90.48 12	85.46 48	73.08 30	90.97 6	73.77 40	84.81 23	85.95 21	77.43 23	88.22 11	87.73 11	87.85 99	94.34 10

OPM-MVS		79.68 48	79.28 63	80.15 39	87.99 41	86.77 47	88.52 30	72.72 31	64.55 120	67.65 77	67.87 86	74.33 68	74.31 40	86.37 36	85.25 41	89.73 46	89.81 52
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
TSAR-MVS + ACMM		85.10 24	88.81 16	80.77 36	89.55 30	88.53 33	88.59 29	72.55 32	87.39 16	71.90 45	90.95 10	87.55 14	74.57 37	87.08 28	86.54 28	87.47 109	93.67 18

EPNet		79.08 57	80.62 54	77.28 52	88.90 36	83.17 86	83.65 56	72.41 33	74.41 59	67.15 83	76.78 35	74.37 67	64.43 119	83.70 61	83.69 54	87.15 113	88.19 63
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP		83.42 32	85.27 33	81.26 32	88.47 39	88.49 34	88.31 33	72.09 34	83.42 36	72.77 43	82.65 25	78.22 51	75.18 35	86.24 39	85.76 36	90.74 17	92.13 32
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
AdaColmap		79.74 47	78.62 65	81.05 34	89.23 34	86.06 53	84.95 51	71.96 35	79.39 50	75.51 34	63.16 112	68.84 114	76.51 30	83.55 62	82.85 60	88.13 80	86.46 84

CDPH-MVS		82.64 35	85.03 35	79.86 40	89.41 32	88.31 37	88.32 32	71.84 36	80.11 47	67.47 78	82.09 27	81.44 42	71.85 57	85.89 42	86.15 33	90.24 34	91.25 39

PGM-MVS		84.42 29	86.29 29	82.23 26	90.04 23	88.82 27	89.23 24	71.74 37	82.82 40	74.61 36	84.41 24	82.09 36	77.03 28	87.13 26	86.73 26	90.73 18	92.06 33

3Dnovator+	75.73 4	82.40 36	82.76 40	81.97 29	88.02 40	89.67 19	86.60 40	71.48 38	81.28 45	78.18 23	64.78 106	77.96 53	77.13 27	87.32 24	86.83 22	90.41 30	91.48 37

CSCG		85.28 22	87.68 20	82.49 25	89.95 25	91.99 5	88.82 26	71.20 39	86.41 22	79.63 18	79.26 31	88.36 11	73.94 42	86.64 32	86.67 27	91.40 2	94.41 9

CPTT-MVS		81.77 39	83.10 39	80.21 38	85.93 51	86.45 50	87.72 37	70.98 40	82.54 42	71.53 51	74.23 46	81.49 41	76.31 32	82.85 72	81.87 68	88.79 67	92.26 31

ACMM	72.26 8	78.86 58	78.13 68	79.71 41	86.89 46	83.40 81	86.02 42	70.50 41	75.28 57	71.49 52	63.01 113	69.26 108	73.57 44	84.11 57	83.98 49	89.76 44	87.84 66
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HQP-MVS		81.19 41	83.27 38	78.76 45	87.40 43	85.45 58	86.95 38	70.47 42	81.31 44	66.91 84	79.24 32	76.63 55	71.67 61	84.43 55	83.78 53	89.19 58	92.05 35

TSAR-MVS + GP.		83.69 31	86.58 27	80.32 37	85.14 55	86.96 45	84.91 52	70.25 43	84.71 29	73.91 39	85.16 22	85.63 23	77.92 18	85.44 43	85.71 37	89.77 43	92.45 28

MSLP-MVS++		82.09 38	82.66 41	81.42 31	87.03 45	87.22 44	85.82 44	70.04 44	80.30 46	78.66 21	68.67 80	81.04 45	77.81 19	85.19 47	84.88 44	89.19 58	91.31 38

PCF-MVS	73.28 6	79.42 50	80.41 57	78.26 47	84.88 61	88.17 38	86.08 41	69.85 45	75.23 58	68.43 70	68.03 85	78.38 49	71.76 58	81.26 94	80.65 92	88.56 70	91.18 40
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TranMVSNet+NR-MVSNet		69.25 142	70.81 134	67.43 149	77.23 133	79.46 133	73.48 168	69.66 46	60.43 154	39.56 220	58.82 135	53.48 199	55.74 189	79.59 130	81.21 76	88.89 63	82.70 137

UniMVSNet_NR-MVSNet		70.59 126	72.19 125	68.72 134	77.72 128	80.72 119	73.81 163	69.65 47	61.99 140	43.23 212	60.54 124	57.50 165	58.57 161	79.56 132	81.07 78	89.34 52	83.97 127

LGP-MVS_train		79.83 44	81.22 50	78.22 49	86.28 50	85.36 60	86.76 39	69.59 48	77.34 52	65.14 91	75.68 38	70.79 98	71.37 64	84.60 51	84.01 48	90.18 35	90.74 43

ACMP	73.23 7	79.79 45	80.53 55	78.94 43	85.61 53	85.68 55	85.61 45	69.59 48	77.33 53	71.00 55	74.45 44	69.16 109	71.88 55	83.15 68	83.37 56	89.92 39	90.57 46
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PHI-MVS		82.36 37	85.89 31	78.24 48	86.40 49	89.52 20	85.52 46	69.52 50	82.38 43	65.67 87	81.35 29	82.36 35	73.07 48	87.31 25	86.76 25	89.24 54	91.56 36

MVS_111021_HR		80.13 43	81.46 47	78.58 46	85.77 52	85.17 61	83.45 57	69.28 51	74.08 63	70.31 60	74.31 45	75.26 64	73.13 47	86.46 35	85.15 42	89.53 49	89.81 52

DU-MVS		69.63 137	70.91 133	68.13 140	75.99 139	79.54 131	73.81 163	69.20 52	61.20 149	43.23 212	58.52 136	53.50 197	58.57 161	79.22 137	80.45 95	87.97 92	83.97 127

NR-MVSNet		68.79 147	70.56 135	66.71 165	77.48 131	79.54 131	73.52 167	69.20 52	61.20 149	39.76 219	58.52 136	50.11 223	51.37 211	80.26 121	80.71 89	88.97 61	83.59 133

MGCNet		84.63 28	87.25 23	81.59 30	88.58 38	90.50 11	87.82 36	69.16 54	83.82 34	78.46 22	82.32 26	84.97 27	74.56 38	88.16 12	87.72 12	90.94 12	93.24 24

LS3D		74.08 97	73.39 115	74.88 81	85.05 56	82.62 101	79.71 92	68.66 55	72.82 68	58.80 114	57.61 145	61.31 142	71.07 67	80.32 118	78.87 130	86.00 153	80.18 165

Baseline_NR-MVSNet		67.53 165	68.77 157	66.09 168	75.99 139	74.75 188	72.43 174	68.41 56	61.33 148	38.33 224	51.31 200	54.13 192	56.03 185	79.22 137	78.19 139	85.37 167	82.45 139

ACMH	65.37 14	70.71 125	70.00 140	71.54 102	82.51 68	82.47 102	77.78 114	68.13 57	56.19 182	46.06 200	54.30 164	51.20 217	68.68 92	80.66 110	80.72 85	86.07 147	84.45 126
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	66.54 13	71.36 121	70.09 139	72.85 94	82.59 67	81.13 114	78.56 106	68.04 58	61.55 145	52.52 160	51.50 199	54.14 190	68.56 93	78.85 142	79.50 115	86.82 125	83.94 129

UniMVSNet (Re)		69.53 138	71.90 128	66.76 163	76.42 137	80.93 115	72.59 173	68.03 59	61.75 144	41.68 217	58.34 142	57.23 167	53.27 207	79.53 133	80.62 93	88.57 69	84.90 119

CANet		81.62 40	83.41 37	79.53 42	87.06 44	88.59 32	85.47 47	67.96 60	76.59 55	74.05 37	74.69 43	81.98 37	72.98 50	86.14 40	85.47 38	89.68 48	90.42 47

DTE-MVSNet		61.85 213	64.96 197	58.22 217	74.32 162	74.39 191	61.01 233	67.85 61	51.76 214	21.91 251	53.28 178	48.17 228	37.74 236	72.22 195	76.44 169	86.52 138	78.49 177

test1111		71.56 117	73.44 114	69.38 129	81.16 81	82.95 96	74.99 142	67.68 62	66.89 102	46.33 197	55.19 159	60.91 143	57.99 167	84.59 52	82.70 62	88.12 81	80.85 156

PEN-MVS		62.96 198	65.77 185	59.70 211	73.98 166	75.45 179	63.39 226	67.61 63	52.49 207	25.49 243	53.39 176	49.12 227	40.85 231	71.94 198	77.26 158	86.86 124	80.72 158

test2506		71.72 115	72.95 119	70.29 116	81.49 77	83.27 82	75.74 130	67.59 64	68.19 96	49.81 173	61.15 119	49.73 225	58.82 159	84.76 49	82.94 58	88.27 74	80.63 159

ECVR-MVS		72.20 111	73.91 111	70.20 118	81.49 77	83.27 82	75.74 130	67.59 64	68.19 96	49.31 177	55.77 153	62.00 140	58.82 159	84.76 49	82.94 58	88.27 74	80.41 163

MAR-MVS		79.21 53	80.32 58	77.92 50	87.46 42	88.15 39	83.95 55	67.48 66	74.28 60	68.25 71	64.70 107	77.04 54	72.17 53	85.42 44	85.00 43	88.22 76	87.62 69
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
CP-MVSNet		62.68 203	65.49 188	59.40 214	71.84 183	75.34 180	62.87 228	67.04 67	52.64 206	27.19 241	53.38 177	48.15 229	41.40 229	71.26 201	75.68 175	86.07 147	82.00 144

PS-CasMVS		62.38 209	65.06 193	59.25 215	71.73 184	75.21 184	62.77 229	66.99 68	51.94 213	26.96 242	52.00 197	47.52 232	41.06 230	71.16 204	75.60 176	85.97 154	81.97 146

UniMVSNet_ETH3D		67.18 170	67.03 176	67.36 151	74.44 161	78.12 148	74.07 158	66.38 69	52.22 209	46.87 192	48.64 211	51.84 214	56.96 175	77.29 161	78.53 133	85.42 166	82.59 138

WR-MVS_H		61.83 215	65.87 183	57.12 221	71.72 185	76.87 164	61.45 232	66.19 70	51.97 212	22.92 248	53.13 183	52.30 212	33.80 241	71.03 206	75.00 182	86.65 134	80.78 157

PVSNet_Blended_VisFu		76.57 71	77.90 69	75.02 79	80.56 98	86.58 49	79.24 98	66.18 71	64.81 117	68.18 72	65.61 100	71.45 85	67.05 99	84.16 56	81.80 70	88.90 62	90.92 41

WR-MVS		63.03 195	67.40 174	57.92 218	75.14 153	77.60 160	60.56 234	66.10 72	54.11 201	23.88 244	53.94 172	53.58 195	34.50 239	73.93 186	77.71 146	87.35 111	80.94 155

PLC	68.99 11	75.68 86	75.31 101	76.12 62	82.94 65	81.26 112	79.94 88	66.10 72	77.15 54	66.86 85	59.13 134	68.53 116	73.73 43	80.38 117	79.04 125	87.13 117	81.68 149
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
QAPM		78.47 60	80.22 59	76.43 59	85.03 57	86.75 48	80.62 82	66.00 74	73.77 65	65.35 90	65.54 102	78.02 52	72.69 51	83.71 60	83.36 57	88.87 64	90.41 48

UA-Net		74.47 95	77.80 71	70.59 112	85.33 54	85.40 59	73.54 166	65.98 75	60.65 152	56.00 131	72.11 54	79.15 47	54.63 200	83.13 69	82.25 65	88.04 87	81.92 147

TSAR-MVS + COLMAP		78.34 61	81.64 46	74.48 88	80.13 106	85.01 62	81.73 71	65.93 76	84.75 28	61.68 104	85.79 20	66.27 127	71.39 63	82.91 71	80.78 83	86.01 152	85.98 87

3Dnovator	73.76 5	79.75 46	80.52 56	78.84 44	84.94 60	87.35 42	84.43 54	65.54 77	78.29 51	73.97 38	63.00 114	75.62 63	74.07 41	85.00 48	85.34 40	90.11 37	89.04 57

Anonymous202405211			72.16 127		80.85 87	81.85 104	76.88 126	65.40 78	62.89 135		46.35 222	67.99 120	62.05 134	81.15 97	80.38 96	85.97 154	84.50 124

viewdifsd2359ckpt09		77.36 65	78.39 67	76.16 60	79.98 107	85.78 54	82.78 59	65.29 79	70.87 78	68.68 69	68.99 73	70.81 97	71.70 60	82.68 74	81.86 69	88.56 70	87.71 68

MVS_111021_LR		78.13 62	79.85 61	76.13 61	81.12 83	81.50 107	80.28 85	65.25 80	76.09 56	71.32 53	76.49 37	72.87 75	72.21 52	82.79 73	81.29 75	86.59 136	87.91 65

FC-MVSNet-train		72.60 107	75.07 103	69.71 124	81.10 85	78.79 141	73.74 165	65.23 81	66.10 107	53.34 153	70.36 65	63.40 136	56.92 177	81.44 87	80.96 80	87.93 94	84.46 125

OMC-MVS		80.26 42	82.59 42	77.54 51	83.04 63	85.54 56	83.25 58	65.05 82	87.32 19	72.42 44	72.04 55	78.97 48	73.30 46	83.86 58	81.60 73	88.15 79	88.83 59

DELS-MVS		79.15 56	81.07 52	76.91 56	83.54 62	87.31 43	84.45 53	64.92 83	69.98 80	69.34 67	71.62 57	76.26 56	69.84 72	86.57 33	85.90 35	89.39 51	89.88 51
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
CNLPA		77.20 67	77.54 73	76.80 57	82.63 66	84.31 68	79.77 90	64.64 84	85.17 24	73.18 42	56.37 151	69.81 105	74.53 39	81.12 98	78.69 132	86.04 151	87.29 72

MSDG		71.52 118	69.87 141	73.44 92	82.21 73	79.35 134	79.52 94	64.59 85	66.15 106	61.87 103	53.21 181	56.09 175	65.85 117	78.94 141	78.50 134	86.60 135	76.85 195

TDRefinement		66.09 175	65.03 195	67.31 152	69.73 202	76.75 166	75.33 132	64.55 86	60.28 155	49.72 175	45.63 224	42.83 242	60.46 152	75.75 174	75.95 173	84.08 190	78.04 184

baseline1		70.10 133	72.17 126	67.69 145	79.74 109	76.80 165	73.91 159	64.38 87	62.74 136	48.30 181	64.94 104	64.08 133	54.17 202	81.46 85	78.92 128	85.66 159	76.22 199

PVSNet_BlendedMVS		76.21 80	77.52 75	74.69 83	79.46 113	83.79 75	77.50 117	64.34 88	69.88 81	71.88 46	68.54 81	70.42 100	67.05 99	83.48 63	79.63 108	87.89 97	86.87 77

PVSNet_Blended		76.21 80	77.52 75	74.69 83	79.46 113	83.79 75	77.50 117	64.34 88	69.88 81	71.88 46	68.54 81	70.42 100	67.05 99	83.48 63	79.63 108	87.89 97	86.87 77

casdiffmvs_mvg		77.79 63	79.55 62	75.73 63	81.56 75	84.70 64	82.12 60	64.26 90	74.27 61	67.93 74	70.83 62	74.66 66	69.19 89	83.33 67	81.94 67	89.29 53	87.14 75
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
casdiffseed414692147		75.68 86	75.69 100	75.67 68	81.52 76	84.14 69	81.64 73	64.19 91	68.92 90	67.29 81	61.24 118	67.12 123	71.02 68	81.17 95	80.83 82	88.36 72	86.40 85

ETV-MVS		77.32 66	78.81 64	75.58 70	82.24 72	83.64 79	79.98 86	64.02 92	69.64 87	63.90 98	70.89 61	69.94 104	73.41 45	85.39 46	83.91 52	89.92 39	88.31 62

dmvs_re		67.22 169	67.92 168	66.40 166	75.94 142	70.55 213	74.97 144	63.87 93	57.07 173	44.75 208	54.29 165	56.72 171	54.65 199	79.53 133	77.51 152	84.20 189	79.78 169

CDS-MVSNet		67.65 162	69.83 143	65.09 172	75.39 151	76.55 168	74.42 151	63.75 94	53.55 202	49.37 176	59.41 132	62.45 138	44.44 223	79.71 129	79.82 106	83.17 199	77.36 191
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SPE-MVS-test		78.79 59	80.72 53	76.53 58	81.11 84	83.88 73	79.69 93	63.72 95	73.80 64	69.95 64	75.40 40	76.17 57	74.85 36	84.50 54	82.78 61	89.87 41	88.54 61

EC-MVSNet		79.44 49	81.35 48	77.22 53	82.95 64	84.67 65	81.31 76	63.65 96	72.47 70	68.75 68	73.15 48	78.33 50	75.99 33	86.06 41	83.96 50	90.67 20	90.79 42

UGNet		72.78 105	77.67 72	67.07 158	71.65 187	83.24 84	75.20 135	63.62 97	64.93 116	56.72 127	71.82 56	73.30 70	49.02 215	81.02 99	80.70 90	86.22 142	88.67 60
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
IS_MVSNet		73.33 102	77.34 81	68.65 136	81.29 80	83.47 80	74.45 148	63.58 98	65.75 110	48.49 179	67.11 96	70.61 99	54.63 200	84.51 53	83.58 55	89.48 50	86.34 86

E5new		76.23 78	76.79 90	75.58 70	80.69 94	83.05 93	82.00 61	63.37 99	69.73 83	70.01 62	67.77 88	71.43 87	69.37 86	80.50 112	79.13 123	88.04 87	85.92 89

E5		76.23 78	76.79 90	75.58 70	80.69 94	83.05 93	82.00 61	63.37 99	69.73 83	70.01 62	67.77 88	71.43 87	69.37 86	80.50 112	79.13 123	88.04 87	85.92 89

EPNet_dtu		68.08 153	71.00 132	64.67 178	79.64 111	68.62 220	75.05 140	63.30 101	66.36 105	45.27 205	67.40 91	66.84 126	43.64 225	75.37 176	74.98 183	81.15 206	77.44 190
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
E4		76.24 77	76.77 92	75.61 69	80.69 94	83.05 93	81.98 64	63.25 102	69.47 88	70.06 61	67.40 91	71.46 84	69.59 79	80.73 104	79.37 118	88.10 85	85.95 88

CS-MVS		79.22 52	81.11 51	77.01 55	81.36 79	84.03 70	80.35 83	63.25 102	73.43 67	70.37 59	74.10 47	76.03 60	76.40 31	86.32 38	83.95 51	90.34 33	89.93 50

casdiffmvs		76.76 68	78.46 66	74.77 82	80.32 102	83.73 78	80.65 81	63.24 104	73.58 66	66.11 86	69.39 72	74.09 69	69.49 84	82.52 76	79.35 120	88.84 66	86.52 83
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
E3new		76.51 73	77.22 83	75.69 66	80.74 90	83.07 89	81.99 63	63.23 105	71.18 76	70.52 58	68.77 76	71.75 82	69.61 77	80.73 104	79.18 121	88.03 90	85.85 92

E3		76.51 73	77.21 84	75.69 66	80.74 90	83.06 92	81.98 64	63.22 106	71.17 77	70.55 57	68.77 76	71.76 81	69.61 77	80.73 104	79.18 121	88.03 90	85.84 94

viewcassd2359sk11		76.64 70	77.43 78	75.72 65	80.75 89	83.07 89	81.95 66	63.20 107	72.02 74	70.88 56	69.50 70	72.02 80	69.58 80	80.68 109	78.98 127	87.97 92	85.74 95

sasdasda		79.16 54	82.37 43	75.41 75	82.33 70	86.38 51	80.80 79	63.18 108	82.90 38	67.34 79	72.79 50	76.07 58	69.62 75	83.46 65	84.41 46	89.20 56	90.60 44

canonicalmvs		79.16 54	82.37 43	75.41 75	82.33 70	86.38 51	80.80 79	63.18 108	82.90 38	67.34 79	72.79 50	76.07 58	69.62 75	83.46 65	84.41 46	89.20 56	90.60 44

E2		76.70 69	77.54 73	75.73 63	80.76 88	83.07 89	81.91 67	63.15 110	72.42 71	71.09 54	70.03 67	72.22 78	69.53 81	80.57 111	78.80 131	87.91 95	85.64 100

TAPA-MVS	71.42 9	77.69 64	80.05 60	74.94 80	80.68 97	84.52 67	81.36 75	63.14 111	84.77 27	64.82 93	68.72 78	75.91 61	71.86 56	81.62 80	79.55 114	87.80 101	85.24 112
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Effi-MVS+		75.28 90	76.20 96	74.20 89	81.15 82	83.24 84	81.11 77	63.13 112	66.37 104	60.27 110	64.30 110	68.88 113	70.93 69	81.56 82	81.69 71	88.61 68	87.35 70

E6new		76.06 83	76.54 94	75.51 73	80.71 92	83.10 87	81.74 69	63.03 113	68.89 91	69.71 65	66.73 97	70.84 95	69.76 73	80.88 102	79.61 110	88.11 83	85.72 97

E6		76.06 83	76.54 94	75.51 73	80.71 92	83.10 87	81.74 69	63.03 113	68.89 91	69.71 65	66.73 97	70.84 95	69.76 73	80.88 102	79.61 110	88.11 83	85.72 97

Vis-MVSNet (Re-imp)		67.83 158	73.52 113	61.19 203	78.37 121	76.72 167	66.80 210	62.96 115	65.50 113	34.17 231	67.19 95	69.68 106	39.20 234	79.39 136	79.44 117	85.68 158	76.73 197

COLMAP_ROB	62.73 15	67.66 161	66.76 179	68.70 135	80.49 100	77.98 153	75.29 134	62.95 116	63.62 129	49.96 171	47.32 221	50.72 220	58.57 161	76.87 167	75.50 180	84.94 182	75.33 210
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Anonymous20231211		71.90 113	72.48 124	71.21 103	80.14 104	81.53 106	76.92 122	62.89 117	64.46 122	58.94 112	43.80 226	70.98 93	62.22 131	80.70 108	80.19 100	86.18 143	85.73 96

tfpn200view9		68.11 152	68.72 158	67.40 150	77.83 126	78.93 137	74.28 153	62.81 118	56.64 176	46.82 193	52.65 192	53.47 200	56.59 178	80.41 114	78.43 135	86.11 144	80.52 161

viewdifsd2359ckpt13		76.26 76	77.31 82	75.03 78	80.14 104	83.77 77	81.58 74	62.80 119	70.34 79	67.83 76	68.06 84	70.93 94	70.20 70	81.46 85	79.88 103	87.63 106	86.71 81

thres600view7		67.68 160	68.43 162	66.80 162	77.90 123	78.86 139	73.84 161	62.75 120	56.07 183	44.70 210	52.85 187	52.81 207	55.58 190	80.41 114	77.77 145	86.05 149	80.28 164

thres200		67.98 154	68.55 161	67.30 153	77.89 125	78.86 139	74.18 157	62.75 120	56.35 179	46.48 196	52.98 185	53.54 196	56.46 179	80.41 114	77.97 142	86.05 149	79.78 169

thres400		67.95 155	68.62 160	67.17 155	77.90 123	78.59 144	74.27 154	62.72 122	56.34 180	45.77 203	53.00 184	53.35 203	56.46 179	80.21 123	78.43 135	85.91 156	80.43 162

GBi-Net		70.78 123	73.37 116	67.76 141	72.95 175	78.00 150	75.15 136	62.72 122	64.13 123	51.44 162	58.37 139	69.02 110	57.59 169	81.33 90	80.72 85	86.70 130	82.02 141

test1		70.78 123	73.37 116	67.76 141	72.95 175	78.00 150	75.15 136	62.72 122	64.13 123	51.44 162	58.37 139	69.02 110	57.59 169	81.33 90	80.72 85	86.70 130	82.02 141

FMVSNet3		70.49 127	72.90 121	67.67 146	72.88 178	77.98 153	74.96 145	62.72 122	64.13 123	51.44 162	58.37 139	69.02 110	57.43 172	79.43 135	79.57 113	86.59 136	81.81 148

FMVSNet2		70.39 129	72.67 123	67.72 144	72.95 175	78.00 150	75.15 136	62.69 126	63.29 131	51.25 166	55.64 154	68.49 117	57.59 169	80.91 101	80.35 97	86.70 130	82.02 141

EPP-MVSNet		74.00 98	77.41 79	70.02 121	80.53 99	83.91 72	74.99 142	62.68 127	65.06 115	49.77 174	68.68 79	72.09 79	63.06 127	82.49 77	80.73 84	89.12 60	88.91 58

TransMVSNet (Re)		64.74 186	65.66 186	63.66 188	77.40 132	75.33 181	69.86 187	62.67 128	47.63 231	41.21 218	50.01 205	52.33 210	45.31 221	79.57 131	77.69 147	85.49 163	77.07 194

DI_MVS_pp		75.13 91	76.12 97	73.96 90	78.18 122	81.55 105	80.97 78	62.54 129	68.59 94	65.13 92	61.43 117	74.81 65	69.32 88	81.01 100	79.59 112	87.64 105	85.89 91

thres100view900		67.60 164	68.02 166	67.12 157	77.83 126	77.75 157	73.90 160	62.52 130	56.64 176	46.82 193	52.65 192	53.47 200	55.92 186	78.77 143	77.62 148	85.72 157	79.23 173

tfpnnormal		64.27 189	63.64 210	65.02 173	75.84 146	75.61 177	71.24 183	62.52 130	47.79 230	42.97 214	42.65 229	44.49 239	52.66 209	78.77 143	76.86 162	84.88 183	79.29 172

ET-MVSNet_ETH3D		72.46 110	74.19 107	70.44 114	62.50 227	81.17 113	79.90 89	62.46 132	64.52 121	57.52 123	71.49 59	59.15 152	72.08 54	78.61 145	81.11 77	88.16 78	83.29 135

FMVSNet1		68.84 146	70.47 137	66.94 160	71.35 192	77.68 158	74.71 146	62.35 133	56.93 174	49.94 172	50.01 205	64.59 131	57.07 174	81.33 90	80.72 85	86.25 141	82.00 144

EIA-MVS		75.64 88	76.60 93	74.53 86	82.43 69	83.84 74	78.32 110	62.28 134	65.96 108	63.28 102	68.95 74	67.54 121	71.61 62	82.55 75	81.63 72	89.24 54	85.72 97

MGCFI-Net		76.55 72	81.71 45	70.52 113	81.71 74	84.62 66	75.02 141	62.17 135	82.91 37	53.58 152	72.78 52	75.87 62	61.75 142	82.96 70	82.61 63	88.86 65	90.26 49

OpenMVS	70.44 10	76.15 82	76.82 89	75.37 77	85.01 58	84.79 63	78.99 102	62.07 136	71.27 75	67.88 75	57.91 144	72.36 77	70.15 71	82.23 78	81.41 74	88.12 81	87.78 67

test-LLR		64.42 187	64.36 202	64.49 179	75.02 154	63.93 235	66.61 212	61.96 137	54.41 197	47.77 188	57.46 146	60.25 145	55.20 193	70.80 208	69.33 206	80.40 210	74.38 214

test0.0.03 1		58.80 224	61.58 225	55.56 227	75.02 154	68.45 221	59.58 238	61.96 137	52.74 205	29.57 236	49.75 209	54.56 188	31.46 243	71.19 202	69.77 204	75.75 228	64.57 238

PatchMatch-RL		67.78 159	66.65 180	69.10 131	73.01 174	72.69 203	68.49 200	61.85 139	62.93 134	60.20 111	56.83 150	50.42 221	69.52 83	75.62 175	74.46 186	81.51 203	73.62 219

IB-MVS	66.94 12	71.21 122	71.66 130	70.68 107	79.18 115	82.83 100	72.61 172	61.77 140	59.66 157	63.44 101	53.26 179	59.65 150	59.16 158	76.78 169	82.11 66	87.90 96	87.33 71
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
Vis-MVSNet		72.77 106	77.20 85	67.59 148	74.19 163	84.01 71	76.61 129	61.69 141	60.62 153	50.61 169	70.25 66	71.31 90	55.57 191	83.85 59	82.28 64	86.90 122	88.08 64
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
DCV-MVSNet		73.65 100	75.78 99	71.16 104	80.19 103	79.27 135	77.45 119	61.68 142	66.73 103	58.72 115	65.31 103	69.96 103	62.19 132	81.29 93	80.97 79	86.74 129	86.91 76

Effi-MVS+-dtu		71.82 114	71.86 129	71.78 101	78.77 117	80.47 122	78.55 107	61.67 143	60.68 151	55.49 132	58.48 138	65.48 129	68.85 91	76.92 166	75.55 179	87.35 111	85.46 106

usedtu_dtu_shiyan1		66.26 174	68.15 165	64.06 183	67.01 211	76.52 169	70.61 185	61.10 144	61.86 142	44.86 206	49.77 208	56.69 172	53.97 203	77.58 157	77.88 143	86.80 127	76.78 196

test20.03		53.93 237	56.28 238	51.19 236	72.19 182	65.83 228	53.20 247	61.08 145	42.74 240	22.08 249	37.07 239	45.76 237	24.29 251	70.44 212	69.04 208	74.31 236	63.05 242

viewmacassd2359aftdt		75.85 85	77.01 87	74.49 87	79.69 110	82.87 99	81.77 68	61.06 146	69.37 89	67.26 82	66.73 97	71.63 83	69.48 85	81.51 84	80.20 98	87.69 103	86.77 80

GeoE		74.23 96	74.84 105	73.52 91	80.42 101	81.46 108	79.77 90	61.06 146	67.23 101	63.67 99	59.56 131	68.74 115	67.90 95	80.25 122	79.37 118	88.31 73	87.26 73

viewmanbaseed2359cas		76.36 75	77.87 70	74.60 85	79.81 108	82.88 98	81.69 72	61.02 148	72.14 73	67.97 73	69.61 69	72.45 76	69.53 81	81.53 83	79.83 105	87.57 107	86.65 82

pmmvs4		67.89 156	67.39 175	68.48 137	71.60 189	73.57 200	74.45 148	60.98 149	64.65 118	57.97 121	54.95 161	51.73 215	61.88 138	73.78 187	75.11 181	83.99 192	77.91 185

CLD-MVS		79.35 51	81.23 49	77.16 54	85.01 58	86.92 46	85.87 43	60.89 150	80.07 49	75.35 35	72.96 49	73.21 73	68.43 94	85.41 45	84.63 45	87.41 110	85.44 107
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
pm-mvs1		65.62 176	67.42 173	63.53 189	73.66 171	76.39 170	69.66 188	60.87 151	49.73 225	43.97 211	51.24 201	57.00 170	48.16 216	79.89 127	77.84 144	84.85 186	79.82 168

v1144		69.93 135	69.36 149	70.61 109	74.89 156	80.93 115	79.11 100	60.64 152	55.97 184	55.31 134	53.85 173	54.14 190	66.54 110	78.10 150	77.44 154	87.14 116	85.09 114

v2v482		70.05 134	69.46 148	70.74 105	74.62 159	80.32 126	79.00 101	60.62 153	57.41 170	56.89 126	55.43 158	55.14 181	66.39 114	77.25 162	77.14 159	86.90 122	83.57 134

v144192		69.34 141	68.68 159	70.12 119	74.06 164	80.54 120	78.08 113	60.54 154	54.99 194	54.13 139	52.92 186	52.80 208	66.73 106	77.13 164	76.72 164	87.15 113	85.63 101

v1192		69.50 139	68.83 155	70.29 116	74.49 160	80.92 117	78.55 107	60.54 154	55.04 192	54.21 137	52.79 188	52.33 210	66.92 103	77.88 154	77.35 157	87.04 120	85.51 104

IterMVS-LS		71.69 116	72.82 122	70.37 115	77.54 130	76.34 171	75.13 139	60.46 156	61.53 146	57.57 122	64.89 105	67.33 122	66.04 116	77.09 165	77.37 156	85.48 164	85.18 113
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
viewmambaseed2359dif		73.61 101	75.14 102	71.84 100	75.87 143	79.69 130	78.99 102	60.42 157	68.19 96	64.15 96	67.85 87	71.20 92	66.55 108	77.41 160	75.78 174	85.04 177	85.85 92

USDC		67.36 167	67.90 169	66.74 164	71.72 185	75.23 183	71.58 180	60.28 158	67.45 100	50.54 170	60.93 120	45.20 238	62.08 133	76.56 171	74.50 185	84.25 188	75.38 209

v1921920		69.03 144	68.32 163	69.86 122	74.03 165	80.37 124	77.55 115	60.25 159	54.62 196	53.59 151	52.36 195	51.50 216	66.75 105	77.17 163	76.69 166	86.96 121	85.56 102

HyFIR lowres test		69.47 140	68.94 154	70.09 120	76.77 136	82.93 97	76.63 128	60.17 160	59.00 160	54.03 140	40.54 236	65.23 130	67.89 96	76.54 172	78.30 138	85.03 178	80.07 166

diffmvs		74.86 93	77.37 80	71.93 98	75.62 148	80.35 125	79.42 97	60.15 161	72.81 69	64.63 94	71.51 58	73.11 74	66.53 111	79.02 140	77.98 141	85.25 174	86.83 79
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_Test		75.37 89	77.13 86	73.31 93	79.07 116	81.32 110	79.98 86	60.12 162	69.72 85	64.11 97	70.53 64	73.22 72	68.90 90	80.14 124	79.48 116	87.67 104	85.50 105

CHOSEN 1792x2688		69.20 143	69.26 150	69.13 130	76.86 135	78.93 137	77.27 120	60.12 162	61.86 142	54.42 136	42.54 230	61.61 141	66.91 104	78.55 146	78.14 140	79.23 214	83.23 136

diffmvs_AUTHOR		74.91 92	77.47 77	71.92 99	75.60 150	80.50 121	79.48 96	60.02 164	72.41 72	64.39 95	70.63 63	73.27 71	66.55 108	79.97 126	78.34 137	85.46 165	87.17 74

v1240		68.64 149	67.89 170	69.51 127	73.89 167	80.26 128	76.73 127	59.97 165	53.43 204	53.08 155	51.82 198	50.84 219	66.62 107	76.79 168	76.77 163	86.78 128	85.34 110

v10		70.22 131	69.76 144	70.74 105	74.79 157	80.30 127	79.22 99	59.81 166	57.71 168	56.58 129	54.22 170	55.31 179	66.95 102	78.28 148	77.47 153	87.12 119	85.07 115

TinyColmap		62.84 199	61.03 227	64.96 175	69.61 203	71.69 207	68.48 201	59.76 167	55.41 187	47.69 190	47.33 220	34.20 253	62.76 129	74.52 182	72.59 196	81.44 204	71.47 222

EG-PatchMatch MVS		67.24 168	66.94 177	67.60 147	78.73 118	81.35 109	73.28 170	59.49 168	46.89 234	51.42 165	43.65 227	53.49 198	55.50 192	81.38 89	80.66 91	87.15 113	81.17 153

pmmvs-eth3d		63.52 194	62.44 221	64.77 177	66.82 215	70.12 214	69.41 190	59.48 169	54.34 200	52.71 156	46.24 223	44.35 240	56.93 176	72.37 191	73.77 189	83.30 197	75.91 201

pmmvs6		62.41 207	62.88 215	61.87 199	71.38 191	75.18 185	67.76 203	59.45 170	41.64 242	42.52 216	37.33 238	52.91 206	46.87 218	77.67 156	76.26 171	83.23 198	79.18 174

FE-MVSNET2		58.78 225	60.53 229	56.73 223	57.08 244	72.23 204	62.74 230	59.35 171	47.17 232	30.52 234	34.62 243	43.62 241	44.57 222	75.24 177	76.57 168	86.11 144	74.30 216

v8		70.23 130	69.86 142	70.67 108	74.69 158	79.82 129	78.79 105	59.18 172	58.80 161	58.20 120	55.00 160	57.33 166	66.31 115	77.51 158	76.71 165	86.82 125	83.88 130

thisisatest0530		71.48 119	73.01 118	69.70 125	73.83 168	78.62 143	74.53 147	59.12 173	64.13 123	58.63 116	64.60 108	58.63 155	64.27 120	80.28 120	80.17 101	87.82 100	84.64 123

tttt0517		71.41 120	72.95 119	69.60 126	73.70 170	78.70 142	74.42 151	59.12 173	63.89 127	58.35 119	64.56 109	58.39 162	64.27 120	80.29 119	80.17 101	87.74 102	84.69 122

LTVRE_ROB	59.44 16	61.82 216	62.64 218	60.87 205	72.83 179	77.19 162	64.37 222	58.97 175	33.56 252	28.00 240	52.59 194	42.21 243	63.93 123	74.52 182	76.28 170	77.15 221	82.13 140
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
MS-PatchMatch		70.17 132	70.49 136	69.79 123	80.98 86	77.97 155	77.51 116	58.95 176	62.33 138	55.22 135	53.14 182	65.90 128	62.03 135	79.08 139	77.11 160	84.08 190	77.91 185

baseline2		69.69 136	70.27 138	69.01 132	75.72 147	77.13 163	73.82 162	58.94 177	61.35 147	57.09 125	61.68 116	57.17 168	61.99 136	78.10 150	76.58 167	86.48 139	79.85 167

v7n		67.05 171	66.94 177	67.17 155	72.35 180	78.97 136	73.26 171	58.88 178	51.16 219	50.90 167	48.21 213	50.11 223	60.96 147	77.70 155	77.38 155	86.68 133	85.05 116

Fast-Effi-MVS+		73.11 104	73.66 112	72.48 96	77.72 128	80.88 118	78.55 107	58.83 179	65.19 114	60.36 109	59.98 128	62.42 139	71.22 66	81.66 79	80.61 94	88.20 77	84.88 120

FC-MVSNet-test		56.90 230	65.20 191	47.21 242	66.98 212	63.20 240	49.11 252	58.60 180	59.38 159	11.50 259	65.60 101	56.68 173	24.66 250	71.17 203	71.36 201	72.38 241	69.02 230

viewdifsd2359ckpt07		74.55 94	76.09 98	72.75 95	79.51 112	81.32 110	80.29 84	58.44 181	68.61 93	65.63 88	68.17 83	71.24 91	67.64 97	80.13 125	77.62 148	84.96 181	85.56 102

GA-MVS		68.14 151	69.17 152	66.93 161	73.77 169	78.50 147	74.45 148	58.28 182	55.11 191	48.44 180	60.08 126	53.99 193	61.50 144	78.43 147	77.57 150	85.13 175	80.54 160

viewdifsd2359ckpt11		72.49 108	74.10 108	70.61 109	75.87 143	78.53 145	76.92 122	58.16 183	65.69 111	61.34 107	67.21 93	68.35 118	66.51 112	77.91 152	75.60 176	84.86 184	85.43 108

viewmsd2359difaftdt		72.49 108	74.10 108	70.61 109	75.87 143	78.53 145	76.92 122	58.16 183	65.69 111	61.33 108	67.21 93	68.34 119	66.51 112	77.91 152	75.60 176	84.86 184	85.42 109

WB-MVS		40.01 248	45.06 249	34.13 248	58.84 241	53.28 252	28.60 258	58.10 185	32.93 254	4.65 264	40.92 232	28.33 258	7.26 257	58.86 249	56.09 247	47.36 256	44.98 252

MDA-MVSNet-bldmvs		53.37 238	53.01 242	53.79 233	43.67 255	67.95 222	59.69 237	57.92 186	43.69 238	32.41 233	41.47 231	27.89 259	52.38 210	56.97 251	65.99 235	76.68 224	67.13 233

Anonymous20231206		56.36 231	57.80 235	54.67 230	70.08 199	66.39 227	60.46 235	57.54 187	49.50 227	29.30 238	33.86 244	46.64 233	35.18 238	70.44 212	68.88 211	75.47 231	68.88 231

SixPastTwentyTwo		61.84 214	62.45 220	61.12 204	69.20 206	72.20 205	62.03 231	57.40 188	46.54 235	38.03 226	57.14 149	41.72 244	58.12 165	69.67 223	71.58 199	81.94 201	78.30 178

thisisatest0515		67.40 166	68.78 156	65.80 169	70.02 200	75.24 182	69.36 191	57.37 189	54.94 195	53.67 150	55.53 157	54.85 186	58.00 166	78.19 149	78.91 129	86.39 140	83.78 131

gbinet_0.2-2-1-0.02		62.72 202	63.87 206	61.39 202	57.04 245	74.70 189	69.09 192	57.36 190	47.91 229	45.94 202	47.47 219	55.96 177	53.90 204	71.07 205	68.83 212	84.99 180	81.15 154

v148		67.85 157	67.53 171	68.23 138	73.25 173	77.57 161	74.26 155	57.36 190	55.70 186	57.45 124	53.53 175	55.42 178	61.96 137	75.23 178	73.92 187	85.08 176	81.32 152

MVSTER		72.06 112	74.24 106	69.51 127	70.39 198	75.97 174	76.91 125	57.36 190	64.64 119	61.39 106	68.86 75	63.76 134	63.46 124	81.44 87	79.70 107	87.56 108	85.31 111

FE-MVSNET		52.98 239	55.99 239	49.47 239	49.71 251	65.83 228	54.09 245	56.91 193	40.70 244	16.86 257	32.90 246	40.15 248	37.83 235	69.80 222	73.04 194	81.41 205	69.49 229

blended_shiyan8		62.98 196	63.65 209	62.21 194	59.20 233	74.17 192	69.03 195	56.52 194	51.08 221	47.96 186	48.07 217	55.02 182	55.00 197	70.43 214	68.60 215	85.52 161	78.15 181

blended_shiyan6		62.98 196	63.66 208	62.19 195	59.20 233	74.17 192	69.04 194	56.52 194	51.09 220	47.91 187	48.11 216	55.02 182	54.98 198	70.43 214	68.59 216	85.51 162	78.20 179

V42		68.76 148	69.63 145	67.74 143	64.93 223	78.01 149	78.30 111	56.48 196	58.65 162	56.30 130	54.26 168	57.03 169	64.85 118	77.47 159	77.01 161	85.60 160	84.96 118

wanda-best-256-512		62.84 199	63.46 211	62.12 197	59.06 235	74.03 195	68.92 197	56.37 197	51.17 215	48.02 184	48.12 214	54.93 184	55.08 195	70.13 217	68.14 222	85.26 170	77.73 187

FE-blended-shiyan7		62.84 199	63.46 211	62.12 197	59.06 235	74.03 195	68.92 197	56.37 197	51.17 215	48.02 184	48.12 214	54.93 184	55.08 195	70.13 217	68.14 222	85.26 170	77.73 187

usedtu_blend_shiyan5		64.27 189	64.70 199	63.77 186	59.06 235	74.03 195	71.65 179	56.37 197	51.17 215	53.88 143	52.71 189	58.58 157	56.43 181	70.13 217	68.14 222	85.26 170	78.14 182

FE-MVSNET3		64.07 192	64.71 198	63.32 192	59.06 235	74.03 195	68.92 197	56.37 197	51.17 215	53.88 143	52.71 189	58.58 157	56.43 181	70.13 217	68.14 222	85.26 170	78.20 179

CANet_DTU		73.29 103	76.96 88	69.00 133	77.04 134	82.06 103	79.49 95	56.30 201	67.85 99	53.29 154	71.12 60	70.37 102	61.81 141	81.59 81	80.96 80	86.09 146	84.73 121

CVMVSNet		62.55 204	65.89 182	58.64 216	66.95 213	69.15 217	66.49 214	56.29 202	52.46 208	32.70 232	59.27 133	58.21 164	50.09 213	71.77 199	71.39 200	79.31 213	78.99 175

Fast-Effi-MVS+-dtu		68.34 150	69.47 147	67.01 159	75.15 152	77.97 155	77.12 121	55.40 203	57.87 163	46.68 195	56.17 152	60.39 144	62.36 130	76.32 173	76.25 172	85.35 168	81.34 151

blend_shiyan4		64.82 185	65.21 190	64.37 180	65.04 220	74.06 194	70.30 186	55.30 204	55.39 188	53.88 143	52.71 189	58.58 157	56.43 181	69.45 225	68.13 227	85.30 169	78.14 182

0.4-1-1-0.1		65.57 177	65.82 184	65.29 170	67.19 210	75.61 177	72.13 176	55.16 205	57.12 172	53.84 147	54.57 163	58.80 154	59.40 156	69.22 227	69.01 210	83.99 192	76.43 198

FA-MVS(training)		73.66 99	74.95 104	72.15 97	78.63 120	80.46 123	78.92 104	54.79 206	69.71 86	65.37 89	62.04 115	66.89 125	67.10 98	80.72 107	79.87 104	88.10 85	84.97 117

0.3-1-1-0.015		65.09 181	65.15 192	65.01 174	66.63 216	75.00 186	71.90 177	54.57 207	56.32 181	53.88 143	53.63 174	58.58 157	59.47 155	68.39 232	68.46 219	83.62 194	75.64 206

0.4-1-1-0.2		64.94 183	65.02 196	64.85 176	66.45 217	74.76 187	71.66 178	54.40 208	55.85 185	53.84 147	53.97 171	58.62 156	59.33 157	68.27 233	68.20 221	83.40 196	75.47 208

gg-mvs-nofinetune		62.55 204	65.05 194	59.62 212	78.72 119	77.61 159	70.83 184	53.63 209	39.71 247	22.04 250	36.36 240	64.32 132	47.53 217	81.16 96	79.03 126	85.00 179	77.17 192

baseline		70.45 128	74.09 110	66.20 167	70.95 195	75.67 175	74.26 155	53.57 210	68.33 95	58.42 117	69.87 68	71.45 85	61.55 143	74.84 181	74.76 184	78.42 216	83.72 132

PMVS	39.38 18	46.06 247	43.30 250	49.28 240	62.93 225	38.75 256	41.88 255	53.50 211	33.33 253	35.46 229	28.90 250	31.01 256	33.04 242	58.61 250	54.63 251	68.86 248	57.88 249
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SCA		65.40 179	66.58 181	64.02 184	70.65 196	73.37 201	67.35 204	53.46 212	63.66 128	54.14 138	60.84 121	60.20 147	61.50 144	69.96 221	68.14 222	77.01 223	69.91 225

testgi		54.39 236	57.86 234	50.35 237	71.59 190	67.24 224	54.95 244	53.25 213	43.36 239	23.78 245	44.64 225	47.87 230	24.96 248	70.45 211	68.66 214	73.60 238	62.78 243

IterMVS-SCA-FT		66.89 172	69.22 151	64.17 181	71.30 193	75.64 176	71.33 181	53.17 214	57.63 169	49.08 178	60.72 122	60.05 148	63.09 126	74.99 180	73.92 187	77.07 222	81.57 150

usedtu_dtu_shiyan2		49.27 241	50.47 244	47.86 241	35.37 259	64.10 234	58.53 240	53.10 215	31.42 255	29.57 236	27.09 252	38.06 251	34.31 240	63.35 241	63.36 240	76.27 227	65.93 236

dps		64.00 193	62.99 214	65.18 171	73.29 172	72.07 206	68.98 196	53.07 216	57.74 167	58.41 118	55.55 156	47.74 231	60.89 150	69.53 224	67.14 231	76.44 226	71.19 223

tpm cat1		65.41 178	63.81 207	67.28 154	75.61 149	72.88 202	75.32 133	52.85 217	62.97 133	63.66 100	53.24 180	53.29 205	61.83 140	65.54 236	64.14 238	74.43 235	74.60 212

CR-MVSNet		64.83 184	65.54 187	64.01 185	70.64 197	69.41 215	65.97 215	52.74 218	57.81 165	52.65 157	54.27 166	56.31 174	60.92 148	72.20 196	73.09 192	81.12 207	75.69 204

Patchmtry						65.80 230	65.97 215	52.74 218		52.65 157

pmmvs5		62.37 210	64.04 204	60.42 206	65.03 221	71.67 208	67.17 206	52.70 220	50.30 222	44.80 207	54.23 169	51.19 218	49.37 214	72.88 190	73.48 191	83.45 195	74.55 213

MIMVSNet1		49.27 241	53.25 241	44.62 244	44.61 253	61.52 245	53.61 246	52.18 221	41.62 243	18.68 254	28.14 251	41.58 245	25.50 246	68.46 231	69.04 208	73.15 239	62.37 244

new-patchmatchnet		46.97 245	49.47 247	44.05 246	62.82 226	56.55 249	45.35 254	52.01 222	42.47 241	17.04 256	35.73 242	35.21 252	21.84 254	61.27 245	54.83 250	65.26 251	60.26 245

CostFormer		68.92 145	69.58 146	68.15 139	75.98 141	76.17 173	78.22 112	51.86 223	65.80 109	61.56 105	63.57 111	62.83 137	61.85 139	70.40 216	68.67 213	79.42 212	79.62 171

CMPMVS	47.78 17	62.49 206	62.52 219	62.46 193	70.01 201	70.66 212	62.97 227	51.84 224	51.98 211	56.71 128	42.87 228	53.62 194	57.80 168	72.23 194	70.37 203	75.45 232	75.91 201
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
PatchmatchNet		64.21 191	64.65 200	63.69 187	71.29 194	68.66 219	69.63 189	51.70 225	63.04 132	53.77 149	59.83 130	58.34 163	60.23 153	68.54 230	66.06 234	75.56 230	68.08 232
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
PM-MVS		60.48 220	60.94 228	59.94 209	58.85 240	66.83 226	64.27 223	51.39 226	55.03 193	48.03 183	50.00 207	40.79 246	58.26 164	69.20 228	67.13 232	78.84 215	77.60 189

FPMVS		51.87 240	50.00 246	54.07 231	66.83 214	57.25 248	60.25 236	50.91 227	50.25 223	34.36 230	36.04 241	32.02 255	41.49 228	58.98 248	56.07 248	70.56 246	59.36 248

RPSCF		67.64 163	71.25 131	63.43 190	61.86 229	70.73 211	67.26 205	50.86 228	74.20 62	58.91 113	67.49 90	69.33 107	64.10 122	71.41 200	68.45 220	77.61 218	77.17 192

IterMVS		66.36 173	68.30 164	64.10 182	69.48 205	74.61 190	73.41 169	50.79 229	57.30 171	48.28 182	60.64 123	59.92 149	60.85 151	74.14 185	72.66 195	81.80 202	78.82 176
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
anonymousdsp		65.28 180	67.98 167	62.13 196	58.73 242	73.98 199	67.10 207	50.69 230	48.41 228	47.66 191	54.27 166	52.75 209	61.45 146	76.71 170	80.20 98	87.13 117	89.53 56

EU-MVSNet		54.63 234	58.69 232	49.90 238	56.99 246	62.70 243	56.41 243	50.64 231	45.95 237	23.14 247	50.42 204	46.51 234	36.63 237	65.51 237	64.85 236	75.57 229	74.91 211

MDTV_nov1_ep13		64.37 188	65.24 189	63.37 191	68.94 207	70.81 210	72.40 175	50.29 232	60.10 156	53.91 142	60.07 127	59.15 152	57.21 173	69.43 226	67.30 229	77.47 219	69.78 227

pmnet_mix02		55.30 233	57.01 237	53.30 235	64.14 224	59.09 246	58.39 241	50.24 233	53.47 203	38.68 223	49.75 209	45.86 236	40.14 233	65.38 238	60.22 244	68.19 249	65.33 237

RPMNet		61.71 217	62.88 215	60.34 207	69.51 204	69.41 215	63.48 225	49.23 234	57.81 165	45.64 204	50.51 203	50.12 222	53.13 208	68.17 234	68.49 218	81.07 208	75.62 207

MVS-HIRNet		54.41 235	52.10 243	57.11 222	58.99 239	56.10 250	49.68 251	49.10 235	46.18 236	52.15 161	33.18 245	46.11 235	56.10 184	63.19 243	59.70 246	76.64 225	60.25 246

MIMVSNet		58.52 227	61.34 226	55.22 228	60.76 230	67.01 225	66.81 209	49.02 236	56.43 178	38.90 222	40.59 235	54.54 189	40.57 232	73.16 189	71.65 198	75.30 233	66.00 235

TAMVS		59.58 223	62.81 217	55.81 226	66.03 218	65.64 231	63.86 224	48.74 237	49.95 224	37.07 228	54.77 162	58.54 161	44.44 223	72.29 193	71.79 197	74.70 234	66.66 234

PatchT		61.97 212	64.04 204	59.55 213	60.49 231	67.40 223	56.54 242	48.65 238	56.69 175	52.65 157	51.10 202	52.14 213	60.92 148	72.20 196	73.09 192	78.03 217	75.69 204

Gipuma		36.38 250	35.80 252	37.07 247	45.76 252	33.90 257	29.81 257	48.47 239	39.91 246	18.02 255	8.00 260	8.14 264	25.14 247	59.29 247	61.02 243	55.19 255	40.31 253
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MDTV_nov1_ep13_2view		60.16 221	60.51 230	59.75 210	65.39 219	69.05 218	68.00 202	48.29 240	51.99 210	45.95 201	48.01 218	49.64 226	53.39 206	68.83 229	66.52 233	77.47 219	69.55 228

EPMVS		60.00 222	61.97 223	57.71 219	68.46 208	63.17 241	64.54 221	48.23 241	63.30 130	44.72 209	60.19 125	56.05 176	50.85 212	65.27 239	62.02 242	69.44 247	63.81 240

tpmrst		62.00 211	62.35 222	61.58 200	71.62 188	64.14 233	69.07 193	48.22 242	62.21 139	53.93 141	58.26 143	55.30 180	55.81 188	63.22 242	62.62 241	70.85 244	70.70 224

FMVSNet5		57.24 228	60.02 231	53.99 232	56.45 247	62.74 242	65.27 218	47.03 243	55.14 190	39.55 221	40.88 233	53.42 202	41.83 226	72.35 192	71.10 202	73.79 237	64.50 239

gm-plane-assit		57.00 229	57.62 236	56.28 225	76.10 138	62.43 244	47.62 253	46.57 244	33.84 251	23.24 246	37.52 237	40.19 247	59.61 154	79.81 128	77.55 151	84.55 187	72.03 221

ADS-MVSNet		55.94 232	58.01 233	53.54 234	62.48 228	58.48 247	59.12 239	46.20 245	59.65 158	42.88 215	52.34 196	53.31 204	46.31 219	62.00 244	60.02 245	64.23 252	60.24 247

tpm		62.41 207	63.15 213	61.55 201	72.24 181	63.79 237	71.31 182	46.12 246	57.82 164	55.33 133	59.90 129	54.74 187	53.63 205	67.24 235	64.29 237	70.65 245	74.25 217

N_pmnet		47.35 244	50.13 245	44.11 245	59.98 232	51.64 253	51.86 248	44.80 247	49.58 226	20.76 252	40.65 234	40.05 249	29.64 244	59.84 246	55.15 249	57.63 253	54.00 250

PMMVS		65.06 182	69.17 152	60.26 208	55.25 250	63.43 238	66.71 211	43.01 248	62.41 137	50.64 168	69.44 71	67.04 124	63.29 125	74.36 184	73.54 190	82.68 200	73.99 218

CHOSEN 280x420		58.70 226	61.88 224	54.98 229	55.45 249	50.55 254	64.92 219	40.36 249	55.21 189	38.13 225	48.31 212	63.76 134	63.03 128	73.73 188	68.58 217	68.00 250	73.04 220

E-PMN		21.77 253	18.24 256	25.89 250	40.22 256	19.58 260	12.46 263	39.87 250	18.68 259	6.71 261	9.57 257	4.31 267	22.36 253	19.89 258	27.28 256	33.73 259	28.34 257

EMVS		20.98 254	17.15 257	25.44 251	39.51 257	19.37 261	12.66 262	39.59 251	19.10 258	6.62 262	9.27 258	4.40 266	22.43 252	17.99 259	24.40 257	31.81 260	25.53 258

TESTMET0.1,1		61.10 218	64.36 202	57.29 220	57.53 243	63.93 235	66.61 212	36.22 252	54.41 197	47.77 188	57.46 146	60.25 145	55.20 193	70.80 208	69.33 206	80.40 210	74.38 214

test-mter		60.84 219	64.62 201	56.42 224	55.99 248	64.18 232	65.39 217	34.23 253	54.39 199	46.21 199	57.40 148	59.49 151	55.86 187	71.02 207	69.65 205	80.87 209	76.20 200

MVE	19.12 19	20.47 255	23.27 255	17.20 255	12.66 262	25.41 259	10.52 264	34.14 254	14.79 260	6.53 263	8.79 259	4.68 265	16.64 256	29.49 256	41.63 253	22.73 262	38.11 254
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
new_pmnet		38.40 249	42.64 251	33.44 249	37.54 258	45.00 255	36.60 256	32.72 255	40.27 245	12.72 258	29.89 248	28.90 257	24.78 249	53.17 252	52.90 252	56.31 254	48.34 251

pmmvs3		47.65 243	49.08 248	45.99 243	44.61 253	54.79 251	50.04 249	31.95 256	33.91 250	29.90 235	30.37 247	33.53 254	46.31 219	63.50 240	63.67 239	73.14 240	63.77 241

PMMVS2		25.60 251	29.75 253	20.76 253	28.00 260	30.93 258	23.10 260	29.18 257	23.14 257	1.46 265	18.23 256	16.54 261	5.08 258	40.22 253	41.40 254	37.76 257	37.79 255

DeepMVS_CX						18.74 262	18.55 261	8.02 258	26.96 256	7.33 260	23.81 254	13.05 263	25.99 245	25.17 257		22.45 263	36.25 256

test_method		22.26 252	25.94 254	17.95 254	3.24 263	7.17 263	23.83 259	7.27 259	37.35 249	20.44 253	21.87 255	39.16 250	18.67 255	34.56 254	20.84 258	34.28 258	20.64 259

tmp_tt				14.50 256	14.68 261	7.17 263	10.46 265	2.21 260	37.73 248	28.71 239	25.26 253	16.98 260	4.37 259	31.49 255	29.77 255	26.56 261

GG-mvs-BLEND		46.86 246	67.51 172	22.75 252	0.05 264	76.21 172	64.69 220	0.04 261	61.90 141	0.09 266	55.57 155	71.32 89	0.08 260	70.54 210	67.19 230	71.58 242	69.86 226

testmvs		0.09 256	0.15 258	0.02 257	0.01 265	0.02 265	0.05 267	0.01 262	0.11 261	0.01 267	0.26 262	0.01 268	0.06 262	0.10 260	0.10 259	0.01 264	0.43 261

test123		0.09 256	0.14 259	0.02 257	0.00 266	0.02 265	0.02 268	0.01 262	0.09 262	0.00 268	0.30 261	0.00 269	0.08 260	0.03 261	0.09 260	0.01 264	0.45 260

uanet_test		0.00 258	0.00 260	0.00 259	0.00 266	0.00 267	0.00 269	0.00 264	0.00 263	0.00 268	0.00 263	0.00 269	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

sosnet-low-res		0.00 258	0.00 260	0.00 259	0.00 266	0.00 267	0.00 269	0.00 264	0.00 263	0.00 268	0.00 263	0.00 269	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

sosnet		0.00 258	0.00 260	0.00 259	0.00 266	0.00 267	0.00 269	0.00 264	0.00 263	0.00 268	0.00 263	0.00 269	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

TPM-MVS					90.07 22	88.36 36	88.45 31			77.10 28	75.60 39	83.98 31	71.33 65			89.75 45	89.62 54
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										46.24 198

9.14												86.88 17

our_test_3					67.93 209	70.99 209	66.89 208

ambc			53.42 240		64.99 222	63.36 239	49.96 250		47.07 233	37.12 227	28.97 249	16.36 262	41.82 227	75.10 179	67.34 228	71.55 243	75.72 203

MTAPA										83.48 1		86.45 20

MTMP										82.66 5		84.91 28

Patchmatch-RL test							2.85 266

XVS					86.63 47	88.68 28	85.00 49			71.81 48		81.92 38				90.47 25

X-MVStestdata					86.63 47	88.68 28	85.00 49			71.81 48		81.92 38				90.47 25

mPP-MVS					89.90 26							81.29 43

NP-MVS									80.10 48

High-resolution multi-view benchmark