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.

SF-MVS		87.30 6	88.71 6	85.64 3	94.57 1	94.55 4	91.01 1	79.94 1	89.15 12	79.85 7	92.37 3	83.29 11	79.75 9	83.52 26	82.72 33	88.75 20	95.37 23

MCST-MVS		85.75 9	86.99 13	84.31 6	94.07 3	92.80 8	88.15 9	79.10 2	85.66 21	70.72 29	76.50 33	80.45 22	82.17 5	88.35 2	87.49 3	91.63 2	97.65 4

DPM-MVS		85.41 11	86.72 16	83.89 10	91.66 13	91.92 14	90.49 2	78.09 3	86.90 17	73.95 20	74.52 35	82.01 17	79.29 13	90.24 1	90.65 1	89.86 6	90.78 74

CNVR-MVS		85.96 8	87.58 11	84.06 8	92.58 5	92.40 11	87.62 11	77.77 4	88.44 14	75.93 16	79.49 26	81.97 18	81.65 6	87.04 6	86.58 4	88.79 18	97.18 7

DVP-MVS		88.07 2	90.73 2	84.97 4	91.98 10	95.01 2	87.86 10	76.88 5	93.90 2	85.15 2	90.11 7	86.90 2	79.46 12	86.26 10	84.67 18	88.50 28	98.25 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
SED-MVS		88.94 1	90.98 1	86.56 1	92.53 7	95.09 1	88.55 5	76.83 6	94.16 1	86.57 1	90.85 5	87.07 1	86.18 1	86.36 7	85.08 12	88.67 21	98.21 3

DVP-MVS++		87.98 3	89.76 5	85.89 2	92.57 6	94.57 3	88.34 6	76.61 7	92.40 6	83.40 3	89.26 10	85.57 5	86.04 2	86.24 11	84.89 15	88.39 31	95.42 20

NCCC		84.16 16	85.46 21	82.64 11	92.34 8	90.57 23	86.57 14	76.51 8	86.85 18	72.91 23	77.20 32	78.69 26	79.09 15	84.64 20	84.88 16	88.44 29	95.41 21

DPE-MVS		87.60 5	90.44 4	84.29 7	92.09 9	93.44 6	88.69 4	75.11 9	93.06 5	80.80 6	94.23 2	86.70 3	81.44 7	84.84 18	83.52 27	87.64 49	97.28 5
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		86.37 7	88.41 8	84.00 9	91.43 15	91.83 15	88.34 6	74.67 10	91.19 7	81.76 5	91.13 4	81.94 19	80.07 8	83.38 27	82.58 35	87.69 47	96.78 10
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
HPM-MVS++		85.64 10	88.43 7	82.39 12	92.65 4	90.24 26	85.83 17	74.21 11	90.68 9	75.63 17	86.77 13	84.15 8	78.68 16	86.33 8	85.26 9	87.32 58	95.60 17

MSP-MVS		87.87 4	90.57 3	84.73 5	89.38 27	91.60 17	88.24 8	74.15 12	93.55 3	82.28 4	94.99 1	83.21 12	85.96 3	87.67 4	84.67 18	88.32 32	98.29 1
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
DeepC-MVS_fast	75.41 2	81.69 24	82.10 32	81.20 17	91.04 17	87.81 53	83.42 27	74.04 13	83.77 25	71.09 27	66.88 48	72.44 38	79.48 11	85.08 15	84.97 14	88.12 39	93.78 40
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CSCG		82.90 20	84.52 23	81.02 18	91.85 11	93.43 7	87.14 12	74.01 14	81.96 31	76.14 14	70.84 37	82.49 14	69.71 64	82.32 41	85.18 11	87.26 62	95.40 22

SD-MVS		84.31 15	86.96 14	81.22 16	88.98 31	88.68 40	85.65 18	73.85 15	89.09 13	79.63 8	87.34 12	84.84 6	73.71 35	82.66 35	81.60 47	85.48 110	94.51 29
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
APD-MVS		84.83 13	87.00 12	82.30 13	89.61 25	89.21 36	86.51 15	73.64 16	90.98 8	77.99 12	89.89 8	80.04 24	79.18 14	82.00 48	81.37 50	86.88 72	95.49 19
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + MP.		84.39 14	86.58 17	81.83 14	88.09 38	86.47 69	85.63 19	73.62 17	90.13 11	79.24 9	89.67 9	82.99 13	77.72 18	81.22 53	80.92 59	86.68 77	94.66 28
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
DeepC-MVS	74.46 3	80.30 29	81.05 35	79.42 23	87.42 40	88.50 42	83.23 28	73.27 18	82.78 28	71.01 28	62.86 60	69.93 51	74.80 29	84.30 21	84.20 21	86.79 75	94.77 26
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SMA-MVS		85.24 12	88.27 9	81.72 15	91.74 12	90.71 20	86.71 13	73.16 19	90.56 10	74.33 19	83.07 18	85.88 4	77.16 20	86.28 9	85.58 6	87.23 63	95.77 13
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
AdaColmap		76.23 53	73.55 75	79.35 24	89.38 27	85.00 83	79.99 52	73.04 20	76.60 52	71.17 26	55.18 82	57.99 103	77.87 17	76.82 95	76.82 97	84.67 132	86.45 117

train_agg		83.35 18	86.93 15	79.17 26	89.70 24	88.41 43	85.60 20	72.89 21	86.31 19	66.58 41	90.48 6	82.24 16	73.06 41	83.10 31	82.64 34	87.21 67	95.30 24

DeepPCF-MVS	76.94 1	83.08 19	87.77 10	77.60 33	90.11 20	90.96 19	78.48 56	72.63 22	93.10 4	65.84 42	80.67 24	81.55 20	74.80 29	85.94 13	85.39 8	83.75 147	96.77 11

ACMMP_NAP		83.54 17	86.37 18	80.25 21	89.57 26	90.10 28	85.27 21	71.66 23	87.38 15	73.08 22	84.23 17	80.16 23	75.31 25	84.85 17	83.64 24	86.57 78	94.21 35

CDPH-MVS		79.39 35	82.13 31	76.19 41	89.22 30	88.34 44	84.20 25	71.00 24	79.67 43	56.97 78	77.77 29	72.24 42	68.50 76	81.33 52	82.74 30	87.23 63	92.84 51

SteuartSystems-ACMMP		82.51 21	85.35 22	79.20 25	90.25 18	89.39 34	84.79 22	70.95 25	82.86 27	68.32 37	86.44 14	77.19 27	73.07 40	83.63 25	83.64 24	87.82 43	94.34 31
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator	70.49 5	78.42 38	76.77 59	80.35 20	91.43 15	90.27 25	81.84 36	70.79 26	72.10 60	71.95 24	50.02 102	67.86 57	77.47 19	82.89 32	84.24 20	88.61 24	89.99 85

DELS-MVS		79.49 30	79.84 40	79.08 27	88.26 37	92.49 9	84.12 26	70.63 27	65.27 83	69.60 35	61.29 65	66.50 60	72.75 44	88.07 3	88.03 2	89.13 14	97.22 6
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
QAPM		77.50 45	77.43 53	77.59 34	91.52 14	92.00 13	81.41 40	70.63 27	66.22 76	58.05 73	54.70 83	71.79 44	74.49 33	82.46 37	82.04 37	89.46 12	92.79 53

PCF-MVS	70.85 4	75.73 56	76.55 62	74.78 54	83.67 53	88.04 51	81.47 38	70.62 29	69.24 71	57.52 76	60.59 69	69.18 53	70.65 59	77.11 92	77.65 91	84.75 130	94.01 37
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS_111021_HR		77.42 46	78.40 49	76.28 39	86.95 42	90.68 21	77.41 65	70.56 30	66.21 77	62.48 55	66.17 52	63.98 71	72.08 49	82.87 33	83.15 28	88.24 35	95.71 15

OPM-MVS		72.74 72	70.93 92	74.85 53	85.30 50	84.34 89	82.82 32	69.79 31	49.96 141	55.39 85	54.09 90	60.14 91	70.04 63	80.38 62	79.43 73	85.74 99	88.20 106
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HFP-MVS		82.48 22	84.12 24	80.56 19	90.15 19	87.55 54	84.28 24	69.67 32	85.22 22	77.95 13	84.69 16	75.94 30	75.04 27	81.85 49	81.17 54	86.30 85	92.40 55

HQP-MVS		78.26 39	80.91 36	75.17 49	85.67 49	84.33 90	83.01 30	69.38 33	79.88 41	55.83 79	79.85 25	64.90 67	70.81 57	82.46 37	81.78 42	86.30 85	93.18 47

MP-MVS		80.94 26	83.49 26	77.96 30	88.48 32	88.16 47	82.82 32	69.34 34	80.79 37	69.67 33	82.35 21	77.13 28	71.60 53	80.97 58	80.96 58	85.87 96	94.06 36
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ACMMPR		80.62 28	82.98 27	77.87 32	88.41 33	87.05 60	83.02 29	69.18 35	83.91 24	68.35 36	82.89 19	73.64 35	72.16 48	80.78 59	81.13 55	86.10 90	91.43 64

X-MVS		78.16 40	80.55 37	75.38 47	87.99 39	86.27 73	81.05 45	68.98 36	78.33 45	61.07 63	75.25 34	72.27 39	67.52 83	80.03 63	80.52 66	85.66 107	91.20 68

CLD-MVS		77.36 47	77.29 55	77.45 35	82.21 59	88.11 48	81.92 35	68.96 37	77.97 47	69.62 34	62.08 61	59.44 94	73.57 37	81.75 50	81.27 52	88.41 30	90.39 81
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PHI-MVS		79.43 32	84.06 25	74.04 56	86.15 47	91.57 18	80.85 47	68.90 38	82.22 30	51.81 94	78.10 28	74.28 33	70.39 61	84.01 24	84.00 22	86.14 89	94.24 33

dmvs_re		67.60 104	67.21 118	68.06 96	74.07 121	79.01 133	73.31 94	68.74 39	58.27 104	42.07 141	49.72 103	43.96 151	60.66 116	76.79 96	78.04 90	89.51 10	84.69 134

MSDG		65.57 119	61.57 156	70.24 79	82.02 61	76.47 156	74.46 89	68.73 40	56.52 113	50.33 102	38.47 161	41.10 160	62.42 108	72.12 146	72.94 147	83.47 150	73.37 186

CP-MVS		79.44 31	81.51 34	77.02 36	86.95 42	85.96 78	82.00 34	68.44 41	81.82 32	67.39 38	77.43 30	73.68 34	71.62 52	79.56 70	79.58 72	85.73 100	92.51 54

EPNet		79.28 36	82.25 29	75.83 43	88.31 36	90.14 27	79.43 54	68.07 42	81.76 33	61.26 61	77.26 31	70.08 50	70.06 62	82.43 39	82.00 39	87.82 43	92.09 58
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
3Dnovator+	70.16 6	77.87 41	77.29 55	78.55 28	89.25 29	88.32 45	80.09 50	67.95 43	74.89 58	71.83 25	52.05 95	70.68 48	76.27 24	82.27 42	82.04 37	85.92 93	90.77 76

TSAR-MVS + GP.		82.27 23	85.98 19	77.94 31	80.72 71	88.25 46	81.12 44	67.71 44	87.10 16	73.31 21	85.23 15	83.68 9	76.64 22	80.43 61	81.47 49	88.15 38	95.66 16

SR-MVS					86.33 46			67.54 45				80.78 21

ACMH	59.42 14	61.59 153	59.22 172	64.36 122	78.92 84	78.26 141	67.65 138	67.48 46	39.81 182	30.98 189	38.25 163	34.59 192	61.37 114	70.55 162	73.47 136	79.74 187	79.59 165
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMMP		77.61 44	79.59 41	75.30 48	85.87 48	85.58 79	81.42 39	67.38 47	79.38 44	62.61 53	78.53 27	65.79 62	68.80 75	78.56 78	78.50 83	85.75 97	90.80 73
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
CANet		80.90 27	82.93 28	78.53 29	86.83 44	92.26 12	81.19 43	66.95 48	81.60 34	69.90 32	66.93 47	74.80 32	76.79 21	84.68 19	84.77 17	89.50 11	95.50 18

baseline1		71.47 78	72.02 81	70.82 75	80.56 73	84.51 86	76.61 69	66.93 49	56.22 116	48.66 108	55.40 81	60.43 88	62.55 106	83.35 29	80.99 56	89.60 8	83.28 147

CHOSEN 1792x2688		72.55 73	71.98 82	73.22 60	86.57 45	92.41 10	75.63 72	66.77 50	62.08 90	52.32 91	30.27 196	50.74 135	66.14 86	86.22 12	85.41 7	91.90 1	96.75 12

TSAR-MVS + ACMM		81.59 25	85.84 20	76.63 37	89.82 23	86.53 68	86.32 16	66.72 51	85.96 20	65.43 43	88.98 11	82.29 15	67.57 82	82.06 46	81.33 51	83.93 145	93.75 41

FC-MVSNet-train		68.83 95	68.29 109	69.47 82	78.35 88	79.94 125	64.72 153	66.38 52	54.96 125	54.51 88	56.75 77	47.91 142	66.91 84	75.57 109	75.75 109	85.92 93	87.12 112

OpenMVS	67.62 8	74.92 62	73.91 73	76.09 42	90.10 21	90.38 24	78.01 60	66.35 53	66.09 78	62.80 51	46.33 127	64.55 69	71.77 51	79.92 65	80.88 60	87.52 53	89.20 94

thres100view900		67.14 112	66.09 127	68.38 95	77.70 93	83.84 94	74.52 86	66.33 54	49.16 145	43.40 132	43.24 131	41.34 156	62.59 105	79.31 71	75.92 108	85.73 100	89.81 86

MSLP-MVS++		78.57 37	77.33 54	80.02 22	88.39 34	84.79 84	84.62 23	66.17 55	75.96 53	78.40 10	61.59 63	71.47 45	73.54 38	78.43 79	78.88 78	88.97 16	90.18 84

LS3D		64.54 128	62.14 152	67.34 104	80.85 68	75.79 162	69.99 123	65.87 56	60.77 94	44.35 126	42.43 140	45.95 147	65.01 89	69.88 168	68.69 178	77.97 195	71.43 193

PGM-MVS		79.42 34	81.84 33	76.60 38	88.38 35	86.69 64	82.97 31	65.75 57	80.39 38	64.94 44	81.95 23	72.11 43	71.41 55	80.45 60	80.55 65	86.18 87	90.76 77

CNLPA		71.37 81	70.27 97	72.66 65	80.79 70	81.33 112	71.07 117	65.75 57	82.36 29	64.80 45	42.46 139	56.49 108	72.70 45	73.00 137	70.52 171	80.84 180	85.76 127

MAR-MVS		77.19 48	78.37 50	75.81 44	89.87 22	90.58 22	79.33 55	65.56 59	77.62 49	58.33 72	59.24 73	67.98 55	74.83 28	82.37 40	83.12 29	86.95 70	87.67 110
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
PVSNet_BlendedMVS		76.84 50	78.47 47	74.95 51	82.37 57	89.90 30	75.45 76	65.45 60	74.99 56	70.66 30	63.07 58	58.27 101	67.60 80	84.24 22	81.70 44	88.18 36	97.10 8

PVSNet_Blended		76.84 50	78.47 47	74.95 51	82.37 57	89.90 30	75.45 76	65.45 60	74.99 56	70.66 30	63.07 58	58.27 101	67.60 80	84.24 22	81.70 44	88.18 36	97.10 8

MVS_111021_LR		74.26 64	75.95 65	72.27 67	79.43 78	85.04 82	72.71 97	65.27 62	70.92 63	63.58 49	69.32 39	60.31 90	69.43 69	77.01 93	77.15 94	83.22 154	91.93 61

IB-MVS	64.48 11	69.02 93	68.97 104	69.09 88	81.75 62	89.01 38	64.50 154	64.91 63	56.65 112	62.59 54	47.89 111	45.23 148	51.99 158	69.18 173	81.88 41	88.77 19	92.93 50
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
ACMM	66.70 10	70.42 83	68.49 107	72.67 64	82.85 54	77.76 147	77.70 63	64.76 64	64.61 84	60.74 67	49.29 104	53.97 125	65.86 87	74.97 112	75.57 113	84.13 144	83.29 146
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CPTT-MVS		75.43 58	77.13 57	73.44 58	81.43 65	82.55 102	80.96 46	64.35 65	77.95 48	61.39 60	69.20 40	70.94 47	69.38 71	73.89 126	73.32 140	83.14 157	92.06 59

thres400		65.18 123	64.44 135	66.04 108	76.40 108	82.63 100	71.52 109	64.27 66	44.93 163	40.69 148	41.86 143	40.79 162	58.12 134	77.67 85	74.64 121	85.26 113	88.56 102

ACMP	68.86 7	72.15 75	72.25 80	72.03 68	80.96 67	80.87 118	77.93 61	64.13 67	69.29 69	60.79 66	64.04 56	53.54 127	63.91 97	73.74 129	75.27 116	84.45 137	88.98 96
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
casdiffmvs_mvg		75.57 57	76.04 64	75.02 50	80.48 74	89.31 35	80.79 48	64.04 68	66.95 74	63.87 47	57.52 75	61.33 84	72.90 42	82.01 47	81.99 40	88.03 40	93.16 48
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
UniMVSNet_NR-MVSNet		62.30 144	63.51 139	60.89 147	69.48 149	77.83 145	64.07 157	63.94 69	50.03 140	31.17 187	44.82 129	41.12 159	51.37 161	71.02 155	74.81 120	85.30 112	84.95 132

MVS_0304		79.43 32	82.20 30	76.20 40	84.22 52	91.79 16	81.82 37	63.81 70	76.83 51	61.71 58	66.37 50	75.52 31	76.38 23	85.54 14	85.03 13	89.28 13	94.32 32

TranMVSNet+NR-MVSNet		60.38 160	61.30 158	59.30 158	68.34 153	75.57 166	63.38 166	63.78 71	46.74 154	27.73 193	42.56 137	36.84 179	47.66 171	70.36 164	74.59 123	84.91 122	82.46 153

PLC	64.00 12	68.54 96	66.66 121	70.74 76	80.28 75	74.88 168	72.64 98	63.70 72	69.26 70	55.71 81	47.24 118	55.31 117	70.42 60	72.05 148	70.67 169	81.66 174	77.19 172
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
casdiffmvs		75.20 60	75.69 67	74.63 55	79.26 81	89.07 37	78.47 57	63.59 73	67.05 73	63.79 48	55.72 80	60.32 89	73.58 36	82.16 43	81.78 42	89.08 15	93.72 42
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVSTER		76.92 49	79.92 39	73.42 59	74.98 118	82.97 98	78.15 59	63.41 74	78.02 46	64.41 46	67.54 45	72.80 37	71.05 56	83.29 30	83.73 23	88.53 27	91.12 69

OMC-MVS		74.03 66	75.82 66	71.95 69	79.56 76	80.98 116	75.35 78	63.21 75	84.48 23	61.83 57	61.54 64	66.89 58	69.41 70	76.60 97	74.07 130	82.34 167	86.15 121

Anonymous202405211			66.35 125		78.00 92	84.41 88	74.85 80	63.18 76	51.00 137		31.37 193	53.73 126	69.67 66	76.28 99	76.84 96	83.21 156	90.85 72

LGP-MVS_train		72.02 76	73.18 78	70.67 77	82.13 60	80.26 124	79.58 53	63.04 77	70.09 65	51.98 92	65.06 53	55.62 115	62.49 107	75.97 104	76.32 104	84.80 129	88.93 97

test1111		66.72 113	67.80 113	65.45 111	77.42 100	86.63 65	69.69 126	62.98 78	55.29 122	39.47 151	40.12 155	47.11 143	55.70 148	79.96 64	80.00 67	87.47 54	85.49 130

diffmvs		74.32 63	75.42 68	73.04 61	75.60 115	87.27 57	78.20 58	62.96 79	68.66 72	61.89 56	59.79 71	59.84 92	71.80 50	78.30 82	79.87 68	87.80 45	94.23 34
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
thres600view7		63.77 133	63.14 141	64.51 119	75.49 116	81.61 106	69.59 127	62.95 80	43.96 166	38.90 156	41.09 147	40.24 167	55.25 151	76.24 100	71.54 157	84.89 123	87.30 111

thres200		65.58 118	64.74 133	66.56 107	77.52 98	81.61 106	73.44 92	62.95 80	46.23 157	42.45 139	42.76 133	41.18 158	58.12 134	76.24 100	75.59 112	84.89 123	89.58 89

tfpn200view9		65.90 117	64.96 131	67.00 106	77.70 93	81.58 108	71.71 107	62.94 82	49.16 145	43.40 132	43.24 131	41.34 156	61.42 112	76.24 100	74.63 122	84.84 125	88.52 103

Baseline_NR-MVSNet		59.47 164	60.28 165	58.54 163	66.69 164	73.90 174	61.63 173	62.90 83	49.15 147	26.87 194	35.18 183	37.62 174	48.20 169	69.67 170	73.61 134	84.92 120	82.82 151

ACMH+	60.36 13	61.16 154	58.38 174	64.42 121	77.37 101	74.35 173	68.45 133	62.81 84	45.86 159	38.48 158	35.71 179	37.35 176	59.81 123	67.24 178	69.80 175	79.58 188	78.32 170

baseline2		71.22 82	73.01 79	69.13 85	75.76 113	86.34 72	71.23 112	62.78 85	62.62 87	52.85 90	57.32 76	54.31 122	63.27 102	79.74 68	79.31 74	88.89 17	91.43 64

test2506		69.26 89	70.79 93	67.48 102	78.64 86	86.40 70	72.22 99	62.75 86	58.05 106	45.24 120	50.76 98	54.93 119	58.05 136	79.82 66	79.70 69	87.96 41	85.90 125

ECVR-MVS		67.93 103	68.49 107	67.28 105	78.64 86	86.40 70	72.22 99	62.75 86	58.05 106	44.06 128	40.92 150	48.20 140	58.05 136	79.82 66	79.70 69	87.96 41	86.32 120

EPNet_dtu		66.17 115	70.13 98	61.54 145	81.04 66	77.39 151	68.87 132	62.50 88	69.78 66	33.51 182	63.77 57	56.22 110	37.65 195	72.20 145	72.18 155	85.69 103	79.38 166
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TAPA-MVS	67.10 9	71.45 79	73.47 77	69.10 86	77.04 102	80.78 119	73.81 91	62.10 89	80.80 36	51.28 95	60.91 66	63.80 73	67.98 77	74.59 116	72.42 152	82.37 166	80.97 161
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DU-MVS		60.87 157	61.82 154	59.76 154	66.69 164	75.87 160	64.07 157	61.96 90	49.31 143	31.17 187	42.76 133	36.95 178	51.37 161	69.67 170	73.20 145	83.30 153	84.95 132

NR-MVSNet		61.08 156	62.09 153	59.90 152	71.96 133	75.87 160	63.60 163	61.96 90	49.31 143	27.95 192	42.76 133	33.85 196	48.82 168	74.35 121	74.05 131	85.13 115	84.45 136

Anonymous20231211		68.44 97	66.37 124	70.86 74	77.58 96	83.49 95	75.15 79	61.89 92	52.54 134	58.50 71	28.89 198	56.78 107	69.29 72	74.96 114	76.61 98	82.73 160	91.36 67

TSAR-MVS + COLMAP		73.09 69	76.86 58	68.71 89	74.97 119	82.49 103	74.51 87	61.83 93	83.16 26	49.31 107	82.22 22	51.62 132	68.94 74	78.76 77	75.52 115	82.67 162	84.23 139

PVSNet_Blended_VisFu		71.76 77	73.54 76	69.69 81	79.01 83	87.16 59	72.05 101	61.80 94	56.46 114	59.66 69	53.88 91	62.48 74	59.08 130	81.17 54	78.90 77	86.53 80	94.74 27

MS-PatchMatch		70.34 87	69.00 103	71.91 70	85.20 51	85.35 80	77.84 62	61.77 95	58.01 108	55.40 84	41.26 146	58.34 100	61.69 110	81.70 51	78.29 84	89.56 9	80.02 164

tfpnnormal		58.97 167	56.48 182	61.89 142	71.27 138	76.21 159	66.65 148	61.76 96	32.90 202	36.41 169	27.83 201	29.14 209	50.64 165	73.06 135	73.05 146	84.58 135	83.15 150

DI_MVS_plusplus_trai		73.94 67	74.85 70	72.88 62	76.57 107	86.80 62	80.41 49	61.47 97	62.35 89	59.44 70	47.91 110	68.12 54	72.24 47	82.84 34	81.50 48	87.15 69	94.42 30

TransMVSNet (Re)		57.83 173	56.90 180	58.91 161	72.26 131	74.69 171	63.57 164	61.42 98	32.30 204	32.65 183	33.97 186	35.96 186	39.17 193	73.84 128	72.84 149	84.37 138	74.69 179

UniMVSNet (Re)		60.62 158	62.93 145	57.92 165	67.64 159	77.90 144	61.75 172	61.24 99	49.83 142	29.80 191	42.57 136	40.62 165	43.36 185	70.49 163	73.27 142	83.76 146	85.81 126

test-LLR		68.23 100	71.61 87	64.28 123	71.37 136	81.32 113	63.98 159	61.03 100	58.62 102	42.96 135	52.74 92	61.65 80	57.74 141	75.64 107	78.09 88	88.61 24	93.21 45

test0.0.03 1		57.35 177	59.89 169	54.38 184	71.37 136	73.45 176	52.71 193	61.03 100	46.11 158	26.33 196	41.73 144	44.08 150	29.72 199	71.43 154	70.90 166	85.10 116	71.56 192

GBi-Net		69.21 90	70.40 95	67.81 98	69.49 146	78.65 137	74.54 83	60.97 102	65.32 80	51.06 96	47.37 115	62.05 76	63.43 99	77.49 87	78.22 85	87.37 55	83.73 141

test1		69.21 90	70.40 95	67.81 98	69.49 146	78.65 137	74.54 83	60.97 102	65.32 80	51.06 96	47.37 115	62.05 76	63.43 99	77.49 87	78.22 85	87.37 55	83.73 141

FMVSNet3		70.41 85	71.89 84	68.68 90	70.89 141	79.42 131	75.63 72	60.97 102	65.32 80	51.06 96	47.37 115	62.05 76	64.90 91	82.49 36	82.27 36	88.64 23	84.34 138

ET-MVSNet_ETH3D		71.38 80	74.70 71	67.51 101	51.61 211	88.06 50	77.29 66	60.95 105	63.61 85	48.36 110	66.60 49	60.67 87	79.55 10	73.56 130	80.58 64	87.30 61	89.80 87

sasdasda		77.65 42	79.59 41	75.39 45	81.52 63	89.83 32	81.32 41	60.74 106	80.05 39	66.72 39	68.43 41	65.09 63	74.72 31	78.87 74	82.73 31	87.32 58	92.16 56

canonicalmvs		77.65 42	79.59 41	75.39 45	81.52 63	89.83 32	81.32 41	60.74 106	80.05 39	66.72 39	68.43 41	65.09 63	74.72 31	78.87 74	82.73 31	87.32 58	92.16 56

EIA-MVS		73.48 68	76.05 63	70.47 78	78.12 90	87.21 58	71.78 104	60.63 108	69.66 68	55.56 83	64.86 54	60.69 86	69.53 67	77.35 91	78.59 79	87.22 65	94.01 37

baseline		72.89 70	74.46 72	71.07 73	75.99 111	87.50 55	74.57 82	60.49 109	70.72 64	57.60 75	60.63 68	60.97 85	70.79 58	75.27 110	76.33 103	86.94 71	89.79 88

CS-MVS-test		75.09 61	77.84 51	71.87 71	79.27 80	86.92 61	70.53 122	60.36 110	75.13 55	63.13 50	67.92 44	65.08 65	71.43 54	78.15 84	78.51 82	86.53 80	93.16 48

PatchMatch-RL		62.22 148	60.69 162	64.01 124	68.74 151	75.75 163	59.27 180	60.35 111	56.09 117	53.80 89	47.06 121	36.45 181	64.80 92	68.22 175	67.22 182	77.10 197	74.02 181

ETV-MVS		76.25 52	80.22 38	71.63 72	78.23 89	87.95 52	72.75 96	60.27 112	77.50 50	57.73 74	71.53 36	66.60 59	73.16 39	80.99 57	81.23 53	87.63 50	95.73 14

CS-MVS		75.84 55	78.61 46	72.61 66	79.03 82	86.74 63	74.43 90	60.27 112	74.15 59	62.78 52	66.26 51	64.25 70	72.81 43	83.36 28	81.69 46	86.32 83	93.85 39

FMVSNet2		68.06 101	68.57 106	67.45 103	69.49 146	78.65 137	74.54 83	60.23 114	56.29 115	49.64 106	42.13 142	57.08 106	63.43 99	81.15 55	80.99 56	87.37 55	83.73 141

MGCFI-Net		74.26 64	78.69 45	69.10 86	80.64 72	87.32 56	73.21 95	59.20 115	79.76 42	50.18 104	68.10 43	64.86 68	64.65 94	78.28 83	80.83 61	86.69 76	91.69 63

Effi-MVS+		70.42 83	71.23 89	69.47 82	78.04 91	85.24 81	75.57 74	58.88 116	59.56 99	48.47 109	52.73 94	54.94 118	69.69 65	78.34 81	77.06 95	86.18 87	90.73 78

MVS_Test		75.22 59	76.69 60	73.51 57	79.30 79	88.82 39	80.06 51	58.74 117	69.77 67	57.50 77	59.78 72	61.35 82	75.31 25	82.07 45	83.60 26	90.13 5	91.41 66

UGNet		67.57 107	71.69 86	62.76 136	69.88 144	82.58 101	66.43 149	58.64 118	54.71 129	51.87 93	61.74 62	62.01 79	45.46 181	74.78 115	74.99 117	84.24 140	91.02 70
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
Anonymous20231206		52.23 192	52.80 194	51.56 189	64.70 177	69.41 190	51.01 195	58.60 119	36.63 191	22.44 202	21.80 212	31.42 203	30.52 198	66.79 179	67.83 179	82.10 170	75.73 175

IS_MVSNet		67.29 110	71.98 82	61.82 143	76.92 103	84.32 91	65.90 152	58.22 120	55.75 120	39.22 154	54.51 86	62.47 75	45.99 179	78.83 76	78.52 81	84.70 131	89.47 91

GA-MVS		64.55 127	65.76 130	63.12 131	69.68 145	81.56 109	69.59 127	58.16 121	45.23 162	35.58 174	47.01 122	41.82 155	59.41 126	79.62 69	78.54 80	86.32 83	86.56 116

HyFIR lowres test		68.39 98	68.28 110	68.52 92	80.85 68	88.11 48	71.08 116	58.09 122	54.87 128	47.80 113	27.55 202	55.80 113	64.97 90	79.11 72	79.14 76	88.31 33	93.35 44

thisisatest0530		68.38 99	70.98 91	65.35 112	72.61 129	84.42 87	68.21 135	57.98 123	59.77 98	50.80 99	54.63 84	58.48 97	57.92 138	76.99 94	77.47 92	84.60 133	85.07 131

tttt0517		67.99 102	70.61 94	64.94 115	71.94 134	83.96 93	67.62 139	57.98 123	59.30 100	49.90 105	54.50 87	57.98 104	57.92 138	76.48 98	77.47 92	84.24 140	84.58 135

CDS-MVSNet		64.22 129	65.89 129	62.28 141	70.05 143	80.59 120	69.91 125	57.98 123	43.53 167	46.58 115	48.22 109	50.76 134	46.45 176	75.68 106	76.08 106	82.70 161	86.34 119
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
FMVSNet1		63.48 135	63.07 142	63.97 125	65.31 174	76.37 158	71.77 106	57.90 126	43.32 168	45.66 117	35.06 184	49.43 137	58.57 132	77.49 87	78.22 85	84.59 134	81.60 160

DCV-MVSNet		69.13 92	69.07 102	69.21 84	77.65 95	77.52 149	74.68 81	57.85 127	54.92 126	55.34 86	55.74 79	55.56 116	66.35 85	75.05 111	76.56 100	83.35 151	88.13 107

EPP-MVSNet		67.58 106	71.10 90	63.48 129	75.71 114	83.35 96	66.85 145	57.83 128	53.02 133	41.15 145	55.82 78	67.89 56	56.01 147	74.40 119	72.92 148	83.33 152	90.30 82

v148		62.00 150	61.19 159	62.96 132	67.46 161	79.49 130	67.87 136	57.66 129	42.30 170	45.02 123	38.20 164	38.89 171	54.77 152	69.83 169	72.60 151	84.96 119	87.01 113

v2v482		63.68 134	62.85 146	64.65 118	68.01 155	80.46 122	71.90 102	57.60 130	44.26 164	42.82 137	39.80 157	38.62 172	61.56 111	73.06 135	74.86 119	86.03 92	88.90 99

pmmvs4		63.14 137	62.46 149	63.94 126	66.03 170	76.40 157	66.82 146	57.60 130	56.74 111	50.26 103	40.81 151	37.51 175	59.26 128	71.75 151	71.48 159	83.68 149	82.53 152

Vis-MVSNet (Re-imp)		62.25 145	68.74 105	54.68 181	73.70 123	78.74 136	56.51 187	57.49 132	55.22 123	26.86 195	54.56 85	61.35 82	31.06 197	73.10 134	74.90 118	82.49 164	83.31 145

UA-Net		64.62 125	68.23 111	60.42 150	77.53 97	81.38 111	60.08 178	57.47 133	47.01 152	44.75 124	60.68 67	71.32 46	41.84 189	73.27 132	72.25 154	80.83 181	71.68 191

DTE-MVSNet		49.82 198	51.92 198	47.37 199	61.75 190	64.38 204	45.89 207	57.33 134	36.11 195	12.79 218	36.87 172	31.93 201	25.73 206	58.01 199	65.22 191	80.75 182	70.93 196

pm-mvs1		59.21 166	59.58 171	58.77 162	67.97 156	77.07 154	64.12 155	57.20 135	34.73 199	36.86 165	35.34 181	40.54 166	43.34 186	74.32 122	73.30 141	83.13 158	81.77 159

PEN-MVS		51.04 193	52.94 192	48.82 194	61.45 191	66.00 199	48.68 198	57.20 135	36.87 189	15.36 211	36.98 171	32.72 198	28.77 203	57.63 201	66.37 186	81.44 176	74.00 182

V42		62.86 141	62.97 143	62.74 137	60.84 192	78.99 135	71.46 110	57.13 137	46.85 153	44.28 127	38.87 159	40.73 164	57.63 143	72.60 143	74.14 128	85.09 118	88.63 101

EC-MVSNet		76.05 54	78.87 44	72.77 63	78.87 85	86.63 65	77.50 64	57.04 138	75.34 54	61.68 59	64.20 55	69.56 52	73.96 34	82.12 44	80.65 63	87.57 51	93.57 43

test20.03		47.23 205	48.69 205	45.53 204	63.28 182	64.39 203	41.01 212	56.93 139	29.16 208	15.21 212	23.90 206	30.76 206	17.51 216	64.63 188	65.26 190	79.21 191	62.71 210

GeoE		68.96 94	69.32 100	68.54 91	76.61 106	83.12 97	71.78 104	56.87 140	60.21 97	54.86 87	45.95 128	54.79 121	64.27 95	74.59 116	75.54 114	86.84 74	91.01 71

v1144		63.00 139	62.39 150	63.70 128	67.72 158	80.27 123	71.23 112	56.40 141	42.51 169	40.81 147	38.12 165	37.73 173	60.42 120	74.46 118	74.55 124	85.64 108	89.12 95

WR-MVS		51.02 194	54.56 186	46.90 200	63.84 180	69.23 191	44.78 208	56.38 142	38.19 187	14.19 213	37.38 167	36.82 180	22.39 209	60.14 197	66.20 189	79.81 186	73.95 183

CP-MVSNet		50.57 195	52.60 196	48.21 197	58.77 200	65.82 200	48.17 199	56.29 143	37.41 188	16.59 208	37.14 169	31.95 200	29.21 200	56.60 204	63.71 195	80.22 183	75.56 176

Effi-MVS+-dtu		64.58 126	64.08 136	65.16 113	73.04 128	75.17 167	70.68 121	56.23 144	54.12 131	44.71 125	47.42 114	51.10 133	63.82 98	68.08 176	66.32 187	82.47 165	86.38 118

PS-CasMVS		50.17 196	52.02 197	48.02 198	58.60 201	65.54 201	48.04 200	56.19 145	36.42 193	16.42 210	35.68 180	31.33 204	28.85 202	56.42 206	63.54 197	80.01 184	75.18 177

v144192		62.05 149	61.46 157	62.73 138	66.59 167	79.87 126	69.30 129	55.88 146	41.50 176	39.41 153	37.23 168	36.45 181	59.62 124	72.69 142	73.51 135	85.61 109	88.93 97

COLMAP_ROB	51.17 15	55.13 180	52.90 193	57.73 168	73.47 127	67.21 196	62.13 170	55.82 147	47.83 149	34.39 178	31.60 192	34.24 193	44.90 183	63.88 192	62.52 200	75.67 200	63.02 209
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
v1192		62.25 145	61.64 155	62.96 132	66.88 163	79.72 127	69.96 124	55.77 148	41.58 174	39.42 152	37.05 170	35.96 186	60.50 119	74.30 123	74.09 129	85.24 114	88.76 100

MDA-MVSNet-bldmvs		44.15 207	42.27 212	46.34 201	38.34 219	62.31 208	46.28 204	55.74 149	29.83 207	20.98 204	27.11 203	16.45 225	41.98 188	41.11 217	57.47 207	74.72 204	61.65 212

PMMVS		70.37 86	75.06 69	64.90 116	71.46 135	81.88 104	64.10 156	55.64 150	71.31 62	46.69 114	70.69 38	58.56 95	69.53 67	79.03 73	75.63 111	81.96 171	88.32 105

UniMVSNet_ETH3D		57.83 173	56.46 183	59.43 157	63.24 183	73.22 177	67.70 137	55.58 151	36.17 194	36.84 166	32.64 188	35.14 190	51.50 160	65.81 181	69.81 174	81.73 173	82.44 155

EG-PatchMatch MVS		58.73 170	58.03 177	59.55 155	72.32 130	80.49 121	63.44 165	55.55 152	32.49 203	38.31 159	28.87 199	37.22 177	42.84 187	74.30 123	75.70 110	84.84 125	77.14 173

v1921920		61.66 152	61.10 160	62.31 140	66.32 168	79.57 129	68.41 134	55.49 153	41.03 177	38.69 157	36.64 176	35.27 189	59.60 125	73.23 133	73.41 137	85.37 111	88.51 104

Vis-MVSNet		65.53 120	69.83 99	60.52 149	70.80 142	84.59 85	66.37 151	55.47 154	48.40 148	40.62 149	57.67 74	58.43 99	45.37 182	77.49 87	76.24 105	84.47 136	85.99 124
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TESTMET0.1,1		67.38 109	71.61 87	62.45 139	66.05 169	81.32 113	63.98 159	55.36 155	58.62 102	42.96 135	52.74 92	61.65 80	57.74 141	75.64 107	78.09 88	88.61 24	93.21 45

USDC		59.69 163	60.03 168	59.28 159	64.04 179	71.84 181	63.15 168	55.36 155	54.90 127	35.02 176	48.34 108	29.79 208	58.16 133	70.60 160	71.33 164	79.99 185	73.42 185

WB-MVS		30.42 214	32.63 216	27.84 213	51.51 212	41.64 220	17.75 223	55.06 157	20.11 221	2.46 228	26.13 205	16.63 224	3.90 223	44.91 212	44.54 215	36.34 222	34.48 219

WR-MVS_H		49.62 199	52.63 195	46.11 203	58.80 199	67.58 195	46.14 206	54.94 158	36.51 192	13.63 216	36.75 174	35.67 188	22.10 210	56.43 205	62.76 199	81.06 178	72.73 188

TDRefinement		52.70 190	51.02 199	54.66 182	57.41 203	65.06 202	61.47 174	54.94 158	44.03 165	33.93 180	30.13 197	27.57 211	46.17 178	61.86 194	62.48 201	74.01 206	66.06 203

v1240		61.09 155	60.55 164	61.72 144	65.92 172	79.28 132	67.16 144	54.91 160	39.79 183	38.10 160	36.08 178	34.64 191	59.15 129	72.86 138	73.36 139	85.10 116	87.84 108

v8		63.44 136	62.58 148	64.43 120	68.28 154	78.07 142	71.82 103	54.85 161	46.70 155	45.20 121	39.40 158	40.91 161	60.54 118	72.85 139	74.39 127	85.92 93	85.76 127

testgi		48.51 202	50.53 200	46.16 202	64.78 175	67.15 197	41.54 211	54.81 162	29.12 209	17.03 207	32.07 191	31.98 199	20.15 213	65.26 184	67.00 184	78.67 193	61.10 213

Fast-Effi-MVS+		67.59 105	67.56 115	67.62 100	73.67 124	81.14 115	71.12 115	54.79 163	58.88 101	50.61 101	46.70 125	47.05 144	69.12 73	76.06 103	76.44 101	86.43 82	86.65 115

CANet_DTU		72.84 71	76.63 61	68.43 94	76.81 104	86.62 67	75.54 75	54.71 164	72.06 61	43.54 130	67.11 46	58.46 98	72.40 46	81.13 56	80.82 62	87.57 51	90.21 83

v10		63.00 139	62.22 151	63.90 127	67.88 157	77.78 146	71.59 108	54.34 165	45.37 161	42.76 138	38.53 160	38.93 170	61.05 115	74.39 120	74.52 125	85.75 97	86.04 122

pmnet_mix02		53.92 188	53.30 190	54.65 183	61.89 189	71.33 185	54.54 191	54.17 166	40.38 179	34.65 177	34.76 185	30.68 207	40.44 191	60.97 195	63.71 195	82.19 169	71.24 194

pmmvs5		59.72 162	60.24 166	59.11 160	62.77 186	77.33 152	63.17 167	54.00 167	40.21 181	37.23 164	40.41 152	35.99 185	51.75 159	72.55 144	72.74 150	85.72 102	82.45 154

thisisatest0515		59.37 165	60.68 163	57.84 167	64.39 178	75.65 165	58.56 183	53.86 168	41.55 175	42.12 140	40.40 153	39.59 168	47.09 174	71.69 152	73.79 132	81.02 179	82.08 157

pmmvs-eth3d		55.20 179	53.95 188	56.65 174	57.34 204	67.77 194	57.54 185	53.74 169	40.93 178	41.09 146	31.19 194	29.10 210	49.07 167	65.54 182	67.28 181	81.14 177	75.81 174

IterMVS-LS		66.08 116	66.56 123	65.51 110	73.67 124	74.88 168	70.89 119	53.55 170	50.42 139	48.32 111	50.59 100	55.66 114	61.83 109	73.93 125	74.42 126	84.82 128	86.01 123
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FC-MVSNet-test		47.24 204	54.37 187	38.93 209	59.49 197	58.25 213	34.48 217	53.36 171	45.66 160	6.66 223	50.62 99	42.02 154	16.62 217	58.39 198	61.21 202	62.99 214	64.40 206

CMPMVS	43.63 17	57.67 176	55.43 184	60.28 151	72.01 132	79.00 134	62.77 169	53.23 172	41.77 173	45.42 118	30.74 195	39.03 169	53.01 156	64.81 187	64.65 193	75.26 202	68.03 200
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
TAMVS		58.86 168	60.91 161	56.47 176	62.38 188	77.57 148	58.97 182	52.98 173	38.76 186	36.17 170	42.26 141	47.94 141	46.45 176	70.23 166	70.79 168	81.86 172	78.82 169

TinyColmap		52.66 191	50.09 202	55.65 177	59.72 196	64.02 206	57.15 186	52.96 174	40.28 180	32.51 184	32.42 189	20.97 219	56.65 146	63.95 191	65.15 192	74.91 203	63.87 207

FMVSNet5		58.86 168	60.24 166	57.25 171	52.66 210	66.25 198	63.77 162	52.86 175	57.85 109	37.92 162	36.12 177	52.22 131	51.37 161	70.88 157	71.43 161	84.92 120	66.91 202

CVMVSNet		54.92 184	58.16 175	51.13 191	62.61 187	68.44 193	55.45 189	52.38 176	42.28 171	21.45 203	47.10 119	46.10 146	37.96 194	64.42 190	63.81 194	76.92 198	75.01 178

pmmvs6		54.20 187	53.54 189	54.97 179	63.22 184	72.98 178	60.17 177	52.32 177	26.77 213	34.30 179	23.29 209	36.23 183	40.33 192	68.77 174	68.76 177	79.47 190	78.00 171

v7n		57.04 178	56.64 181	57.52 169	62.85 185	74.75 170	61.76 171	51.80 178	35.58 198	36.02 172	32.33 190	33.61 197	50.16 166	67.73 177	70.34 172	82.51 163	82.12 156

N_pmnet		47.67 203	47.00 207	48.45 196	54.72 207	62.78 207	46.95 203	51.25 179	36.01 196	26.09 197	26.59 204	25.93 216	35.50 196	55.67 208	59.01 204	76.22 199	63.04 208

MIMVSNet1		40.84 210	43.46 208	37.79 210	32.14 220	58.92 212	39.24 214	50.83 180	27.00 212	11.29 220	16.76 219	26.53 214	17.75 215	57.14 203	61.12 203	75.46 201	56.78 214

new-patchmatchnet		42.21 208	42.97 209	41.33 207	53.05 209	59.89 210	39.38 213	49.61 181	28.26 211	12.10 219	22.17 211	21.54 218	19.22 214	50.96 211	56.04 209	74.61 205	61.92 211

MDTV_nov1_ep13		65.21 122	67.28 117	62.79 134	70.91 140	81.72 105	69.28 130	49.50 182	58.08 105	43.94 129	50.50 101	56.02 111	58.86 131	70.72 158	73.37 138	84.24 140	80.52 163

FA-MVS(training)		70.24 88	71.77 85	68.45 93	77.52 98	86.03 77	73.33 93	49.12 183	63.55 86	55.77 80	48.91 107	56.26 109	67.78 79	77.60 86	79.62 71	87.19 68	90.40 80

CostFormer		72.18 74	73.90 74	70.18 80	79.47 77	86.19 76	76.94 68	48.62 184	66.07 79	60.40 68	54.14 89	65.82 61	67.98 77	75.84 105	76.41 102	87.67 48	92.83 52

IterMVS		61.87 151	63.55 138	59.90 152	67.29 162	72.20 180	67.34 143	48.56 185	47.48 151	37.86 163	47.07 120	48.27 138	54.08 154	72.12 146	73.71 133	84.30 139	83.99 140
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
anonymousdsp		54.99 182	57.24 179	52.36 187	53.82 208	71.75 184	51.49 194	48.14 186	33.74 200	33.66 181	38.34 162	36.13 184	47.54 172	64.53 189	70.60 170	79.53 189	85.59 129

test-mter		64.06 131	69.24 101	58.01 164	59.07 198	77.40 150	59.13 181	48.11 187	55.64 121	39.18 155	51.56 97	58.54 96	55.38 150	73.52 131	76.00 107	87.22 65	92.05 60

SixPastTwentyTwo		49.11 201	49.22 204	48.99 193	58.54 202	64.14 205	47.18 202	47.75 188	31.15 206	24.42 198	41.01 149	26.55 213	44.04 184	54.76 209	58.70 206	71.99 209	68.21 198

tpm cat1		67.47 108	67.05 119	67.98 97	76.63 105	81.51 110	74.49 88	47.65 189	61.18 92	61.12 62	42.51 138	53.02 130	64.74 93	70.11 167	71.50 158	83.22 154	89.49 90

EU-MVSNet		44.84 206	47.85 206	41.32 208	49.26 214	56.59 214	43.07 210	47.64 190	33.03 201	13.82 214	36.78 173	30.99 205	24.37 207	53.80 210	55.57 210	69.78 211	68.21 198

LTVRE_ROB	47.26 16	49.41 200	49.91 203	48.82 194	64.76 176	69.79 189	49.05 197	47.12 191	20.36 220	16.52 209	36.65 175	26.96 212	50.76 164	60.47 196	63.16 198	64.73 213	72.00 190
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
IterMVS-SCA-FT		60.21 161	62.97 143	57.00 173	66.64 166	71.84 181	67.53 140	46.93 192	47.56 150	36.77 168	46.85 124	48.21 139	52.51 157	70.36 164	72.40 153	71.63 210	83.53 144

dps		64.08 130	63.22 140	65.08 114	75.27 117	79.65 128	66.68 147	46.63 193	56.94 110	55.67 82	43.96 130	43.63 153	64.00 96	69.50 172	69.82 173	82.25 168	79.02 168

PatchmatchNet		65.43 121	67.71 114	62.78 135	73.49 126	82.83 99	66.42 150	45.40 194	60.40 96	45.27 119	49.22 105	57.60 105	60.01 122	70.61 159	71.38 163	86.08 91	81.91 158
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		67.15 111	68.12 112	66.03 109	76.21 109	80.98 116	71.27 111	45.05 195	60.69 95	50.63 100	46.95 123	54.15 124	65.30 88	71.80 150	71.77 156	87.72 46	90.48 79

MIMVSNet		57.78 175	59.71 170	55.53 178	54.79 206	77.10 153	63.89 161	45.02 196	46.59 156	36.79 167	28.36 200	40.77 163	45.84 180	74.97 112	76.58 99	86.87 73	73.60 184

tpm		64.85 124	66.02 128	63.48 129	74.52 120	78.38 140	70.98 118	44.99 197	51.61 136	43.28 134	47.66 113	53.18 128	60.57 117	70.58 161	71.30 165	86.54 79	89.45 92

PM-MVS		50.11 197	50.38 201	49.80 192	47.23 217	62.08 209	50.91 196	44.84 198	41.90 172	36.10 171	35.22 182	26.05 215	46.83 175	57.64 200	55.42 211	72.90 207	74.32 180

EPMVS		66.21 114	67.49 116	64.73 117	75.81 112	84.20 92	68.94 131	44.37 199	61.55 91	48.07 112	49.21 106	54.87 120	62.88 103	71.82 149	71.40 162	88.28 34	79.37 167

SCA		63.90 132	66.67 120	60.66 148	73.75 122	71.78 183	59.87 179	43.66 200	61.13 93	45.03 122	51.64 96	59.45 93	57.92 138	70.96 156	70.80 167	83.71 148	80.92 162

MDTV_nov1_ep13_2view		54.47 186	54.61 185	54.30 185	60.50 193	73.82 175	57.92 184	43.38 201	39.43 185	32.51 184	33.23 187	34.05 194	47.26 173	62.36 193	66.21 188	84.24 140	73.19 187

CR-MVSNet		62.31 143	64.75 132	59.47 156	68.63 152	71.29 186	67.53 140	43.18 202	55.83 118	41.40 142	41.04 148	55.85 112	57.29 144	72.76 140	73.27 142	78.77 192	83.23 148

Patchmtry						78.06 143	67.53 140	43.18 202		41.40 142

Fast-Effi-MVS+-dtu		63.05 138	64.72 134	61.11 146	71.21 139	76.81 155	70.72 120	43.13 204	52.51 135	35.34 175	46.55 126	46.36 145	61.40 113	71.57 153	71.44 160	84.84 125	87.79 109

gm-plane-assit		54.99 182	57.99 178	51.49 190	69.27 150	54.42 215	32.32 218	42.59 205	21.18 218	13.71 215	23.61 207	43.84 152	60.21 121	87.09 5	86.55 5	90.81 4	89.28 93

CHOSEN 280x420		62.23 147	66.57 122	57.17 172	59.88 195	68.92 192	61.20 175	42.28 206	54.17 130	39.57 150	47.78 112	64.97 66	62.68 104	73.85 127	69.52 176	77.43 196	86.75 114

MVS-HIRNet		53.86 189	53.02 191	54.85 180	60.30 194	72.36 179	44.63 209	42.20 207	39.45 184	43.47 131	21.66 213	34.00 195	55.47 149	65.42 183	67.16 183	83.02 159	71.08 195

FPMVS		39.11 211	36.39 213	42.28 205	55.97 205	45.94 218	46.23 205	41.57 208	35.73 197	22.61 200	23.46 208	19.82 221	28.32 204	43.57 214	40.67 216	58.96 216	45.54 216

PatchT		60.46 159	63.85 137	56.51 175	65.95 171	75.68 164	47.34 201	41.39 209	53.89 132	41.40 142	37.84 166	50.30 136	57.29 144	72.76 140	73.27 142	85.67 104	83.23 148

PMVS	27.44 18	32.08 213	29.07 217	35.60 211	48.33 216	24.79 222	26.97 220	41.34 210	20.45 219	22.50 201	17.11 218	18.64 222	20.44 212	41.99 216	38.06 217	54.02 218	42.44 217
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
RPSCF		55.07 181	58.06 176	51.57 188	48.87 215	58.95 211	53.68 192	41.26 211	62.42 88	45.88 116	54.38 88	54.26 123	53.75 155	57.15 202	53.53 212	66.01 212	65.75 204

gg-mvs-nofinetune		62.34 142	66.19 126	57.86 166	76.15 110	88.61 41	71.18 114	41.24 212	25.74 214	13.16 217	22.91 210	63.97 72	54.52 153	85.06 16	85.25 10	90.92 3	91.78 62

ADS-MVSNet		58.40 172	59.16 173	57.52 169	65.80 173	74.57 172	60.26 176	40.17 213	50.51 138	38.01 161	40.11 156	44.72 149	59.36 127	64.91 185	66.55 185	81.53 175	72.72 189

RPMNet		58.63 171	62.80 147	53.76 186	67.59 160	71.29 186	54.60 190	38.13 214	55.83 118	35.70 173	41.58 145	53.04 129	47.89 170	66.10 180	67.38 180	78.65 194	84.40 137

Gipuma		24.91 216	24.61 218	25.26 215	31.47 221	21.59 223	18.06 222	37.53 215	25.43 215	10.03 221	4.18 225	4.25 229	14.85 218	43.20 215	47.03 213	39.62 220	26.55 222
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
EMVS		14.40 219	10.71 222	18.70 218	28.15 223	12.09 228	7.06 227	36.89 216	11.00 223	3.56 227	4.95 223	2.27 231	13.91 219	10.13 224	16.06 223	22.63 225	18.51 224

E-PMN		15.08 218	11.65 221	19.08 217	28.73 222	12.31 227	6.95 228	36.87 217	10.71 224	3.63 226	5.13 222	2.22 232	13.81 220	11.34 223	18.50 222	24.49 224	21.32 223

pmmvs3		41.86 209	42.29 211	41.36 206	39.80 218	52.66 216	38.93 215	35.85 218	23.40 217	20.22 205	19.30 214	20.84 220	40.56 190	55.98 207	58.79 205	72.80 208	65.03 205

new_pmnet		33.19 212	35.52 214	30.47 212	27.55 224	45.31 219	29.29 219	30.92 219	29.00 210	9.88 222	18.77 215	17.64 223	26.77 205	44.07 213	45.98 214	58.41 217	47.87 215

MVE	15.98 19	14.37 220	16.36 220	12.04 221	7.72 227	20.24 225	5.90 229	29.05 220	8.28 225	3.92 225	4.72 224	2.42 230	9.57 221	18.89 222	31.46 219	16.07 227	28.53 221
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMMVS2		20.45 217	22.31 219	18.27 219	20.52 225	26.73 221	14.85 225	28.43 221	13.69 222	0.79 229	10.35 221	9.10 226	3.83 224	27.64 220	32.87 218	41.17 219	35.81 218

test_method		28.15 215	34.48 215	20.76 216	6.76 228	21.18 224	21.03 221	18.41 222	36.77 190	17.52 206	15.67 220	31.63 202	24.05 208	41.03 218	26.69 220	36.82 221	68.38 197

DeepMVS_CX						19.81 226	17.01 224	10.02 223	23.61 216	5.85 224	17.21 217	8.03 228	21.13 211	22.60 221		21.42 226	30.01 220

tmp_tt				16.09 220	13.07 226	8.12 229	13.61 226	2.08 224	55.09 124	30.10 190	40.26 154	22.83 217	5.35 222	29.91 219	25.25 221	32.33 223

GG-mvs-BLEND		54.54 185	77.58 52	27.67 214	0.03 229	90.09 29	77.20 67	0.02 225	66.83 75	0.05 230	59.90 70	73.33 36	0.04 225	78.40 80	79.30 75	88.65 22	95.20 25

testmvs		0.05 221	0.08 223	0.01 222	0.00 230	0.01 230	0.03 231	0.01 226	0.05 226	0.00 231	0.14 227	0.01 233	0.03 227	0.05 225	0.05 224	0.01 228	0.24 226

uanet_test		0.00 223	0.00 225	0.00 224	0.00 230	0.00 232	0.00 233	0.00 227	0.00 228	0.00 231	0.00 228	0.00 234	0.00 228	0.00 227	0.00 226	0.00 229	0.00 227

sosnet-low-res		0.00 223	0.00 225	0.00 224	0.00 230	0.00 232	0.00 233	0.00 227	0.00 228	0.00 231	0.00 228	0.00 234	0.00 228	0.00 227	0.00 226	0.00 229	0.00 227

sosnet		0.00 223	0.00 225	0.00 224	0.00 230	0.00 232	0.00 233	0.00 227	0.00 228	0.00 231	0.00 228	0.00 234	0.00 228	0.00 227	0.00 226	0.00 229	0.00 227

test123		0.05 221	0.08 223	0.01 222	0.00 230	0.01 230	0.01 232	0.00 227	0.05 226	0.00 231	0.16 226	0.00 234	0.04 225	0.02 226	0.05 224	0.00 229	0.26 225

TPM-MVS					94.34 2	93.91 5	89.34 3			75.49 18	82.52 20	83.34 10	83.53 4			89.62 7	90.78 74
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										31.47 186

9.14												84.47 7

our_test_3					63.32 181	71.07 188	55.90 188

ambc			42.30 210		50.36 213	49.51 217	35.47 216		32.04 205	23.53 199	17.36 216	8.95 227	29.06 201	64.88 186	56.26 208	61.29 215	67.12 201

MTAPA										78.32 11		79.42 25

MTMP										76.04 15		76.65 29

Patchmatch-RL test							2.17 230

XVS					82.43 55	86.27 73	75.70 70			61.07 63		72.27 39				85.67 104

X-MVStestdata					82.43 55	86.27 73	75.70 70			61.07 63		72.27 39				85.67 104

mPP-MVS					86.96 41							70.61 49

NP-MVS									81.60 34

High-resolution multi-view benchmark