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		77.13 8	81.70 8	71.79 3	79.32 1	80.76 5	82.96 2	57.49 11	82.82 9	64.79 5	83.69 10	84.46 5	62.83 13	77.13 26	75.21 32	83.35 7	87.85 16

SED-MVS		79.21 1	84.74 2	72.75 1	78.66 2	81.96 2	82.94 4	58.16 4	86.82 2	67.66 1	88.29 4	86.15 3	66.42 2	80.41 4	78.65 6	82.65 16	90.92 2

DVP-MVS		78.77 2	84.89 1	71.62 4	78.04 3	82.05 1	81.64 10	57.96 7	87.53 1	66.64 2	88.77 1	86.31 1	63.16 10	79.99 7	78.56 7	82.31 23	91.03 1
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
APDe-MVS		77.58 6	82.93 6	71.35 6	77.86 4	80.55 6	83.38 1	57.61 10	85.57 5	61.11 22	86.10 7	82.98 8	64.76 4	78.29 15	76.78 22	83.40 6	90.20 5
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DPE-MVS		78.11 4	83.84 4	71.42 5	77.82 5	81.32 4	82.92 5	57.81 9	84.04 8	63.19 12	88.63 2	86.00 4	64.52 5	78.71 11	77.63 15	82.26 24	90.57 3
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SteuartSystems-ACMMP		75.23 13	79.60 15	70.13 13	76.81 6	78.92 12	81.74 8	57.99 6	75.30 29	59.83 27	75.69 18	78.45 24	60.48 29	80.58 2	79.77 2	83.94 3	88.52 10
Skip Steuart: Steuart Systems R&D Blog.
DVP-MVS++		78.76 3	84.44 3	72.14 2	76.63 7	81.93 3	82.92 5	58.10 5	85.86 4	66.53 3	87.86 5	86.16 2	66.45 1	80.46 3	78.53 9	82.19 28	90.29 4

HPM-MVS++		76.01 10	80.47 12	70.81 9	76.60 8	74.96 36	80.18 17	58.36 2	81.96 10	63.50 11	78.80 14	82.53 11	64.40 6	78.74 10	78.84 5	81.81 34	87.46 18

MCST-MVS		73.67 24	77.39 26	69.33 18	76.26 9	78.19 17	78.77 26	54.54 30	75.33 27	59.99 26	67.96 32	79.23 22	62.43 16	78.00 18	75.71 30	84.02 2	87.30 19

CNVR-MVS		75.62 12	79.91 14	70.61 10	75.76 10	78.82 14	81.66 9	57.12 13	79.77 16	63.04 13	70.69 25	81.15 16	62.99 11	80.23 5	79.54 3	83.11 8	89.16 8

NCCC		74.27 19	77.83 24	70.13 13	75.70 11	77.41 23	80.51 15	57.09 14	78.25 20	62.28 18	65.54 37	78.26 25	62.18 18	79.13 8	78.51 10	83.01 10	87.68 17

CSCG		74.68 16	79.22 16	69.40 17	75.69 12	80.01 9	79.12 24	52.83 41	79.34 17	63.99 9	70.49 26	82.02 12	60.35 32	77.48 24	77.22 19	84.38 1	87.97 15

DPM-MVS		72.80 26	75.90 30	69.19 20	75.51 13	77.68 21	81.62 11	54.83 26	75.96 25	62.06 19	63.96 49	76.58 31	58.55 40	76.66 33	76.77 23	82.60 19	83.68 40

TPM-MVS					75.48 14	76.70 30	79.31 21			62.34 17	64.71 42	77.88 28	56.94 53			81.88 32	83.68 40
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
SMA-MVS		77.32 7	82.51 7	71.26 7	75.43 15	80.19 8	82.22 7	58.26 3	84.83 7	64.36 7	78.19 15	83.46 6	63.61 8	81.00 1	80.28 1	83.66 4	89.62 6
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
APD-MVS		75.80 11	80.90 11	69.86 15	75.42 16	78.48 16	81.43 13	57.44 12	80.45 14	59.32 28	85.28 8	80.82 18	63.96 7	76.89 28	76.08 28	81.58 39	88.30 12
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MSP-MVS		77.82 5	83.46 5	71.24 8	75.26 17	80.22 7	82.95 3	57.85 8	85.90 3	64.79 5	88.54 3	83.43 7	66.24 3	78.21 17	78.56 7	80.34 46	89.39 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
train_agg		73.89 21	78.25 22	68.80 23	75.25 18	72.27 51	79.75 18	56.05 20	74.87 32	58.97 29	81.83 11	79.76 21	61.05 25	77.39 25	76.01 29	81.71 37	85.61 30

TSAR-MVS + MP.		75.22 14	80.06 13	69.56 16	74.61 19	72.74 49	80.59 14	55.70 23	80.80 13	62.65 15	86.25 6	82.92 9	62.07 19	76.89 28	75.66 31	81.77 36	85.19 33
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SD-MVS		74.43 17	78.87 18	69.26 19	74.39 20	73.70 45	79.06 25	55.24 25	81.04 12	62.71 14	80.18 12	82.61 10	61.70 21	75.43 40	73.92 43	82.44 22	85.22 32
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
ACMMP_NAP		76.15 9	81.17 9	70.30 11	74.09 21	79.47 10	81.59 12	57.09 14	81.38 11	63.89 10	79.02 13	80.48 19	62.24 17	80.05 6	79.12 4	82.94 11	88.64 9

HFP-MVS		74.87 15	78.86 20	70.21 12	73.99 22	77.91 18	80.36 16	56.63 16	78.41 19	64.27 8	74.54 20	77.75 29	62.96 12	78.70 12	77.82 13	83.02 9	86.91 21

AdaColmap		67.89 45	68.85 60	66.77 29	73.73 23	74.30 43	75.28 41	53.58 36	70.24 47	57.59 36	51.19 108	59.19 97	60.74 28	75.33 42	73.72 45	79.69 54	77.96 73

MP-MVS		74.31 18	78.87 18	68.99 21	73.49 24	78.56 15	79.25 23	56.51 17	75.33 27	60.69 24	75.30 19	79.12 23	61.81 20	77.78 21	77.93 12	82.18 30	88.06 14
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TSAR-MVS + ACMM		72.56 28	79.07 17	64.96 41	73.24 25	73.16 48	78.50 27	48.80 67	79.34 17	55.32 42	85.04 9	81.49 15	58.57 39	75.06 43	73.75 44	75.35 109	85.61 30

CDPH-MVS		71.47 32	75.82 32	66.41 32	72.97 26	77.15 25	78.14 30	54.71 27	69.88 49	53.07 56	70.98 24	74.83 37	56.95 52	76.22 34	76.57 24	82.62 17	85.09 34

PGM-MVS		72.89 25	77.13 27	67.94 25	72.47 27	77.25 24	79.27 22	54.63 29	73.71 36	57.95 35	72.38 23	75.33 35	60.75 27	78.25 16	77.36 18	82.57 20	85.62 29

ACMMPR		73.79 23	78.41 21	68.40 24	72.35 28	77.79 20	79.32 20	56.38 18	77.67 23	58.30 33	74.16 21	76.66 30	61.40 22	78.32 14	77.80 14	82.68 15	86.51 22

OPM-MVS		69.33 37	71.05 46	67.32 27	72.34 29	75.70 33	79.57 19	56.34 19	55.21 78	53.81 53	59.51 69	68.96 58	59.67 34	77.61 23	76.44 26	82.19 28	83.88 39
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
X-MVS		71.18 33	75.66 33	65.96 36	71.71 30	76.96 26	77.26 33	55.88 22	72.75 40	54.48 49	64.39 44	74.47 38	54.19 67	77.84 20	77.37 17	82.21 27	85.85 27

HQP-MVS		70.88 34	75.02 34	66.05 35	71.69 31	74.47 41	77.51 32	53.17 38	72.89 39	54.88 46	70.03 28	70.48 52	57.26 48	76.02 36	75.01 35	81.78 35	86.21 23

MAR-MVS		68.04 44	70.74 48	64.90 42	71.68 32	76.33 32	74.63 44	50.48 55	63.81 57	55.52 41	54.88 88	69.90 54	57.39 47	75.42 41	74.79 37	79.71 51	80.03 57
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
mPP-MVS					71.67 33							74.36 41

SR-MVS					71.46 34			54.67 28				81.54 14

MVS_0304		72.45 29	77.44 25	66.61 30	71.08 35	77.81 19	76.74 34	49.30 61	73.12 38	61.17 20	73.70 22	78.08 26	58.78 37	76.75 32	76.52 25	82.61 18	86.14 25

CLD-MVS		67.02 49	71.57 43	61.71 51	71.01 36	74.81 38	71.62 51	38.91 165	71.86 43	60.70 23	64.97 41	67.88 67	51.88 93	76.77 31	74.98 36	76.11 97	69.75 128
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CP-MVS		72.63 27	76.95 28	67.59 26	70.67 37	75.53 34	77.95 31	56.01 21	75.65 26	58.82 30	69.16 30	76.48 32	60.46 30	77.66 22	77.20 20	81.65 38	86.97 20

ACMM	60.30 7	67.58 47	68.82 61	66.13 34	70.59 38	72.01 53	76.54 36	54.26 32	65.64 55	54.78 48	50.35 111	61.72 86	58.74 38	75.79 38	75.03 34	81.88 32	81.17 52
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XVS					70.49 39	76.96 26	74.36 45			54.48 49		74.47 38				82.24 25

X-MVStestdata					70.49 39	76.96 26	74.36 45			54.48 49		74.47 38				82.24 25

ACMMP		71.57 31	75.84 31	66.59 31	70.30 41	76.85 29	78.46 28	53.95 34	73.52 37	55.56 40	70.13 27	71.36 50	58.55 40	77.00 27	76.23 27	82.71 14	85.81 28
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
MVS_111021_HR		67.62 46	70.39 50	64.39 44	69.77 42	70.45 59	71.44 53	51.72 47	60.77 65	55.06 44	62.14 60	66.40 71	58.13 43	76.13 35	74.79 37	80.19 48	82.04 49

MSLP-MVS++		68.17 43	70.72 49	65.19 39	69.41 43	70.64 56	74.99 42	45.76 77	70.20 48	60.17 25	56.42 80	73.01 44	61.14 23	72.80 54	70.54 59	79.70 52	81.42 51

LGP-MVS_train		68.87 39	72.03 42	65.18 40	69.33 44	74.03 44	76.67 35	53.88 35	68.46 50	52.05 61	63.21 52	63.89 75	56.31 56	75.99 37	74.43 39	82.83 13	84.18 36

ACMP	61.42 5	68.72 42	71.37 44	65.64 38	69.06 45	74.45 42	75.88 39	53.30 37	68.10 51	55.74 39	61.53 63	62.29 82	56.97 51	74.70 46	74.23 41	82.88 12	84.31 35
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DeepC-MVS_fast	65.08 3	72.00 30	76.11 29	67.21 28	68.93 46	77.46 22	76.54 36	54.35 31	74.92 31	58.64 32	65.18 39	74.04 43	62.62 14	77.92 19	77.02 21	82.16 31	86.21 23
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CANet		68.77 40	73.01 37	63.83 45	68.30 47	75.19 35	73.73 48	47.90 68	63.86 56	54.84 47	67.51 34	74.36 41	57.62 44	74.22 48	73.57 47	80.56 44	82.36 46

TSAR-MVS + GP.		69.71 35	73.92 36	64.80 43	68.27 48	70.56 57	71.90 50	50.75 51	71.38 44	57.46 37	68.68 31	75.42 34	60.10 33	73.47 51	73.99 42	80.32 47	83.97 38

3Dnovator+	62.63 4	69.51 36	72.62 39	65.88 37	68.21 49	76.47 31	73.50 49	52.74 42	70.85 45	58.65 31	55.97 82	69.95 53	61.11 24	76.80 30	75.09 33	81.09 42	83.23 44

DeepC-MVS	66.32 2	73.85 22	78.10 23	68.90 22	67.92 50	79.31 11	78.16 29	59.28 1	78.24 21	61.13 21	67.36 35	76.10 33	63.40 9	79.11 9	78.41 11	83.52 5	88.16 13
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DeepPCF-MVS	66.49 1	74.25 20	80.97 10	66.41 32	67.75 51	78.87 13	75.61 40	54.16 33	84.86 6	58.22 34	77.94 16	81.01 17	62.52 15	78.34 13	77.38 16	80.16 49	88.40 11

EC-MVSNet		67.01 50	70.27 53	63.21 47	67.21 52	70.47 58	69.01 57	46.96 71	59.16 70	53.23 55	64.01 48	69.71 56	60.37 31	74.92 44	71.24 55	82.50 21	82.41 45

UA-Net		58.50 95	64.68 82	51.30 124	66.97 53	67.13 86	53.68 166	45.65 80	49.51 111	31.58 152	62.91 54	68.47 60	35.85 176	68.20 103	67.28 97	74.03 121	69.24 138

PHI-MVS		69.27 38	74.84 35	62.76 50	66.83 54	74.83 37	73.88 47	49.32 60	70.61 46	50.93 64	69.62 29	74.84 36	57.25 49	75.53 39	74.32 40	78.35 68	84.17 37

3Dnovator	60.86 6	66.99 51	70.32 51	63.11 48	66.63 55	74.52 39	71.56 52	45.76 77	67.37 53	55.00 45	54.31 93	68.19 63	58.49 42	73.97 49	73.63 46	81.22 41	80.23 56

EPNet		65.14 60	69.54 57	60.00 58	66.61 56	67.67 77	67.53 65	55.32 24	62.67 61	46.22 84	67.74 33	65.93 72	48.07 114	72.17 57	72.12 49	76.28 93	78.47 68
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OpenMVS	57.13 9	62.81 67	65.75 74	59.39 62	66.47 57	69.52 61	64.26 101	43.07 130	61.34 64	50.19 67	47.29 129	64.41 74	54.60 65	70.18 79	68.62 80	77.73 70	78.89 64

ACMH	52.42 13	58.24 102	59.56 122	56.70 86	66.34 58	69.59 60	66.71 75	49.12 62	46.08 144	28.90 165	42.67 176	41.20 193	52.60 85	71.39 63	70.28 61	76.51 89	75.72 95
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MSDG		58.46 97	58.97 128	57.85 78	66.27 59	66.23 95	67.72 62	42.33 134	53.43 86	43.68 96	43.39 167	45.35 170	49.75 103	68.66 93	67.77 89	77.38 76	67.96 143

QAPM		65.27 56	69.49 58	60.35 55	65.43 60	72.20 52	65.69 88	47.23 69	63.46 58	49.14 69	53.56 94	71.04 51	57.01 50	72.60 56	71.41 53	77.62 72	82.14 48

CPTT-MVS		68.76 41	73.01 37	63.81 46	65.42 61	73.66 46	76.39 38	52.08 43	72.61 41	50.33 66	60.73 64	72.65 46	59.43 35	73.32 52	72.12 49	79.19 60	85.99 26

MS-PatchMatch		58.19 104	60.20 109	55.85 93	65.17 62	64.16 115	64.82 95	41.48 143	50.95 101	42.17 105	45.38 150	56.42 109	48.08 113	68.30 98	66.70 106	73.39 131	69.46 136

PCF-MVS	59.98 8	67.32 48	71.04 47	62.97 49	64.77 63	74.49 40	74.78 43	49.54 57	67.44 52	54.39 52	58.35 74	72.81 45	55.79 62	71.54 62	69.24 70	78.57 62	83.41 42
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EG-PatchMatch MVS		56.98 111	58.24 135	55.50 95	64.66 64	68.62 65	61.48 110	43.63 114	38.44 197	41.44 107	38.05 188	46.18 165	43.95 132	71.71 61	70.61 58	77.87 69	74.08 108

Effi-MVS+-dtu		60.34 82	62.32 92	58.03 73	64.31 65	67.44 81	65.99 82	42.26 135	49.55 109	42.00 106	48.92 119	59.79 95	56.27 57	68.07 107	67.03 98	77.35 77	75.45 98

FC-MVSNet-train		58.40 98	63.15 89	52.85 114	64.29 66	61.84 129	55.98 150	46.47 73	53.06 90	34.96 140	61.95 62	56.37 111	39.49 153	68.67 92	68.36 82	75.92 103	71.81 116

Effi-MVS+		63.28 64	65.96 73	60.17 57	64.26 67	68.06 71	68.78 60	45.71 79	54.08 82	46.64 79	55.92 83	63.13 79	55.94 60	70.38 76	71.43 52	79.68 55	78.70 65

LS3D		60.20 83	61.70 93	58.45 68	64.18 68	67.77 74	67.19 68	48.84 66	61.67 63	41.27 110	45.89 144	51.81 128	54.18 68	68.78 90	66.50 113	75.03 113	69.48 134

ACMH+	53.71 12	59.26 87	60.28 106	58.06 71	64.17 69	68.46 66	67.51 66	50.93 50	52.46 96	35.83 136	40.83 181	45.12 174	52.32 88	69.88 81	69.00 75	77.59 74	76.21 92

GeoE		62.43 70	64.79 81	59.68 61	64.15 70	67.17 85	68.80 59	44.42 96	55.65 77	47.38 73	51.54 105	62.51 80	54.04 70	69.99 80	68.07 84	79.28 58	78.57 66

DELS-MVS		65.87 53	70.30 52	60.71 54	64.05 71	72.68 50	70.90 54	45.43 81	57.49 73	49.05 71	64.43 43	68.66 59	55.11 64	74.31 47	73.02 48	79.70 52	81.51 50
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
sasdasda		65.62 54	72.06 40	58.11 69	63.94 72	71.05 54	64.49 98	43.18 126	74.08 33	47.35 74	64.17 46	71.97 47	51.17 96	71.87 58	70.74 56	78.51 65	80.56 54

canonicalmvs		65.62 54	72.06 40	58.11 69	63.94 72	71.05 54	64.49 98	43.18 126	74.08 33	47.35 74	64.17 46	71.97 47	51.17 96	71.87 58	70.74 56	78.51 65	80.56 54

EIA-MVS		61.53 77	63.79 87	58.89 66	63.82 74	67.61 78	65.35 91	42.15 138	49.98 106	45.66 87	57.47 78	56.62 107	56.59 55	70.91 70	69.15 71	79.78 50	74.80 102

Anonymous202405211			60.60 102		63.44 75	66.71 92	61.00 115	47.23 69	50.62 104		36.85 191	60.63 92	43.03 140	69.17 86	67.72 91	75.41 106	72.54 113

ETV-MVS		63.23 65	66.08 72	59.91 59	63.13 76	68.13 70	67.62 64	44.62 92	53.39 87	46.23 83	58.74 71	58.19 100	57.45 46	73.60 50	71.38 54	80.39 45	79.13 61

casdiffmvs_mvg		65.26 57	69.48 59	60.33 56	62.99 77	69.34 62	69.80 56	45.27 83	63.38 59	51.11 63	65.12 40	69.75 55	53.51 75	71.74 60	68.86 76	79.33 56	78.19 72
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
gg-mvs-nofinetune		49.07 172	52.56 172	45.00 172	61.99 78	59.78 148	53.55 168	41.63 141	31.62 213	12.08 209	29.56 209	53.28 122	29.57 191	66.27 138	64.49 141	71.19 160	62.92 177

SPE-MVS-test		65.18 58	68.70 62	61.07 53	61.92 79	68.06 71	67.09 72	45.18 85	58.47 72	52.02 62	65.76 36	66.44 70	59.24 36	72.71 55	70.05 64	80.98 43	79.40 60

DCV-MVSNet		59.49 85	64.00 86	54.23 100	61.81 80	64.33 113	61.42 111	43.77 108	52.85 93	38.94 124	55.62 85	62.15 84	43.24 139	69.39 84	67.66 93	76.22 95	75.97 93

casdiffmvs		64.09 61	68.13 63	59.37 63	61.81 80	68.32 68	68.48 61	44.45 95	61.95 62	49.12 70	63.04 53	69.67 57	53.83 71	70.46 73	66.06 118	78.55 63	77.43 76
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CS-MVS		65.88 52	69.71 56	61.41 52	61.76 82	68.14 69	67.65 63	44.00 105	59.14 71	52.69 57	65.19 38	68.13 64	60.90 26	74.74 45	71.58 51	81.46 40	81.04 53

Anonymous20231211		57.71 107	60.79 99	54.13 102	61.68 83	65.81 99	60.81 116	43.70 112	51.97 99	39.67 119	34.82 196	63.59 76	43.31 137	68.55 96	66.63 109	75.59 104	74.13 107

IS_MVSNet		57.95 105	64.26 84	50.60 126	61.62 84	65.25 105	57.18 136	45.42 82	50.79 102	26.49 179	57.81 76	60.05 94	34.51 180	71.24 66	70.20 63	78.36 67	74.44 104

viewmanbaseed2359cas		63.67 62	67.42 64	59.30 64	61.34 85	67.42 82	70.01 55	40.50 155	59.53 67	52.60 58	62.56 58	67.34 69	54.44 66	70.33 77	66.93 102	76.91 83	77.82 75

NR-MVSNet		55.35 128	59.46 123	50.56 127	61.33 86	62.97 123	57.91 132	51.80 45	48.62 126	20.59 193	51.99 103	44.73 180	34.10 183	68.58 94	68.64 79	77.66 71	70.67 125

MVS_111021_LR		63.05 66	66.43 69	59.10 65	61.33 86	63.77 119	65.87 85	43.58 115	60.20 66	53.70 54	62.09 61	62.38 81	55.84 61	70.24 78	68.08 83	74.30 118	78.28 71

MGCFI-Net		61.46 78	69.72 55	51.83 121	61.00 88	66.16 96	56.50 143	40.73 151	73.98 35	35.18 137	64.23 45	71.42 49	42.45 142	69.22 85	64.01 145	75.09 112	79.03 63

EPP-MVSNet		59.39 86	65.45 76	52.32 118	60.96 89	67.70 76	58.42 129	44.75 90	49.71 108	27.23 173	59.03 70	62.20 83	43.34 136	70.71 71	69.13 72	79.25 59	79.63 59

TransMVSNet (Re)		51.92 154	55.38 152	47.88 158	60.95 90	59.90 147	53.95 163	45.14 86	39.47 191	24.85 183	43.87 162	46.51 161	29.15 192	67.55 117	65.23 132	73.26 136	65.16 168

gm-plane-assit		44.74 192	45.95 200	43.33 180	60.88 91	46.79 206	36.97 215	32.24 205	24.15 220	11.79 210	29.26 210	32.97 215	46.64 119	65.09 153	62.95 155	71.45 157	60.42 188

baseline1		54.48 137	58.69 129	49.57 133	60.63 92	58.29 163	55.70 152	44.95 88	49.20 114	29.62 161	54.77 89	54.75 116	35.29 177	67.15 125	64.08 143	71.21 159	62.58 181

test2506		55.82 123	59.57 121	51.46 122	60.39 93	64.55 111	58.69 127	48.87 64	53.91 83	26.99 174	48.97 117	41.72 192	37.71 163	70.96 68	69.49 67	76.08 98	67.37 148

ECVR-MVS		56.44 118	60.74 100	51.42 123	60.39 93	64.55 111	58.69 127	48.87 64	53.91 83	26.76 176	45.55 149	53.43 121	37.71 163	70.96 68	69.49 67	76.08 98	67.32 150

DI_MVS_pp		61.88 72	65.17 78	58.06 71	60.05 95	65.26 103	66.03 81	44.22 97	55.75 76	46.73 77	54.64 91	68.12 65	54.13 69	69.13 87	66.66 107	77.18 79	76.61 84

PVSNet_Blended_VisFu		63.65 63	66.92 65	59.83 60	60.03 96	73.44 47	66.33 78	48.95 63	52.20 98	50.81 65	56.07 81	60.25 93	53.56 73	73.23 53	70.01 65	79.30 57	83.24 43

UniMVSNet_NR-MVSNet		56.94 113	61.14 96	52.05 120	60.02 97	65.21 106	57.44 134	52.93 40	49.37 112	24.31 186	54.62 92	50.54 134	39.04 155	68.69 91	68.84 77	78.53 64	70.72 121

IterMVS-LS		58.30 101	61.39 95	54.71 98	59.92 98	58.40 160	59.42 121	43.64 113	48.71 123	40.25 117	57.53 77	58.55 99	52.15 90	65.42 151	65.34 129	72.85 138	75.77 94
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test1111		55.24 129	59.98 114	49.71 132	59.80 99	64.10 116	56.48 144	49.34 59	52.27 97	21.56 191	44.49 157	51.96 127	35.93 175	70.59 72	69.07 73	75.13 111	67.40 146

MVS_Test		62.40 71	66.23 71	57.94 74	59.77 100	64.77 109	66.50 77	41.76 139	57.26 74	49.33 68	62.68 56	67.47 68	53.50 77	68.57 95	66.25 115	76.77 85	76.58 85

FA-MVS(training)		60.00 84	63.14 90	56.33 88	59.50 101	64.30 114	65.15 93	38.75 170	56.20 75	45.77 85	53.08 95	56.45 108	52.10 91	69.04 89	67.67 92	76.69 86	75.27 101

TranMVSNet+NR-MVSNet		55.87 121	60.14 111	50.88 125	59.46 102	63.82 118	57.93 131	52.98 39	48.94 118	20.52 194	52.87 97	47.33 152	36.81 171	69.12 88	69.03 74	77.56 75	69.89 127

Fast-Effi-MVS+		60.36 81	63.35 88	56.87 84	58.70 103	65.86 98	65.08 94	37.11 179	53.00 92	45.36 89	52.12 102	56.07 113	56.27 57	71.28 65	69.42 69	78.71 61	75.69 96

IB-MVS	54.11 11	58.36 100	60.70 101	55.62 94	58.67 104	68.02 73	61.56 108	43.15 128	46.09 143	44.06 95	44.24 159	50.99 133	48.71 108	66.70 131	70.33 60	77.60 73	78.50 67
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
Fast-Effi-MVS+-dtu		56.30 119	59.29 125	52.82 115	58.64 105	64.89 107	65.56 89	32.89 202	45.80 146	35.04 139	45.89 144	54.14 118	49.41 104	67.16 124	66.45 114	75.37 108	70.69 123

CNLPA		62.78 68	66.31 70	58.65 67	58.47 106	68.41 67	65.98 83	41.22 147	78.02 22	56.04 38	46.65 132	59.50 96	57.50 45	69.67 82	65.27 131	72.70 144	76.67 83

tpm cat1		53.30 142	53.41 165	53.17 111	58.16 107	59.15 154	63.73 104	38.27 174	50.73 103	46.98 76	45.57 148	44.00 186	49.20 105	55.90 199	54.02 198	62.65 190	64.50 172

v1144		58.88 90	60.16 110	57.39 80	58.03 108	67.26 83	67.14 70	44.46 94	45.17 149	44.33 94	47.81 126	49.92 139	53.20 83	67.77 113	66.62 110	77.15 80	76.58 85

v10		59.17 89	60.60 102	57.50 79	57.95 109	66.73 89	67.09 72	44.11 98	46.85 137	45.42 88	48.18 125	51.07 130	53.63 72	67.84 111	66.59 111	76.79 84	76.92 81

v1192		58.51 94	59.66 117	57.17 81	57.82 110	67.72 75	66.21 80	44.83 89	44.15 157	43.49 97	46.68 131	47.94 143	53.55 74	67.39 120	66.51 112	77.13 81	77.20 79

viewmambaseed2359dif		60.40 80	64.15 85	56.03 90	57.79 111	63.53 121	65.91 84	41.64 140	54.98 79	46.47 80	60.16 66	64.71 73	50.76 98	66.25 139	62.83 157	73.61 129	76.57 87

v144192		58.23 103	59.40 124	56.87 84	57.56 112	66.89 87	65.70 86	45.01 87	44.06 158	42.88 99	46.61 133	48.09 142	53.49 78	66.94 129	65.90 123	76.61 87	77.29 77

v1921920		57.89 106	59.02 127	56.58 87	57.55 113	66.66 93	64.72 97	44.70 91	43.55 162	42.73 100	46.17 141	46.93 156	53.51 75	66.78 130	65.75 125	76.29 92	77.28 78

Vis-MVSNet (Re-imp)		50.37 162	57.73 141	41.80 187	57.53 114	54.35 177	45.70 196	45.24 84	49.80 107	13.43 207	58.23 75	56.42 109	20.11 208	62.96 159	63.36 151	68.76 169	58.96 193

CostFormer		56.57 116	59.13 126	53.60 105	57.52 115	61.12 136	66.94 74	35.95 184	53.44 85	44.68 92	55.87 84	54.44 117	48.21 111	60.37 172	58.33 179	68.27 171	70.33 126

thres400		52.38 148	55.51 150	48.74 144	57.49 116	60.10 146	55.45 155	43.54 116	42.90 169	26.72 177	43.34 169	45.03 178	36.61 172	66.20 141	64.53 140	72.66 145	66.43 154

thres600view7		51.91 155	55.14 154	48.14 154	57.43 117	60.18 144	54.60 161	43.73 110	42.61 173	25.20 182	43.10 172	44.47 183	35.19 178	66.36 135	63.28 152	72.66 145	66.01 161

thres200		52.39 147	55.37 153	48.90 142	57.39 118	60.18 144	55.60 153	43.73 110	42.93 168	27.41 171	43.35 168	45.09 175	36.61 172	66.36 135	63.92 147	72.66 145	65.78 163

baseline2		55.89 120	57.82 138	53.64 104	57.36 119	61.09 137	59.75 120	40.45 156	47.38 135	41.26 111	51.23 107	46.90 157	48.11 112	65.63 148	64.38 142	74.90 114	68.16 142

v8		58.88 90	60.57 104	56.92 83	57.35 120	65.69 100	66.69 76	42.64 132	47.89 132	45.77 85	49.04 116	52.98 123	52.77 84	67.51 118	65.57 126	76.26 94	75.30 100

thres100view900		52.04 152	54.81 158	48.80 143	57.31 121	59.33 151	55.30 157	42.92 131	42.85 170	27.81 169	43.00 173	45.06 176	36.99 169	64.74 154	63.51 149	72.47 148	65.21 167

tfpn200view9		52.53 145	55.51 150	49.06 140	57.31 121	60.24 143	55.42 156	43.77 108	42.85 170	27.81 169	43.00 173	45.06 176	37.32 167	66.38 134	64.54 139	72.71 143	66.54 153

v1240		57.55 108	58.63 131	56.29 89	57.30 123	66.48 94	63.77 103	44.56 93	42.77 172	42.48 102	45.64 147	46.28 163	53.46 79	66.32 137	65.80 124	76.16 96	77.13 80

dmvs_re		52.07 150	55.11 155	48.54 149	57.27 124	51.93 186	57.73 133	43.13 129	43.65 160	26.57 178	44.52 156	50.00 138	36.53 174	66.58 133	62.15 163	69.97 165	66.91 151

CHOSEN 1792x2688		55.85 122	58.01 136	53.33 107	57.26 125	62.82 125	63.29 107	41.55 142	46.65 139	38.34 125	34.55 197	53.50 119	52.43 87	67.10 126	67.56 95	67.13 175	73.92 110

PVSNet_BlendedMVS		61.63 75	64.82 79	57.91 76	57.21 126	67.55 79	63.47 105	46.08 75	54.72 80	52.46 59	58.59 72	60.73 89	51.82 94	70.46 73	65.20 133	76.44 90	76.50 89

PVSNet_Blended		61.63 75	64.82 79	57.91 76	57.21 126	67.55 79	63.47 105	46.08 75	54.72 80	52.46 59	58.59 72	60.73 89	51.82 94	70.46 73	65.20 133	76.44 90	76.50 89

v2v482		58.69 93	60.12 113	57.03 82	57.16 128	66.05 97	67.17 69	43.52 117	46.33 141	45.19 90	49.46 115	51.02 131	52.51 86	67.30 121	66.03 120	76.61 87	74.62 103

tfpnnormal		50.16 164	52.19 176	47.78 160	56.86 129	58.37 161	54.15 162	44.01 104	38.35 199	25.94 180	36.10 192	37.89 206	34.50 181	65.93 143	63.42 150	71.26 158	65.28 166

diffmvs_AUTHOR		61.79 73	66.80 66	55.95 91	56.69 130	63.92 117	67.27 67	41.28 145	59.32 69	46.43 81	63.31 51	68.30 62	50.56 99	68.30 98	66.06 118	73.48 130	78.36 69

diffmvs		61.64 74	66.55 68	55.90 92	56.63 131	63.71 120	67.13 71	41.27 146	59.49 68	46.70 78	63.93 50	68.01 66	50.46 100	67.30 121	65.51 127	73.24 137	77.87 74
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HyFIR lowres test		56.87 114	58.60 132	54.84 97	56.62 132	69.27 63	64.77 96	42.21 136	45.66 147	37.50 131	33.08 200	57.47 105	53.33 80	65.46 150	67.94 85	74.60 115	71.35 118

v7n		55.67 124	57.46 143	53.59 106	56.06 133	65.29 102	61.06 114	43.26 125	40.17 188	37.99 128	40.79 182	45.27 173	47.09 118	67.67 115	66.21 116	76.08 98	76.82 82

dps		50.42 161	51.20 182	49.51 134	55.88 134	56.07 173	53.73 164	38.89 166	43.66 159	40.36 116	45.66 146	37.63 208	45.23 127	59.05 175	56.18 183	62.94 189	60.16 189

CANet_DTU		58.88 90	64.68 82	52.12 119	55.77 135	66.75 88	63.92 102	37.04 180	53.32 88	37.45 132	59.81 67	61.81 85	44.43 131	68.25 100	67.47 96	74.12 120	75.33 99

WR-MVS		48.78 174	55.06 156	41.45 188	55.50 136	60.40 142	43.77 204	49.99 56	41.92 176	8.10 220	45.24 153	45.56 168	17.47 209	61.57 167	64.60 138	73.85 122	66.14 160

UniMVSNet (Re)		55.15 133	60.39 105	49.03 141	55.31 137	64.59 110	55.77 151	50.63 52	48.66 125	20.95 192	51.47 106	50.40 135	34.41 182	67.81 112	67.89 86	77.11 82	71.88 115

test-LLR		49.28 168	50.29 186	48.10 155	55.26 138	47.16 201	49.52 177	43.48 120	39.22 192	31.98 148	43.65 165	47.93 144	41.29 148	56.80 190	55.36 189	67.08 176	61.94 182

test0.0.03 1		43.15 197	46.95 199	38.72 196	55.26 138	50.56 190	42.48 207	43.48 120	38.16 201	15.11 203	35.07 195	44.69 181	16.47 211	55.95 198	54.34 197	59.54 197	49.87 211

GA-MVS		55.67 124	58.33 133	52.58 117	55.23 140	63.09 122	61.08 113	40.15 161	42.95 167	37.02 134	52.61 99	47.68 147	47.51 116	65.92 144	65.35 128	74.49 117	70.68 124

DTE-MVSNet		48.03 180	53.28 167	41.91 186	54.64 141	57.50 169	44.63 203	51.66 48	41.02 182	7.97 221	46.26 138	40.90 194	20.24 207	60.45 171	62.89 156	72.33 151	63.97 173

pmmvs4		54.66 136	56.07 147	53.00 112	54.63 142	57.08 171	60.43 118	44.10 99	51.69 100	40.55 114	46.55 136	44.79 179	45.95 124	62.54 161	63.66 148	72.36 150	66.20 158

DU-MVS		55.41 127	59.59 118	50.54 128	54.60 143	62.97 123	57.44 134	51.80 45	48.62 126	24.31 186	51.99 103	47.00 155	39.04 155	68.11 105	67.75 90	76.03 102	70.72 121

Baseline_NR-MVSNet		53.50 140	57.89 137	48.37 152	54.60 143	59.25 153	56.10 146	51.84 44	49.32 113	17.92 201	45.38 150	47.68 147	36.93 170	68.11 105	65.95 121	72.84 139	69.57 132

v148		55.58 126	57.61 142	53.20 109	54.59 145	61.86 128	61.18 112	38.70 171	44.30 156	42.25 104	47.53 127	50.24 137	48.73 107	65.15 152	62.61 161	73.79 123	71.61 117

PEN-MVS		49.21 170	54.32 160	43.24 182	54.33 146	59.26 152	47.04 190	51.37 49	41.67 178	9.97 215	46.22 139	41.80 191	22.97 205	60.52 170	64.03 144	73.73 124	66.75 152

pm-mvs1		51.02 158	55.55 149	45.73 167	54.16 147	58.52 158	50.92 173	42.56 133	40.32 186	25.67 181	43.66 164	50.34 136	30.06 190	65.85 145	63.97 146	70.99 161	66.21 157

EPNet_dtu		52.05 151	58.26 134	44.81 173	54.10 148	50.09 193	52.01 171	40.82 150	53.03 91	27.41 171	54.90 87	57.96 104	26.72 197	62.97 158	62.70 160	67.78 173	66.19 159
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tpm		48.82 173	51.27 181	45.96 166	54.10 148	47.35 200	56.05 147	30.23 206	46.70 138	43.21 98	52.54 100	47.55 150	37.28 168	54.11 204	50.50 207	54.90 207	60.12 190

CDS-MVSNet		52.42 146	57.06 145	47.02 163	53.92 150	58.30 162	55.50 154	46.47 73	42.52 174	29.38 163	49.50 114	52.85 124	28.49 195	66.70 131	66.89 103	68.34 170	62.63 180
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test20.03		40.38 206	44.20 206	35.92 204	53.73 151	49.05 194	38.54 213	43.49 119	32.55 210	9.54 216	27.88 212	39.12 202	12.24 216	56.28 195	54.69 194	57.96 202	49.83 212

Vis-MVSNet		58.48 96	65.70 75	50.06 131	53.40 152	67.20 84	60.24 119	43.32 123	48.83 120	30.23 158	62.38 59	61.61 87	40.35 151	71.03 67	69.77 66	72.82 140	79.11 62
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PLC	52.09 14	59.21 88	62.47 91	55.41 96	53.24 153	64.84 108	64.47 100	40.41 158	65.92 54	44.53 93	46.19 140	55.69 114	55.33 63	68.24 102	65.30 130	74.50 116	71.09 119
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
thisisatest0530		56.68 115	59.68 116	53.19 110	52.97 154	60.96 139	59.41 122	40.51 153	48.26 129	41.06 112	52.67 98	46.30 162	49.78 101	67.66 116	67.83 87	75.39 107	74.07 109

OMC-MVS		65.16 59	71.35 45	57.94 74	52.95 155	68.82 64	69.00 58	38.28 173	79.89 15	55.20 43	62.76 55	68.31 61	56.14 59	71.30 64	68.70 78	76.06 101	79.67 58

tpmrst		48.08 178	49.88 190	45.98 165	52.71 156	48.11 198	53.62 167	33.70 197	48.70 124	39.74 118	48.96 118	46.23 164	40.29 152	50.14 213	49.28 209	55.80 204	57.71 196

tttt0517		56.53 117	59.59 118	52.95 113	52.66 157	60.99 138	59.21 124	40.51 153	47.89 132	40.40 115	52.50 101	46.04 166	49.78 101	67.75 114	67.83 87	75.15 110	74.17 106

GBi-Net		55.20 130	60.25 107	49.31 135	52.42 158	61.44 131	57.03 137	44.04 101	49.18 115	30.47 154	48.28 121	58.19 100	38.22 158	68.05 108	66.96 99	73.69 125	69.65 129

test1		55.20 130	60.25 107	49.31 135	52.42 158	61.44 131	57.03 137	44.04 101	49.18 115	30.47 154	48.28 121	58.19 100	38.22 158	68.05 108	66.96 99	73.69 125	69.65 129

FMVSNet2		55.04 134	59.95 115	49.31 135	52.42 158	61.44 131	57.03 137	44.08 100	49.55 109	30.40 157	46.89 130	58.84 98	38.22 158	67.07 127	66.21 116	73.69 125	69.65 129

FMVSNet3		54.78 135	59.58 120	49.17 138	52.37 161	61.31 135	56.72 142	44.04 101	49.18 115	30.47 154	48.28 121	58.19 100	38.09 161	65.48 149	65.20 133	73.31 134	69.45 137

testgi		38.71 208	43.64 208	32.95 208	52.30 162	48.63 197	35.59 218	35.05 187	31.58 214	9.03 219	30.29 205	40.75 196	11.19 222	55.30 200	53.47 203	54.53 209	45.48 215

Anonymous20231206		42.28 198	45.89 201	38.07 198	51.96 163	48.98 195	43.66 205	38.81 169	38.74 196	14.32 206	26.74 213	40.90 194	20.94 206	56.64 193	54.67 195	58.71 198	54.59 200

pmmvs6		48.35 176	51.64 178	44.51 175	51.92 164	57.94 167	49.44 179	42.17 137	34.45 206	24.62 185	28.87 211	46.90 157	29.07 194	64.60 155	63.08 153	69.83 166	65.68 164

PatchmatchNet		49.92 166	51.29 180	48.32 153	51.83 165	51.86 187	53.38 169	37.63 178	47.90 131	40.83 113	48.54 120	45.30 171	45.19 128	56.86 189	53.99 200	61.08 195	54.57 201
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
WR-MVS_H		47.65 181	53.67 163	40.63 191	51.45 166	59.74 149	44.71 202	49.37 58	40.69 184	7.61 222	46.04 142	44.34 185	17.32 210	57.79 186	61.18 167	73.30 135	65.86 162

LTVRE_ROB	44.17 16	47.06 186	50.15 189	43.44 179	51.39 167	58.42 159	42.90 206	43.51 118	22.27 222	14.85 205	41.94 180	34.57 212	45.43 125	62.28 164	62.77 159	62.56 192	68.83 140
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
CP-MVSNet		48.37 175	53.53 164	42.34 184	51.35 168	58.01 166	46.56 191	50.54 53	41.62 179	10.61 211	46.53 137	40.68 197	23.18 203	58.71 180	61.83 164	71.81 154	67.36 149

PS-CasMVS		48.18 177	53.25 168	42.27 185	51.26 169	57.94 167	46.51 192	50.52 54	41.30 180	10.56 212	45.35 152	40.34 199	23.04 204	58.66 181	61.79 165	71.74 156	67.38 147

our_test_3					51.15 170	57.31 170	55.12 158

SCA		50.99 159	53.22 169	48.40 151	51.07 171	56.78 172	50.25 175	39.05 164	48.31 128	41.38 108	49.54 113	46.70 160	46.00 123	58.31 182	56.28 182	62.65 190	56.60 198

UniMVSNet_ETH3D		52.62 144	55.98 148	48.70 146	51.04 172	60.71 141	56.87 140	46.74 72	42.52 174	26.96 175	42.50 177	45.95 167	37.87 162	66.22 140	65.15 136	72.74 141	68.78 141

IterMVS-SCA-FT		52.18 149	57.75 140	45.68 168	51.01 173	62.06 127	55.10 159	34.75 188	44.85 150	32.86 146	51.13 109	51.22 129	48.74 106	62.47 162	61.51 166	51.61 214	71.02 120

FMVSNet1		54.08 138	58.68 130	48.71 145	50.90 174	61.35 134	56.73 141	43.94 106	45.91 145	29.32 164	42.72 175	56.26 112	37.70 165	68.05 108	66.96 99	73.69 125	69.50 133

pmmvs-eth3d		51.33 156	52.25 175	50.26 130	50.82 175	54.65 176	56.03 148	43.45 122	43.51 163	37.20 133	39.20 185	39.04 203	42.28 143	61.85 166	62.78 158	71.78 155	64.72 170

MVSTER		57.19 109	61.11 97	52.62 116	50.82 175	58.79 156	61.55 109	37.86 176	48.81 121	41.31 109	57.43 79	52.10 126	48.60 109	68.19 104	66.75 105	75.56 105	75.68 97

ambc			45.54 204		50.66 177	52.63 184	40.99 210		38.36 198	24.67 184	22.62 218	13.94 228	29.14 193	65.71 147	58.06 180	58.60 200	67.43 145

thisisatest0515		53.85 139	56.84 146	50.37 129	50.25 178	58.17 164	55.99 149	39.90 162	41.88 177	38.16 127	45.91 143	45.30 171	44.58 130	66.15 142	66.89 103	73.36 133	73.57 112

baseline		55.19 132	60.88 98	48.55 148	49.87 179	58.10 165	58.70 126	34.75 188	52.82 94	39.48 123	60.18 65	60.86 88	45.41 126	61.05 168	60.74 171	63.10 188	72.41 114

MDTV_nov1_ep13		50.32 163	52.43 174	47.86 159	49.87 179	54.70 175	58.10 130	34.29 192	45.59 148	37.71 129	47.44 128	47.42 151	41.86 145	58.07 185	55.21 191	65.34 182	58.56 194

IterMVS		53.45 141	57.12 144	49.17 138	49.23 181	60.93 140	59.05 125	34.63 190	44.53 152	33.22 142	51.09 110	51.01 132	48.38 110	62.43 163	60.79 170	70.54 163	69.05 139
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
COLMAP_ROB	46.52 15	51.99 153	54.86 157	48.63 147	49.13 182	61.73 130	60.53 117	36.57 181	53.14 89	32.95 145	37.10 189	38.68 204	40.49 150	65.72 146	63.08 153	72.11 153	64.60 171
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
CR-MVSNet		50.47 160	52.61 171	47.98 157	49.03 183	52.94 181	48.27 182	38.86 167	44.41 153	39.59 120	44.34 158	44.65 182	46.63 120	58.97 177	60.31 172	65.48 180	62.66 178

V42		56.97 112	60.14 111	53.28 108	48.16 184	62.78 126	66.30 79	37.93 175	47.44 134	42.68 101	48.19 124	52.59 125	51.90 92	67.46 119	65.94 122	72.72 142	76.55 88

MDTV_nov1_ep13_2view		47.62 182	49.72 191	45.18 171	48.05 185	53.70 179	54.90 160	33.80 196	39.90 190	29.79 160	38.85 186	41.89 190	39.17 154	58.99 176	55.55 188	65.34 182	59.17 192

EPMVS		44.66 193	47.86 197	40.92 190	47.97 186	44.70 210	47.58 187	33.27 199	48.11 130	29.58 162	49.65 112	44.38 184	34.65 179	51.71 208	47.90 211	52.49 212	48.57 213

RPMNet		46.41 187	48.72 193	43.72 177	47.77 187	52.94 181	46.02 195	33.92 194	44.41 153	31.82 151	36.89 190	37.42 209	37.41 166	53.88 205	54.02 198	65.37 181	61.47 184

TAPA-MVS	54.74 10	60.85 79	66.61 67	54.12 103	47.38 188	65.33 101	65.35 91	36.51 182	75.16 30	48.82 72	54.70 90	63.51 77	53.31 81	68.36 97	64.97 137	73.37 132	74.27 105
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SixPastTwentyTwo		47.55 183	50.25 188	44.41 176	47.30 189	54.31 178	47.81 185	40.36 159	33.76 207	19.93 196	43.75 163	32.77 216	42.07 144	59.82 173	60.94 169	68.98 167	66.37 156

TAMVS		44.02 195	49.18 192	37.99 199	47.03 190	45.97 207	45.04 199	28.47 210	39.11 194	20.23 195	43.22 171	48.52 140	28.49 195	58.15 184	57.95 181	58.71 198	51.36 204

UGNet		57.03 110	65.25 77	47.44 161	46.54 191	66.73 89	56.30 145	43.28 124	50.06 105	32.99 144	62.57 57	63.26 78	33.31 185	68.25 100	67.58 94	72.20 152	78.29 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
TSAR-MVS + COLMAP		62.65 69	69.90 54	54.19 101	46.31 192	66.73 89	65.49 90	41.36 144	76.57 24	46.31 82	76.80 17	56.68 106	53.27 82	69.50 83	66.65 108	72.40 149	76.36 91

PatchMatch-RL		50.11 165	51.56 179	48.43 150	46.23 193	51.94 185	50.21 176	38.62 172	46.62 140	37.51 130	42.43 178	39.38 201	52.24 89	60.98 169	59.56 175	65.76 179	60.01 191

CMPMVS	37.70 17	49.24 169	52.71 170	45.19 170	45.97 194	51.23 189	47.44 188	29.31 207	43.04 166	44.69 91	34.45 198	48.35 141	43.64 133	62.59 160	59.82 174	60.08 196	69.48 134
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmnet_mix02		40.48 205	43.80 207	36.61 202	45.79 195	40.45 215	42.12 208	33.18 200	40.30 187	24.11 188	38.76 187	37.11 210	24.30 201	52.97 206	46.66 215	50.17 215	50.33 208

pmmvs5		47.07 185	51.02 184	42.46 183	45.18 196	51.47 188	48.23 184	33.09 201	38.17 200	28.62 167	46.60 134	43.48 187	30.74 188	58.28 183	58.63 178	68.92 168	60.48 187

USDC		51.11 157	53.71 162	48.08 156	44.76 197	55.99 174	53.01 170	40.90 148	52.49 95	36.14 135	44.67 155	33.66 214	43.27 138	63.23 157	61.10 168	70.39 164	64.82 169

FC-MVSNet-test		39.65 207	48.35 195	29.49 211	44.43 198	39.28 219	30.23 221	40.44 157	43.59 161	3.12 228	53.00 96	42.03 189	10.02 224	55.09 201	54.77 193	48.66 216	50.71 206

ADS-MVSNet		40.67 203	43.38 209	37.50 200	44.36 199	39.79 217	42.09 209	32.67 204	44.34 155	28.87 166	40.76 183	40.37 198	30.22 189	48.34 218	45.87 216	46.81 218	44.21 217

new-patchmatchnet		33.24 214	37.20 215	28.62 213	44.32 200	38.26 220	29.68 222	36.05 183	31.97 212	6.33 224	26.59 214	27.33 219	11.12 223	50.08 214	41.05 219	44.23 219	45.15 216

MVS-HIRNet		42.24 199	41.15 212	43.51 178	44.06 201	40.74 213	35.77 217	35.35 185	35.38 205	38.34 125	25.63 215	38.55 205	43.48 135	50.77 210	47.03 213	64.07 184	49.98 209

PatchT		48.08 178	51.03 183	44.64 174	42.96 202	50.12 192	40.36 211	35.09 186	43.17 165	39.59 120	42.00 179	39.96 200	46.63 120	58.97 177	60.31 172	63.21 187	62.66 178

CVMVSNet		46.38 189	52.01 177	39.81 193	42.40 203	50.26 191	46.15 193	37.68 177	40.03 189	15.09 204	46.56 135	47.56 149	33.72 184	56.50 194	55.65 187	63.80 186	67.53 144

TinyColmap		47.08 184	47.56 198	46.52 164	42.35 204	53.44 180	51.77 172	40.70 152	43.44 164	31.92 150	29.78 208	23.72 224	45.04 129	61.99 165	59.54 176	67.35 174	61.03 185

ET-MVSNet_ETH3D		58.38 99	61.57 94	54.67 99	42.15 205	65.26 103	65.70 86	43.82 107	48.84 119	42.34 103	59.76 68	47.76 146	56.68 54	67.02 128	68.60 81	77.33 78	73.73 111

MIMVSNet		43.79 196	48.53 194	38.27 197	41.46 206	48.97 196	50.81 174	32.88 203	44.55 151	22.07 189	32.05 201	47.15 153	24.76 200	58.73 179	56.09 185	57.63 203	52.14 202

WB-MVS		29.70 216	35.40 217	23.05 216	40.96 207	39.59 218	18.79 225	40.20 160	25.26 218	1.88 231	33.33 199	21.97 226	3.36 225	48.69 217	44.60 217	33.11 223	34.39 219

N_pmnet		32.67 215	36.85 216	27.79 214	40.55 208	32.13 221	35.80 216	26.79 213	37.24 203	9.10 217	32.02 202	30.94 217	16.30 212	47.22 219	41.21 218	38.21 221	37.21 218

anonymousdsp		52.84 143	57.78 139	47.06 162	40.24 209	58.95 155	53.70 165	33.54 198	36.51 204	32.69 147	43.88 161	45.40 169	47.97 115	67.17 123	70.28 61	74.22 119	82.29 47

EU-MVSNet		40.63 204	45.65 203	34.78 207	39.11 210	46.94 204	40.02 212	34.03 193	33.50 208	10.37 213	35.57 194	37.80 207	23.65 202	51.90 207	50.21 208	61.49 194	63.62 176

FPMVS		38.36 209	40.41 213	35.97 203	38.92 211	39.85 216	45.50 197	25.79 216	41.13 181	18.70 198	30.10 206	24.56 222	31.86 187	49.42 215	46.80 214	55.04 205	51.03 205

TESTMET0.1,1		46.09 190	50.29 186	41.18 189	36.91 212	47.16 201	49.52 177	20.32 220	39.22 192	31.98 148	43.65 165	47.93 144	41.29 148	56.80 190	55.36 189	67.08 176	61.94 182

FMVSNet5		40.96 201	45.81 202	35.29 206	34.30 213	44.55 211	47.28 189	28.84 209	40.76 183	21.62 190	29.85 207	42.44 188	24.77 199	57.53 187	55.00 192	54.93 206	50.56 207

PMMVS		49.20 171	54.28 161	43.28 181	34.13 214	45.70 208	48.98 180	26.09 215	46.31 142	34.92 141	55.22 86	53.47 120	47.48 117	59.43 174	59.04 177	68.05 172	60.77 186

PMVS	27.84 18	33.81 213	35.28 218	32.09 209	34.13 214	24.81 224	32.51 220	26.48 214	26.41 217	19.37 197	23.76 216	24.02 223	25.18 198	50.78 209	47.24 212	54.89 208	49.95 210
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test-mter		45.30 191	50.37 185	39.38 194	33.65 216	46.99 203	47.59 186	18.59 221	38.75 195	28.00 168	43.28 170	46.82 159	41.50 147	57.28 188	55.78 186	66.93 178	63.70 175

CHOSEN 280x420		40.80 202	45.05 205	35.84 205	32.95 217	29.57 222	44.98 200	23.71 218	37.54 202	18.42 199	31.36 204	47.07 154	46.41 122	56.71 192	54.65 196	48.55 217	58.47 195

PM-MVS		44.55 194	48.13 196	40.37 192	32.85 218	46.82 205	46.11 194	29.28 208	40.48 185	29.99 159	39.98 184	34.39 213	41.80 146	56.08 197	53.88 202	62.19 193	65.31 165

TDRefinement		49.31 167	52.44 173	45.67 169	30.44 219	59.42 150	59.24 123	39.78 163	48.76 122	31.20 153	35.73 193	29.90 218	42.81 141	64.24 156	62.59 162	70.55 162	66.43 154

Gipuma		25.87 217	26.91 220	24.66 215	28.98 220	20.17 225	20.46 223	34.62 191	29.55 215	9.10 217	4.91 228	5.31 232	15.76 213	49.37 216	49.10 210	39.03 220	29.95 221
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MDA-MVSNet-bldmvs		41.36 200	43.15 210	39.27 195	28.74 221	52.68 183	44.95 201	40.84 149	32.89 209	18.13 200	31.61 203	22.09 225	38.97 157	50.45 212	56.11 184	64.01 185	56.23 199

E-PMN		15.09 220	13.19 224	17.30 218	27.80 222	12.62 228	7.81 229	27.54 211	14.62 226	3.19 226	6.89 225	2.52 235	15.09 214	15.93 224	20.22 223	22.38 224	19.53 224

MIMVSNet1		35.51 211	41.41 211	28.63 212	27.53 223	43.36 212	38.09 214	33.82 195	32.01 211	6.77 223	21.63 219	35.43 211	11.97 218	55.05 202	53.99 200	53.59 211	48.36 214

EMVS		14.49 221	12.45 225	16.87 220	27.02 224	12.56 229	8.13 228	27.19 212	15.05 225	3.14 227	6.69 226	2.67 234	15.08 215	14.60 226	18.05 224	20.67 225	17.56 226

pmmvs3		35.10 212	38.47 214	31.17 210	26.37 225	40.47 214	34.51 219	18.09 222	24.75 219	16.88 202	23.05 217	26.69 220	32.69 186	50.73 211	51.60 205	58.46 201	51.98 203

RPSCF		46.41 187	54.42 159	37.06 201	25.70 226	45.14 209	45.39 198	20.81 219	62.79 60	35.10 138	44.92 154	55.60 115	43.56 134	56.12 196	52.45 204	51.80 213	63.91 174

new_pmnet		23.19 218	28.17 219	17.37 217	17.03 227	24.92 223	19.66 224	16.16 224	27.05 216	4.42 225	20.77 220	19.20 227	12.19 217	37.71 220	36.38 220	34.77 222	31.17 220

PMMVS2		15.84 219	19.68 221	11.35 221	15.74 228	16.95 226	13.31 226	17.64 223	16.08 224	0.36 232	13.12 222	11.47 229	1.69 227	28.82 221	27.24 222	19.38 227	24.09 223

MVE	12.28 19	13.53 222	15.72 222	10.96 222	7.39 229	15.71 227	6.05 230	23.73 217	10.29 228	3.01 229	5.77 227	3.41 233	11.91 219	20.11 222	29.79 221	13.67 228	24.98 222
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				5.40 224	3.97 230	2.35 232	3.26 232	0.44 227	17.56 223	12.09 208	11.48 224	7.14 230	1.98 226	15.68 225	15.49 225	10.69 229

test_method		12.44 223	14.66 223	9.85 223	1.30 231	3.32 231	13.00 227	3.21 225	22.42 221	10.22 214	14.13 221	25.64 221	11.43 221	19.75 223	11.61 226	19.96 226	5.79 227

GG-mvs-BLEND		36.62 210	53.39 166	17.06 219	0.01 232	58.61 157	48.63 181	0.01 228	47.13 136	0.02 233	43.98 160	60.64 91	0.03 228	54.92 203	51.47 206	53.64 210	56.99 197

uanet_test		0.00 226	0.00 228	0.00 225	0.00 233	0.00 233	0.00 235	0.00 229	0.00 231	0.00 234	0.00 231	0.00 236	0.00 231	0.00 229	0.00 229	0.00 231	0.00 230

sosnet-low-res		0.00 226	0.00 228	0.00 225	0.00 233	0.00 233	0.00 235	0.00 229	0.00 231	0.00 234	0.00 231	0.00 236	0.00 231	0.00 229	0.00 229	0.00 231	0.00 230

sosnet		0.00 226	0.00 228	0.00 225	0.00 233	0.00 233	0.00 235	0.00 229	0.00 231	0.00 234	0.00 231	0.00 236	0.00 231	0.00 229	0.00 229	0.00 231	0.00 230

testmvs		0.01 224	0.02 226	0.00 225	0.00 233	0.00 233	0.01 234	0.00 229	0.01 229	0.00 234	0.03 230	0.00 236	0.01 229	0.01 228	0.01 227	0.00 231	0.06 229

test123		0.01 224	0.02 226	0.00 225	0.00 233	0.00 233	0.00 235	0.00 229	0.01 229	0.00 234	0.04 229	0.00 236	0.01 229	0.00 229	0.01 227	0.00 231	0.07 228

RE-MVS-def										33.01 143

9.14												81.81 13

MTAPA										65.14 4		80.20 20

MTMP										62.63 16		78.04 27

Patchmatch-RL test							1.04 233

NP-MVS									72.00 42

Patchmtry						47.61 199	48.27 182	38.86 167		39.59 120

DeepMVS_CX						6.95 230	5.98 231	2.25 226	11.73 227	2.07 230	11.85 223	5.43 231	11.75 220	11.40 227		8.10 230	18.38 225

High-resolution multi-view benchmark