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.

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
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.
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

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

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

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
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
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

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

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
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.
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

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

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
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

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 68	77.84 20	77.37 17	82.21 27	85.85 27

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

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

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

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
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
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

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

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

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 79	53.81 53	59.51 70	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).
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
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
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

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

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
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

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 84	69.95 53	61.11 24	76.80 30	75.09 33	81.09 42	83.23 44

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	50.35 113	61.72 88	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
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

CLD-MVS		67.02 49	71.57 43	61.71 51	71.01 36	74.81 38	71.62 51	38.91 167	71.86 43	60.70 23	64.97 41	67.88 67	51.88 94	76.77 31	74.98 36	76.11 98	69.75 130
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
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 72	58.13 43	76.13 35	74.79 37	80.19 48	82.04 49

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 90	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
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 62	63.21 52	63.89 76	56.31 56	75.99 37	74.43 39	82.83 13	84.18 36

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 65	69.62 29	74.84 36	57.25 49	75.53 39	74.32 40	78.35 68	84.17 37

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 83	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
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

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
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	75.35 110	85.61 30

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	51.19 110	59.19 99	60.74 28	75.33 42	73.72 45	79.69 54	77.96 74

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 95	68.19 63	58.49 42	73.97 49	73.63 46	81.22 41	80.23 56

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

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 74	49.05 72	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
EPNet		65.14 60	69.54 57	60.00 58	66.61 56	67.67 77	67.53 66	55.32 24	62.67 61	46.22 85	67.74 33	65.93 73	48.07 116	72.17 57	72.12 49	76.28 94	78.47 68
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
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 67	60.73 64	72.65 46	59.43 35	73.32 52	72.12 49	79.19 60	85.99 26

CS-MVS		65.88 52	69.71 56	61.41 52	61.76 82	68.14 69	67.65 64	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

Effi-MVS+		63.28 65	65.96 74	60.17 57	64.26 67	68.06 71	68.78 61	45.71 79	54.08 83	46.64 80	55.92 85	63.13 80	55.94 60	70.38 77	71.43 52	79.68 55	78.70 65

QAPM		65.27 56	69.49 58	60.35 55	65.43 60	72.20 52	65.69 89	47.23 69	63.46 58	49.14 70	53.56 96	71.04 51	57.01 50	72.60 56	71.41 53	77.62 72	82.14 48

ETV-MVS		63.23 66	66.08 73	59.91 59	63.13 76	68.13 70	67.62 65	44.62 92	53.39 88	46.23 84	58.74 73	58.19 102	57.45 46	73.60 50	71.38 54	80.39 45	79.13 61

EC-MVSNet		67.01 50	70.27 53	63.21 47	67.21 52	70.47 58	69.01 58	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

sasdasda		65.62 54	72.06 40	58.11 70	63.94 72	71.05 54	64.49 100	43.18 126	74.08 33	47.35 75	64.17 46	71.97 47	51.17 98	71.87 58	70.74 56	78.51 65	80.56 54

canonicalmvs		65.62 54	72.06 40	58.11 70	63.94 72	71.05 54	64.49 100	43.18 126	74.08 33	47.35 75	64.17 46	71.97 47	51.17 98	71.87 58	70.74 56	78.51 65	80.56 54

EG-PatchMatch MVS		56.98 113	58.24 137	55.50 96	64.66 64	68.62 65	61.48 112	43.63 114	38.44 199	41.44 109	38.05 190	46.18 167	43.95 134	71.71 61	70.61 58	77.87 69	74.08 110

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 82	73.01 44	61.14 23	72.80 54	70.54 59	79.70 52	81.42 51

IB-MVS	54.11 11	58.36 102	60.70 103	55.62 95	58.67 105	68.02 73	61.56 110	43.15 128	46.09 145	44.06 96	44.24 161	50.99 135	48.71 110	66.70 133	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
anonymousdsp		52.84 145	57.78 141	47.06 164	40.24 211	58.95 157	53.70 167	33.54 200	36.51 206	32.69 149	43.88 163	45.40 171	47.97 117	67.17 125	70.28 61	74.22 120	82.29 47

ACMH	52.42 13	58.24 104	59.56 124	56.70 87	66.34 58	69.59 60	66.71 76	49.12 62	46.08 146	28.90 167	42.67 178	41.20 195	52.60 86	71.39 63	70.28 61	76.51 90	75.72 97
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IS_MVSNet		57.95 107	64.26 85	50.60 128	61.62 84	65.25 106	57.18 138	45.42 82	50.79 104	26.49 181	57.81 78	60.05 96	34.51 182	71.24 66	70.20 63	78.36 67	74.44 106

SPE-MVS-test		65.18 58	68.70 62	61.07 53	61.92 79	68.06 71	67.09 73	45.18 85	58.47 72	52.02 63	65.76 36	66.44 71	59.24 36	72.71 55	70.05 64	80.98 43	79.40 60

PVSNet_Blended_VisFu		63.65 63	66.92 66	59.83 60	60.03 97	73.44 47	66.33 79	48.95 63	52.20 100	50.81 66	56.07 83	60.25 95	53.56 74	73.23 53	70.01 65	79.30 57	83.24 43

Vis-MVSNet		58.48 98	65.70 76	50.06 133	53.40 154	67.20 85	60.24 121	43.32 123	48.83 122	30.23 160	62.38 59	61.61 89	40.35 153	71.03 67	69.77 66	72.82 142	79.11 62
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test2506		55.82 125	59.57 123	51.46 124	60.39 94	64.55 112	58.69 129	48.87 64	53.91 84	26.99 176	48.97 119	41.72 194	37.71 165	70.96 68	69.49 67	76.08 99	67.37 150

ECVR-MVS		56.44 120	60.74 102	51.42 125	60.39 94	64.55 112	58.69 129	48.87 64	53.91 84	26.76 178	45.55 151	53.43 123	37.71 165	70.96 68	69.49 67	76.08 99	67.32 152

Fast-Effi-MVS+		60.36 82	63.35 90	56.87 85	58.70 104	65.86 99	65.08 95	37.11 181	53.00 93	45.36 90	52.12 104	56.07 115	56.27 57	71.28 65	69.42 69	78.71 61	75.69 98

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 76	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
EIA-MVS		61.53 78	63.79 88	58.89 67	63.82 74	67.61 78	65.35 92	42.15 138	49.98 108	45.66 88	57.47 80	56.62 109	56.59 55	70.91 70	69.15 71	79.78 50	74.80 104

EPP-MVSNet		59.39 88	65.45 77	52.32 120	60.96 90	67.70 76	58.42 131	44.75 90	49.71 110	27.23 175	59.03 71	62.20 85	43.34 138	70.71 71	69.13 72	79.25 59	79.63 59

test1111		55.24 131	59.98 116	49.71 134	59.80 100	64.10 117	56.48 146	49.34 59	52.27 99	21.56 193	44.49 159	51.96 129	35.93 177	70.59 73	69.07 73	75.13 112	67.40 148

TranMVSNet+NR-MVSNet		55.87 123	60.14 113	50.88 127	59.46 103	63.82 119	57.93 133	52.98 39	48.94 120	20.52 196	52.87 99	47.33 154	36.81 173	69.12 89	69.03 74	77.56 75	69.89 129

ACMH+	53.71 12	59.26 89	60.28 108	58.06 72	64.17 69	68.46 66	67.51 67	50.93 50	52.46 98	35.83 138	40.83 183	45.12 176	52.32 89	69.88 82	69.00 75	77.59 74	76.21 94

casdiffmvs_mvg		65.26 57	69.48 59	60.33 56	62.99 77	69.34 62	69.80 57	45.27 83	63.38 59	51.11 64	65.12 40	69.75 55	53.51 76	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
UniMVSNet_NR-MVSNet		56.94 115	61.14 98	52.05 122	60.02 98	65.21 107	57.44 136	52.93 40	49.37 114	24.31 188	54.62 94	50.54 136	39.04 157	68.69 92	68.84 77	78.53 64	70.72 123

OMC-MVS		65.16 59	71.35 45	57.94 75	52.95 157	68.82 64	69.00 59	38.28 175	79.89 15	55.20 43	62.76 55	68.31 61	56.14 59	71.30 64	68.70 78	76.06 102	79.67 58

NR-MVSNet		55.35 130	59.46 125	50.56 129	61.33 86	62.97 124	57.91 134	51.80 45	48.62 128	20.59 195	51.99 105	44.73 182	34.10 185	68.58 95	68.64 79	77.66 71	70.67 127

OpenMVS	57.13 9	62.81 68	65.75 75	59.39 62	66.47 57	69.52 61	64.26 103	43.07 130	61.34 64	50.19 68	47.29 131	64.41 75	54.60 65	70.18 80	68.62 80	77.73 70	78.89 64

ET-MVSNet_ETH3D		58.38 101	61.57 96	54.67 100	42.15 207	65.26 104	65.70 87	43.82 107	48.84 121	42.34 104	59.76 69	47.76 148	56.68 54	67.02 130	68.60 81	77.33 78	73.73 113

FC-MVSNet-train		58.40 100	63.15 91	52.85 116	64.29 66	61.84 131	55.98 152	46.47 73	53.06 91	34.96 142	61.95 62	56.37 113	39.49 155	68.67 93	68.36 82	75.92 104	71.81 118

MVS_111021_LR		63.05 67	66.43 70	59.10 66	61.33 86	63.77 120	65.87 86	43.58 115	60.20 66	53.70 54	62.09 61	62.38 82	55.84 61	70.24 79	68.08 83	74.30 119	78.28 71

GeoE		62.43 71	64.79 82	59.68 61	64.15 70	67.17 86	68.80 60	44.42 96	55.65 78	47.38 74	51.54 107	62.51 81	54.04 71	69.99 81	68.07 84	79.28 58	78.57 66

HyFIR lowres test		56.87 116	58.60 134	54.84 98	56.62 134	69.27 63	64.77 97	42.21 136	45.66 149	37.50 133	33.08 202	57.47 107	53.33 81	65.46 152	67.94 85	74.60 116	71.35 120

UniMVSNet (Re)		55.15 135	60.39 107	49.03 143	55.31 139	64.59 111	55.77 153	50.63 52	48.66 127	20.95 194	51.47 108	50.40 137	34.41 184	67.81 113	67.89 86	77.11 82	71.88 117

thisisatest0530		56.68 117	59.68 118	53.19 112	52.97 156	60.96 141	59.41 124	40.51 154	48.26 131	41.06 114	52.67 100	46.30 164	49.78 103	67.66 117	67.83 87	75.39 108	74.07 111

tttt0517		56.53 119	59.59 120	52.95 115	52.66 159	60.99 140	59.21 126	40.51 154	47.89 134	40.40 117	52.50 103	46.04 168	49.78 103	67.75 115	67.83 87	75.15 111	74.17 108

MSDG		58.46 99	58.97 130	57.85 79	66.27 59	66.23 96	67.72 63	42.33 134	53.43 87	43.68 97	43.39 169	45.35 172	49.75 105	68.66 94	67.77 89	77.38 76	67.96 145

DU-MVS		55.41 129	59.59 120	50.54 130	54.60 145	62.97 124	57.44 136	51.80 45	48.62 128	24.31 188	51.99 105	47.00 157	39.04 157	68.11 106	67.75 90	76.03 103	70.72 123

Anonymous202405211			60.60 104		63.44 75	66.71 93	61.00 117	47.23 69	50.62 106		36.85 193	60.63 94	43.03 142	69.17 87	67.72 91	75.41 107	72.54 115

FA-MVS(training)		60.00 85	63.14 92	56.33 89	59.50 102	64.30 115	65.15 94	38.75 172	56.20 76	45.77 86	53.08 97	56.45 110	52.10 92	69.04 90	67.67 92	76.69 87	75.27 103

DCV-MVSNet		59.49 86	64.00 87	54.23 102	61.81 80	64.33 114	61.42 113	43.77 108	52.85 95	38.94 126	55.62 87	62.15 86	43.24 141	69.39 85	67.66 93	76.22 96	75.97 95

UGNet		57.03 112	65.25 78	47.44 163	46.54 193	66.73 90	56.30 147	43.28 124	50.06 107	32.99 146	62.57 57	63.26 79	33.31 187	68.25 101	67.58 94	72.20 154	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
CHOSEN 1792x2688		55.85 124	58.01 138	53.33 109	57.26 126	62.82 126	63.29 109	41.55 142	46.65 141	38.34 127	34.55 199	53.50 121	52.43 88	67.10 128	67.56 95	67.13 177	73.92 112

CANet_DTU		58.88 92	64.68 83	52.12 121	55.77 137	66.75 89	63.92 104	37.04 182	53.32 89	37.45 134	59.81 68	61.81 87	44.43 133	68.25 101	67.47 96	74.12 121	75.33 101

viewmacassd2359aftdt		63.43 64	66.95 65	59.32 64	61.27 88	67.48 81	70.15 55	40.54 153	57.82 73	52.27 61	60.49 65	66.81 70	54.58 66	70.67 72	67.39 97	77.08 83	78.02 73

UA-Net		58.50 97	64.68 83	51.30 126	66.97 53	67.13 87	53.68 168	45.65 80	49.51 113	31.58 154	62.91 54	68.47 60	35.85 178	68.20 104	67.28 98	74.03 122	69.24 140

Effi-MVS+-dtu		60.34 83	62.32 94	58.03 74	64.31 65	67.44 82	65.99 83	42.26 135	49.55 111	42.00 108	48.92 121	59.79 97	56.27 57	68.07 108	67.03 99	77.35 77	75.45 100

GBi-Net		55.20 132	60.25 109	49.31 137	52.42 160	61.44 133	57.03 139	44.04 101	49.18 117	30.47 156	48.28 123	58.19 102	38.22 160	68.05 109	66.96 100	73.69 127	69.65 131

test1		55.20 132	60.25 109	49.31 137	52.42 160	61.44 133	57.03 139	44.04 101	49.18 117	30.47 156	48.28 123	58.19 102	38.22 160	68.05 109	66.96 100	73.69 127	69.65 131

FMVSNet1		54.08 140	58.68 132	48.71 147	50.90 176	61.35 136	56.73 143	43.94 106	45.91 147	29.32 166	42.72 177	56.26 114	37.70 167	68.05 109	66.96 100	73.69 127	69.50 135

viewmanbaseed2359cas		63.67 62	67.42 64	59.30 65	61.34 85	67.42 83	70.01 56	40.50 156	59.53 67	52.60 58	62.56 58	67.34 69	54.44 67	70.33 78	66.93 103	76.91 84	77.82 76

thisisatest0515		53.85 141	56.84 148	50.37 131	50.25 180	58.17 166	55.99 151	39.90 163	41.88 179	38.16 129	45.91 145	45.30 173	44.58 132	66.15 144	66.89 104	73.36 135	73.57 114

CDS-MVSNet		52.42 148	57.06 147	47.02 165	53.92 152	58.30 164	55.50 156	46.47 73	42.52 176	29.38 165	49.50 116	52.85 126	28.49 197	66.70 133	66.89 104	68.34 172	62.63 182
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVSTER		57.19 111	61.11 99	52.62 118	50.82 177	58.79 158	61.55 111	37.86 178	48.81 123	41.31 111	57.43 81	52.10 128	48.60 111	68.19 105	66.75 106	75.56 106	75.68 99

MS-PatchMatch		58.19 106	60.20 111	55.85 94	65.17 62	64.16 116	64.82 96	41.48 143	50.95 103	42.17 106	45.38 152	56.42 111	48.08 115	68.30 99	66.70 107	73.39 133	69.46 138

DI_MVS_pp		61.88 73	65.17 79	58.06 72	60.05 96	65.26 104	66.03 82	44.22 97	55.75 77	46.73 78	54.64 93	68.12 65	54.13 70	69.13 88	66.66 108	77.18 79	76.61 86

TSAR-MVS + COLMAP		62.65 70	69.90 54	54.19 103	46.31 194	66.73 90	65.49 91	41.36 144	76.57 24	46.31 83	76.80 17	56.68 108	53.27 83	69.50 84	66.65 109	72.40 151	76.36 93

Anonymous20231211		57.71 109	60.79 101	54.13 104	61.68 83	65.81 100	60.81 118	43.70 112	51.97 101	39.67 121	34.82 198	63.59 77	43.31 139	68.55 97	66.63 110	75.59 105	74.13 109

v1144		58.88 92	60.16 112	57.39 81	58.03 109	67.26 84	67.14 71	44.46 94	45.17 151	44.33 95	47.81 128	49.92 141	53.20 84	67.77 114	66.62 111	77.15 80	76.58 87

v10		59.17 91	60.60 104	57.50 80	57.95 110	66.73 90	67.09 73	44.11 98	46.85 139	45.42 89	48.18 127	51.07 132	53.63 73	67.84 112	66.59 112	76.79 85	76.92 82

v1192		58.51 96	59.66 119	57.17 82	57.82 111	67.72 75	66.21 81	44.83 89	44.15 159	43.49 98	46.68 133	47.94 145	53.55 75	67.39 121	66.51 113	77.13 81	77.20 80

LS3D		60.20 84	61.70 95	58.45 69	64.18 68	67.77 74	67.19 69	48.84 66	61.67 63	41.27 112	45.89 146	51.81 130	54.18 69	68.78 91	66.50 114	75.03 114	69.48 136

Fast-Effi-MVS+-dtu		56.30 121	59.29 127	52.82 117	58.64 106	64.89 108	65.56 90	32.89 204	45.80 148	35.04 141	45.89 146	54.14 120	49.41 106	67.16 126	66.45 115	75.37 109	70.69 125

MVS_Test		62.40 72	66.23 72	57.94 75	59.77 101	64.77 110	66.50 78	41.76 139	57.26 75	49.33 69	62.68 56	67.47 68	53.50 78	68.57 96	66.25 116	76.77 86	76.58 87

v7n		55.67 126	57.46 145	53.59 108	56.06 135	65.29 103	61.06 116	43.26 125	40.17 190	37.99 130	40.79 184	45.27 175	47.09 120	67.67 116	66.21 117	76.08 99	76.82 83

FMVSNet2		55.04 136	59.95 117	49.31 137	52.42 160	61.44 133	57.03 139	44.08 100	49.55 111	30.40 159	46.89 132	58.84 100	38.22 160	67.07 129	66.21 117	73.69 127	69.65 131

diffmvs_AUTHOR		61.79 74	66.80 67	55.95 92	56.69 132	63.92 118	67.27 68	41.28 145	59.32 69	46.43 82	63.31 51	68.30 62	50.56 101	68.30 99	66.06 119	73.48 132	78.36 69

casdiffmvs		64.09 61	68.13 63	59.37 63	61.81 80	68.32 68	68.48 62	44.45 95	61.95 62	49.12 71	63.04 53	69.67 57	53.83 72	70.46 74	66.06 119	78.55 63	77.43 77
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
v2v482		58.69 95	60.12 115	57.03 83	57.16 130	66.05 98	67.17 70	43.52 117	46.33 143	45.19 91	49.46 117	51.02 133	52.51 87	67.30 123	66.03 121	76.61 88	74.62 105

Baseline_NR-MVSNet		53.50 142	57.89 139	48.37 154	54.60 145	59.25 155	56.10 148	51.84 44	49.32 115	17.92 203	45.38 152	47.68 149	36.93 172	68.11 106	65.95 122	72.84 141	69.57 134

V42		56.97 114	60.14 113	53.28 110	48.16 186	62.78 127	66.30 80	37.93 177	47.44 136	42.68 102	48.19 126	52.59 127	51.90 93	67.46 120	65.94 123	72.72 144	76.55 90

v144192		58.23 105	59.40 126	56.87 85	57.56 113	66.89 88	65.70 87	45.01 87	44.06 160	42.88 100	46.61 135	48.09 144	53.49 79	66.94 131	65.90 124	76.61 88	77.29 78

v1240		57.55 110	58.63 133	56.29 90	57.30 124	66.48 95	63.77 105	44.56 93	42.77 174	42.48 103	45.64 149	46.28 165	53.46 80	66.32 139	65.80 125	76.16 97	77.13 81

v1921920		57.89 108	59.02 129	56.58 88	57.55 114	66.66 94	64.72 98	44.70 91	43.55 164	42.73 101	46.17 143	46.93 158	53.51 76	66.78 132	65.75 126	76.29 93	77.28 79

v8		58.88 92	60.57 106	56.92 84	57.35 121	65.69 101	66.69 77	42.64 132	47.89 134	45.77 86	49.04 118	52.98 125	52.77 85	67.51 119	65.57 127	76.26 95	75.30 102

diffmvs		61.64 75	66.55 69	55.90 93	56.63 133	63.71 121	67.13 72	41.27 146	59.49 68	46.70 79	63.93 50	68.01 66	50.46 102	67.30 123	65.51 128	73.24 139	77.87 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
GA-MVS		55.67 126	58.33 135	52.58 119	55.23 142	63.09 123	61.08 115	40.15 162	42.95 169	37.02 136	52.61 101	47.68 149	47.51 118	65.92 146	65.35 129	74.49 118	70.68 126

IterMVS-LS		58.30 103	61.39 97	54.71 99	59.92 99	58.40 162	59.42 123	43.64 113	48.71 125	40.25 119	57.53 79	58.55 101	52.15 91	65.42 153	65.34 130	72.85 140	75.77 96
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PLC	52.09 14	59.21 90	62.47 93	55.41 97	53.24 155	64.84 109	64.47 102	40.41 159	65.92 54	44.53 94	46.19 142	55.69 116	55.33 63	68.24 103	65.30 131	74.50 117	71.09 121
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNLPA		62.78 69	66.31 71	58.65 68	58.47 107	68.41 67	65.98 84	41.22 147	78.02 22	56.04 38	46.65 134	59.50 98	57.50 45	69.67 83	65.27 132	72.70 146	76.67 85

TransMVSNet (Re)		51.92 156	55.38 154	47.88 160	60.95 91	59.90 149	53.95 165	45.14 86	39.47 193	24.85 185	43.87 164	46.51 163	29.15 194	67.55 118	65.23 133	73.26 138	65.16 170

PVSNet_BlendedMVS		61.63 76	64.82 80	57.91 77	57.21 127	67.55 79	63.47 107	46.08 75	54.72 81	52.46 59	58.59 74	60.73 91	51.82 95	70.46 74	65.20 134	76.44 91	76.50 91

PVSNet_Blended		61.63 76	64.82 80	57.91 77	57.21 127	67.55 79	63.47 107	46.08 75	54.72 81	52.46 59	58.59 74	60.73 91	51.82 95	70.46 74	65.20 134	76.44 91	76.50 91

FMVSNet3		54.78 137	59.58 122	49.17 140	52.37 163	61.31 137	56.72 144	44.04 101	49.18 117	30.47 156	48.28 123	58.19 102	38.09 163	65.48 151	65.20 134	73.31 136	69.45 139

UniMVSNet_ETH3D		52.62 146	55.98 150	48.70 148	51.04 174	60.71 143	56.87 142	46.74 72	42.52 176	26.96 177	42.50 179	45.95 169	37.87 164	66.22 142	65.15 137	72.74 143	68.78 143

TAPA-MVS	54.74 10	60.85 80	66.61 68	54.12 105	47.38 190	65.33 102	65.35 92	36.51 184	75.16 30	48.82 73	54.70 92	63.51 78	53.31 82	68.36 98	64.97 138	73.37 134	74.27 107
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
WR-MVS		48.78 176	55.06 158	41.45 190	55.50 138	60.40 144	43.77 206	49.99 56	41.92 178	8.10 222	45.24 155	45.56 170	17.47 211	61.57 169	64.60 139	73.85 123	66.14 162

tfpn200view9		52.53 147	55.51 152	49.06 142	57.31 122	60.24 145	55.42 158	43.77 108	42.85 172	27.81 171	43.00 175	45.06 178	37.32 169	66.38 136	64.54 140	72.71 145	66.54 155

thres400		52.38 150	55.51 152	48.74 146	57.49 117	60.10 148	55.45 157	43.54 116	42.90 171	26.72 179	43.34 171	45.03 180	36.61 174	66.20 143	64.53 141	72.66 147	66.43 156

gg-mvs-nofinetune		49.07 174	52.56 174	45.00 174	61.99 78	59.78 150	53.55 170	41.63 141	31.62 215	12.08 211	29.56 211	53.28 124	29.57 193	66.27 140	64.49 142	71.19 162	62.92 179

baseline2		55.89 122	57.82 140	53.64 106	57.36 120	61.09 139	59.75 122	40.45 157	47.38 137	41.26 113	51.23 109	46.90 159	48.11 114	65.63 150	64.38 143	74.90 115	68.16 144

baseline1		54.48 139	58.69 131	49.57 135	60.63 93	58.29 165	55.70 154	44.95 88	49.20 116	29.62 163	54.77 91	54.75 118	35.29 179	67.15 127	64.08 144	71.21 161	62.58 183

PEN-MVS		49.21 172	54.32 162	43.24 184	54.33 148	59.26 154	47.04 192	51.37 49	41.67 180	9.97 217	46.22 141	41.80 193	22.97 207	60.52 172	64.03 145	73.73 126	66.75 154

MGCFI-Net		61.46 79	69.72 55	51.83 123	61.00 89	66.16 97	56.50 145	40.73 151	73.98 35	35.18 139	64.23 45	71.42 49	42.45 144	69.22 86	64.01 146	75.09 113	79.03 63

viewmsd2359difaftdt		59.45 87	63.57 89	54.65 101	57.17 129	62.71 128	64.67 99	38.99 166	52.96 94	42.12 107	58.97 72	62.22 84	51.18 97	67.35 122	63.98 147	73.75 125	76.80 84

pm-mvs1		51.02 160	55.55 151	45.73 169	54.16 149	58.52 160	50.92 175	42.56 133	40.32 188	25.67 183	43.66 166	50.34 138	30.06 192	65.85 147	63.97 148	70.99 163	66.21 159

thres200		52.39 149	55.37 155	48.90 144	57.39 119	60.18 146	55.60 155	43.73 110	42.93 170	27.41 173	43.35 170	45.09 177	36.61 174	66.36 137	63.92 149	72.66 147	65.78 165

pmmvs4		54.66 138	56.07 149	53.00 114	54.63 144	57.08 173	60.43 120	44.10 99	51.69 102	40.55 116	46.55 138	44.79 181	45.95 126	62.54 163	63.66 150	72.36 152	66.20 160

thres100view900		52.04 154	54.81 160	48.80 145	57.31 122	59.33 153	55.30 159	42.92 131	42.85 172	27.81 171	43.00 175	45.06 178	36.99 171	64.74 156	63.51 151	72.47 150	65.21 169

tfpnnormal		50.16 166	52.19 178	47.78 162	56.86 131	58.37 163	54.15 164	44.01 104	38.35 201	25.94 182	36.10 194	37.89 208	34.50 183	65.93 145	63.42 152	71.26 160	65.28 168

Vis-MVSNet (Re-imp)		50.37 164	57.73 143	41.80 189	57.53 115	54.35 179	45.70 198	45.24 84	49.80 109	13.43 209	58.23 77	56.42 111	20.11 210	62.96 161	63.36 153	68.76 171	58.96 195

thres600view7		51.91 157	55.14 156	48.14 156	57.43 118	60.18 146	54.60 163	43.73 110	42.61 175	25.20 184	43.10 174	44.47 185	35.19 180	66.36 137	63.28 154	72.66 147	66.01 163

pmmvs6		48.35 178	51.64 180	44.51 177	51.92 166	57.94 169	49.44 181	42.17 137	34.45 208	24.62 187	28.87 213	46.90 159	29.07 196	64.60 157	63.08 155	69.83 168	65.68 166

COLMAP_ROB	46.52 15	51.99 155	54.86 159	48.63 149	49.13 184	61.73 132	60.53 119	36.57 183	53.14 90	32.95 147	37.10 191	38.68 206	40.49 152	65.72 148	63.08 155	72.11 155	64.60 173
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
gm-plane-assit		44.74 194	45.95 202	43.33 182	60.88 92	46.79 208	36.97 217	32.24 207	24.15 222	11.79 212	29.26 212	32.97 217	46.64 121	65.09 155	62.95 157	71.45 159	60.42 190

DTE-MVSNet		48.03 182	53.28 169	41.91 188	54.64 143	57.50 171	44.63 205	51.66 48	41.02 184	7.97 223	46.26 140	40.90 196	20.24 209	60.45 173	62.89 158	72.33 153	63.97 175

viewmambaseed2359dif		60.40 81	64.15 86	56.03 91	57.79 112	63.53 122	65.91 85	41.64 140	54.98 80	46.47 81	60.16 67	64.71 74	50.76 100	66.25 141	62.83 159	73.61 131	76.57 89

pmmvs-eth3d		51.33 158	52.25 177	50.26 132	50.82 177	54.65 178	56.03 150	43.45 122	43.51 165	37.20 135	39.20 187	39.04 205	42.28 145	61.85 168	62.78 160	71.78 157	64.72 172

LTVRE_ROB	44.17 16	47.06 188	50.15 191	43.44 181	51.39 169	58.42 161	42.90 208	43.51 118	22.27 224	14.85 207	41.94 182	34.57 214	45.43 127	62.28 166	62.77 161	62.56 194	68.83 142
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
EPNet_dtu		52.05 153	58.26 136	44.81 175	54.10 150	50.09 195	52.01 173	40.82 150	53.03 92	27.41 173	54.90 89	57.96 106	26.72 199	62.97 160	62.70 162	67.78 175	66.19 161
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
v148		55.58 128	57.61 144	53.20 111	54.59 147	61.86 130	61.18 114	38.70 173	44.30 158	42.25 105	47.53 129	50.24 139	48.73 109	65.15 154	62.61 163	73.79 124	71.61 119

TDRefinement		49.31 169	52.44 175	45.67 171	30.44 221	59.42 152	59.24 125	39.78 164	48.76 124	31.20 155	35.73 195	29.90 220	42.81 143	64.24 158	62.59 164	70.55 164	66.43 156

dmvs_re		52.07 152	55.11 157	48.54 151	57.27 125	51.93 188	57.73 135	43.13 129	43.65 162	26.57 180	44.52 158	50.00 140	36.53 176	66.58 135	62.15 165	69.97 167	66.91 153

CP-MVSNet		48.37 177	53.53 166	42.34 186	51.35 170	58.01 168	46.56 193	50.54 53	41.62 181	10.61 213	46.53 139	40.68 199	23.18 205	58.71 182	61.83 166	71.81 156	67.36 151

PS-CasMVS		48.18 179	53.25 170	42.27 187	51.26 171	57.94 169	46.51 194	50.52 54	41.30 182	10.56 214	45.35 154	40.34 201	23.04 206	58.66 183	61.79 167	71.74 158	67.38 149

IterMVS-SCA-FT		52.18 151	57.75 142	45.68 170	51.01 175	62.06 129	55.10 161	34.75 190	44.85 152	32.86 148	51.13 111	51.22 131	48.74 108	62.47 164	61.51 168	51.61 216	71.02 122

WR-MVS_H		47.65 183	53.67 165	40.63 193	51.45 168	59.74 151	44.71 204	49.37 58	40.69 186	7.61 224	46.04 144	44.34 187	17.32 212	57.79 188	61.18 169	73.30 137	65.86 164

USDC		51.11 159	53.71 164	48.08 158	44.76 199	55.99 176	53.01 172	40.90 148	52.49 97	36.14 137	44.67 157	33.66 216	43.27 140	63.23 159	61.10 170	70.39 166	64.82 171

SixPastTwentyTwo		47.55 185	50.25 190	44.41 178	47.30 191	54.31 180	47.81 187	40.36 160	33.76 209	19.93 198	43.75 165	32.77 218	42.07 146	59.82 175	60.94 171	68.98 169	66.37 158

IterMVS		53.45 143	57.12 146	49.17 140	49.23 183	60.93 142	59.05 127	34.63 192	44.53 154	33.22 144	51.09 112	51.01 134	48.38 112	62.43 165	60.79 172	70.54 165	69.05 141
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
baseline		55.19 134	60.88 100	48.55 150	49.87 181	58.10 167	58.70 128	34.75 190	52.82 96	39.48 125	60.18 66	60.86 90	45.41 128	61.05 170	60.74 173	63.10 190	72.41 116

CR-MVSNet		50.47 162	52.61 173	47.98 159	49.03 185	52.94 183	48.27 184	38.86 169	44.41 155	39.59 122	44.34 160	44.65 184	46.63 122	58.97 179	60.31 174	65.48 182	62.66 180

PatchT		48.08 180	51.03 185	44.64 176	42.96 204	50.12 194	40.36 213	35.09 188	43.17 167	39.59 122	42.00 181	39.96 202	46.63 122	58.97 179	60.31 174	63.21 189	62.66 180

CMPMVS	37.70 17	49.24 171	52.71 172	45.19 172	45.97 196	51.23 191	47.44 190	29.31 209	43.04 168	44.69 92	34.45 200	48.35 143	43.64 135	62.59 162	59.82 176	60.08 198	69.48 136
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
PatchMatch-RL		50.11 167	51.56 181	48.43 152	46.23 195	51.94 187	50.21 178	38.62 174	46.62 142	37.51 132	42.43 180	39.38 203	52.24 90	60.98 171	59.56 177	65.76 181	60.01 193

TinyColmap		47.08 186	47.56 200	46.52 166	42.35 206	53.44 182	51.77 174	40.70 152	43.44 166	31.92 152	29.78 210	23.72 226	45.04 131	61.99 167	59.54 178	67.35 176	61.03 187

PMMVS		49.20 173	54.28 163	43.28 183	34.13 216	45.70 210	48.98 182	26.09 217	46.31 144	34.92 143	55.22 88	53.47 122	47.48 119	59.43 176	59.04 179	68.05 174	60.77 188

pmmvs5		47.07 187	51.02 186	42.46 185	45.18 198	51.47 190	48.23 186	33.09 203	38.17 202	28.62 169	46.60 136	43.48 189	30.74 190	58.28 185	58.63 180	68.92 170	60.48 189

CostFormer		56.57 118	59.13 128	53.60 107	57.52 116	61.12 138	66.94 75	35.95 186	53.44 86	44.68 93	55.87 86	54.44 119	48.21 113	60.37 174	58.33 181	68.27 173	70.33 128

ambc			45.54 206		50.66 179	52.63 186	40.99 212		38.36 200	24.67 186	22.62 220	13.94 230	29.14 195	65.71 149	58.06 182	58.60 202	67.43 147

TAMVS		44.02 197	49.18 194	37.99 201	47.03 192	45.97 209	45.04 201	28.47 212	39.11 196	20.23 197	43.22 173	48.52 142	28.49 197	58.15 186	57.95 183	58.71 200	51.36 206

SCA		50.99 161	53.22 171	48.40 153	51.07 173	56.78 174	50.25 177	39.05 165	48.31 130	41.38 110	49.54 115	46.70 162	46.00 125	58.31 184	56.28 184	62.65 192	56.60 200

dps		50.42 163	51.20 184	49.51 136	55.88 136	56.07 175	53.73 166	38.89 168	43.66 161	40.36 118	45.66 148	37.63 210	45.23 129	59.05 177	56.18 185	62.94 191	60.16 191

MDA-MVSNet-bldmvs		41.36 202	43.15 212	39.27 197	28.74 223	52.68 185	44.95 203	40.84 149	32.89 211	18.13 202	31.61 205	22.09 227	38.97 159	50.45 214	56.11 186	64.01 187	56.23 201

MIMVSNet		43.79 198	48.53 196	38.27 199	41.46 208	48.97 198	50.81 176	32.88 205	44.55 153	22.07 191	32.05 203	47.15 155	24.76 202	58.73 181	56.09 187	57.63 205	52.14 204

test-mter		45.30 193	50.37 187	39.38 196	33.65 218	46.99 205	47.59 188	18.59 223	38.75 197	28.00 170	43.28 172	46.82 161	41.50 149	57.28 190	55.78 188	66.93 180	63.70 177

CVMVSNet		46.38 191	52.01 179	39.81 195	42.40 205	50.26 193	46.15 195	37.68 179	40.03 191	15.09 206	46.56 137	47.56 151	33.72 186	56.50 196	55.65 189	63.80 188	67.53 146

MDTV_nov1_ep13_2view		47.62 184	49.72 193	45.18 173	48.05 187	53.70 181	54.90 162	33.80 198	39.90 192	29.79 162	38.85 188	41.89 192	39.17 156	58.99 178	55.55 190	65.34 184	59.17 194

test-LLR		49.28 170	50.29 188	48.10 157	55.26 140	47.16 203	49.52 179	43.48 120	39.22 194	31.98 150	43.65 167	47.93 146	41.29 150	56.80 192	55.36 191	67.08 178	61.94 184

TESTMET0.1,1		46.09 192	50.29 188	41.18 191	36.91 214	47.16 203	49.52 179	20.32 222	39.22 194	31.98 150	43.65 167	47.93 146	41.29 150	56.80 192	55.36 191	67.08 178	61.94 184

MDTV_nov1_ep13		50.32 165	52.43 176	47.86 161	49.87 181	54.70 177	58.10 132	34.29 194	45.59 150	37.71 131	47.44 130	47.42 153	41.86 147	58.07 187	55.21 193	65.34 184	58.56 196

FMVSNet5		40.96 203	45.81 204	35.29 208	34.30 215	44.55 213	47.28 191	28.84 211	40.76 185	21.62 192	29.85 209	42.44 190	24.77 201	57.53 189	55.00 194	54.93 208	50.56 209

FC-MVSNet-test		39.65 209	48.35 197	29.49 213	44.43 200	39.28 221	30.23 223	40.44 158	43.59 163	3.12 230	53.00 98	42.03 191	10.02 226	55.09 203	54.77 195	48.66 218	50.71 208

test20.03		40.38 208	44.20 208	35.92 206	53.73 153	49.05 196	38.54 215	43.49 119	32.55 212	9.54 218	27.88 214	39.12 204	12.24 218	56.28 197	54.69 196	57.96 204	49.83 214

Anonymous20231206		42.28 200	45.89 203	38.07 200	51.96 165	48.98 197	43.66 207	38.81 171	38.74 198	14.32 208	26.74 215	40.90 196	20.94 208	56.64 195	54.67 197	58.71 200	54.59 202

CHOSEN 280x420		40.80 204	45.05 207	35.84 207	32.95 219	29.57 224	44.98 202	23.71 220	37.54 204	18.42 201	31.36 206	47.07 156	46.41 124	56.71 194	54.65 198	48.55 219	58.47 197

test0.0.03 1		43.15 199	46.95 201	38.72 198	55.26 140	50.56 192	42.48 209	43.48 120	38.16 203	15.11 205	35.07 197	44.69 183	16.47 213	55.95 200	54.34 199	59.54 199	49.87 213

tpm cat1		53.30 144	53.41 167	53.17 113	58.16 108	59.15 156	63.73 106	38.27 176	50.73 105	46.98 77	45.57 150	44.00 188	49.20 107	55.90 201	54.02 200	62.65 192	64.50 174

RPMNet		46.41 189	48.72 195	43.72 179	47.77 189	52.94 183	46.02 197	33.92 196	44.41 155	31.82 153	36.89 192	37.42 211	37.41 168	53.88 207	54.02 200	65.37 183	61.47 186

MIMVSNet1		35.51 213	41.41 213	28.63 214	27.53 225	43.36 214	38.09 216	33.82 197	32.01 213	6.77 225	21.63 221	35.43 213	11.97 220	55.05 204	53.99 202	53.59 213	48.36 216

PatchmatchNet		49.92 168	51.29 182	48.32 155	51.83 167	51.86 189	53.38 171	37.63 180	47.90 133	40.83 115	48.54 122	45.30 173	45.19 130	56.86 191	53.99 202	61.08 197	54.57 203
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
PM-MVS		44.55 196	48.13 198	40.37 194	32.85 220	46.82 207	46.11 196	29.28 210	40.48 187	29.99 161	39.98 186	34.39 215	41.80 148	56.08 199	53.88 204	62.19 195	65.31 167

testgi		38.71 210	43.64 210	32.95 210	52.30 164	48.63 199	35.59 220	35.05 189	31.58 216	9.03 221	30.29 207	40.75 198	11.19 224	55.30 202	53.47 205	54.53 211	45.48 217

RPSCF		46.41 189	54.42 161	37.06 203	25.70 228	45.14 211	45.39 200	20.81 221	62.79 60	35.10 140	44.92 156	55.60 117	43.56 136	56.12 198	52.45 206	51.80 215	63.91 176

pmmvs3		35.10 214	38.47 216	31.17 212	26.37 227	40.47 216	34.51 221	18.09 224	24.75 221	16.88 204	23.05 219	26.69 222	32.69 188	50.73 213	51.60 207	58.46 203	51.98 205

GG-mvs-BLEND		36.62 212	53.39 168	17.06 221	0.01 234	58.61 159	48.63 183	0.01 230	47.13 138	0.02 235	43.98 162	60.64 93	0.03 230	54.92 205	51.47 208	53.64 212	56.99 199

tpm		48.82 175	51.27 183	45.96 168	54.10 150	47.35 202	56.05 149	30.23 208	46.70 140	43.21 99	52.54 102	47.55 152	37.28 170	54.11 206	50.50 209	54.90 209	60.12 192

EU-MVSNet		40.63 206	45.65 205	34.78 209	39.11 212	46.94 206	40.02 214	34.03 195	33.50 210	10.37 215	35.57 196	37.80 209	23.65 204	51.90 209	50.21 210	61.49 196	63.62 178

tpmrst		48.08 180	49.88 192	45.98 167	52.71 158	48.11 200	53.62 169	33.70 199	48.70 126	39.74 120	48.96 120	46.23 166	40.29 154	50.14 215	49.28 211	55.80 206	57.71 198

Gipuma		25.87 219	26.91 222	24.66 217	28.98 222	20.17 227	20.46 225	34.62 193	29.55 217	9.10 219	4.91 230	5.31 234	15.76 215	49.37 218	49.10 212	39.03 222	29.95 223
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
EPMVS		44.66 195	47.86 199	40.92 192	47.97 188	44.70 212	47.58 189	33.27 201	48.11 132	29.58 164	49.65 114	44.38 186	34.65 181	51.71 210	47.90 213	52.49 214	48.57 215

PMVS	27.84 18	33.81 215	35.28 220	32.09 211	34.13 216	24.81 226	32.51 222	26.48 216	26.41 219	19.37 199	23.76 218	24.02 225	25.18 200	50.78 211	47.24 214	54.89 210	49.95 212
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVS-HIRNet		42.24 201	41.15 214	43.51 180	44.06 203	40.74 215	35.77 219	35.35 187	35.38 207	38.34 127	25.63 217	38.55 207	43.48 137	50.77 212	47.03 215	64.07 186	49.98 211

FPMVS		38.36 211	40.41 215	35.97 205	38.92 213	39.85 218	45.50 199	25.79 218	41.13 183	18.70 200	30.10 208	24.56 224	31.86 189	49.42 217	46.80 216	55.04 207	51.03 207

pmnet_mix02		40.48 207	43.80 209	36.61 204	45.79 197	40.45 217	42.12 210	33.18 202	40.30 189	24.11 190	38.76 189	37.11 212	24.30 203	52.97 208	46.66 217	50.17 217	50.33 210

ADS-MVSNet		40.67 205	43.38 211	37.50 202	44.36 201	39.79 219	42.09 211	32.67 206	44.34 157	28.87 168	40.76 185	40.37 200	30.22 191	48.34 220	45.87 218	46.81 220	44.21 219

WB-MVS		29.70 218	35.40 219	23.05 218	40.96 209	39.59 220	18.79 227	40.20 161	25.26 220	1.88 233	33.33 201	21.97 228	3.36 227	48.69 219	44.60 219	33.11 225	34.39 221

N_pmnet		32.67 217	36.85 218	27.79 216	40.55 210	32.13 223	35.80 218	26.79 215	37.24 205	9.10 219	32.02 204	30.94 219	16.30 214	47.22 221	41.21 220	38.21 223	37.21 220

new-patchmatchnet		33.24 216	37.20 217	28.62 215	44.32 202	38.26 222	29.68 224	36.05 185	31.97 214	6.33 226	26.59 216	27.33 221	11.12 225	50.08 216	41.05 221	44.23 221	45.15 218

new_pmnet		23.19 220	28.17 221	17.37 219	17.03 229	24.92 225	19.66 226	16.16 226	27.05 218	4.42 227	20.77 222	19.20 229	12.19 219	37.71 222	36.38 222	34.77 224	31.17 222

MVE	12.28 19	13.53 224	15.72 224	10.96 224	7.39 231	15.71 229	6.05 232	23.73 219	10.29 230	3.01 231	5.77 229	3.41 235	11.91 221	20.11 224	29.79 223	13.67 230	24.98 224
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMMVS2		15.84 221	19.68 223	11.35 223	15.74 230	16.95 228	13.31 228	17.64 225	16.08 226	0.36 234	13.12 224	11.47 231	1.69 229	28.82 223	27.24 224	19.38 229	24.09 225

E-PMN		15.09 222	13.19 226	17.30 220	27.80 224	12.62 230	7.81 231	27.54 213	14.62 228	3.19 228	6.89 227	2.52 237	15.09 216	15.93 226	20.22 225	22.38 226	19.53 226

EMVS		14.49 223	12.45 227	16.87 222	27.02 226	12.56 231	8.13 230	27.19 214	15.05 227	3.14 229	6.69 228	2.67 236	15.08 217	14.60 228	18.05 226	20.67 227	17.56 228

tmp_tt				5.40 226	3.97 232	2.35 234	3.26 234	0.44 229	17.56 225	12.09 210	11.48 226	7.14 232	1.98 228	15.68 227	15.49 227	10.69 231

test_method		12.44 225	14.66 225	9.85 225	1.30 233	3.32 233	13.00 229	3.21 227	22.42 223	10.22 216	14.13 223	25.64 223	11.43 223	19.75 225	11.61 228	19.96 228	5.79 229

testmvs		0.01 226	0.02 228	0.00 227	0.00 235	0.00 235	0.01 236	0.00 231	0.01 231	0.00 236	0.03 232	0.00 238	0.01 231	0.01 230	0.01 229	0.00 233	0.06 231

test123		0.01 226	0.02 228	0.00 227	0.00 235	0.00 235	0.00 237	0.00 231	0.01 231	0.00 236	0.04 231	0.00 238	0.01 231	0.00 231	0.01 229	0.00 233	0.07 230

uanet_test		0.00 228	0.00 230	0.00 227	0.00 235	0.00 235	0.00 237	0.00 231	0.00 233	0.00 236	0.00 233	0.00 238	0.00 233	0.00 231	0.00 231	0.00 233	0.00 232

sosnet-low-res		0.00 228	0.00 230	0.00 227	0.00 235	0.00 235	0.00 237	0.00 231	0.00 233	0.00 236	0.00 233	0.00 238	0.00 233	0.00 231	0.00 231	0.00 233	0.00 232

sosnet		0.00 228	0.00 230	0.00 227	0.00 235	0.00 235	0.00 237	0.00 231	0.00 233	0.00 236	0.00 233	0.00 238	0.00 233	0.00 231	0.00 231	0.00 233	0.00 232

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
RE-MVS-def										33.01 145

9.14												81.81 13

SR-MVS					71.46 34			54.67 28				81.54 14

our_test_3					51.15 172	57.31 172	55.12 160

MTAPA										65.14 4		80.20 20

MTMP										62.63 16		78.04 27

Patchmatch-RL test							1.04 235

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

mPP-MVS					71.67 33							74.36 41

NP-MVS									72.00 42

Patchmtry						47.61 201	48.27 184	38.86 169		39.59 122

DeepMVS_CX						6.95 232	5.98 233	2.25 228	11.73 229	2.07 232	11.85 225	5.43 233	11.75 222	11.40 229		8.10 232	18.38 227

High-resolution multi-view benchmark