Papers › GeoMVSNet: Learning Multi-View Stereo With Geometry Perception

GeoMVSNet: Learning Multi-View Stereo With Geometry Perception

1 Jan 2023CVPR 2023 1archive 2025-07-28

Zhe Zhang, Rui Peng, Yuxi Hu, Ronggang Wang

Recent cascade Multi-View Stereo (MVS) methods can efficiently estimate high-resolution depth maps through narrowing hypothesis ranges. However, previous methods ignored the vital geometric information embedded in coarse stages, leading to vulnerable cost matching and sub-optimal reconstruction results. In this paper, we propose a geometry awareness model, termed GeoMVSNet, to explicitly integrate geometric clues implied in coarse stages for delicate depth estimation. In particular, we design a two-branch geometry fusion network to extract geometric priors from coarse estimations to enhance structural feature extraction at finer stages. Besides, we embed the coarse probability volumes, which encode valuable depth distribution attributes, into the lightweight regularization network to further strengthen depth-wise geometry intuition. Meanwhile, we apply the frequency domain filtering to mitigate the negative impact of the high-frequency regions and adopt the curriculum learning strategy to progressively boost the geometry integration of the model. To intensify the full-scene geometry perception of our model, we present the depth distribution similarity loss based on the Gaussian-Mixture Model assumption. Extensive experiments on DTU and Tanks and Temples (T&T) datasets demonstrate that our GeoMVSNet achieves state-of-the-art results and ranks first on the T&T-Advanced set. Code is available at https://github.com/doubleZ0108/GeoMVSNet.

PaperPDFCode

Code

doublez0108/geomvsnet officialmentioned in paperpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D ReconstructionDepth EstimationPoint CloudsStereo Matching

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Reconstruction DTU GeoMVSNet Acc 0.331 #6 of 24 Archive leaderboard report
3D Reconstruction DTU GeoMVSNet Comp 0.259 #6 of 24 Archive leaderboard report
3D Reconstruction DTU GeoMVSNet Overall 0.295 #6 of 24 Archive leaderboard report
Point Clouds Tanks and Temples GeoMVSNet Mean F1 (Advanced) 41.52 #2 of 21 Archive leaderboard report
Point Clouds Tanks and Temples GeoMVSNet Mean F1 (Intermediate) 65.89 #2 of 21 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections