Papers › GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View Stereo
GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View Stereo
Vibhas K. Vats, Sripad Joshi, David J. Crandall, Md. Alimoor Reza, Soon-Heung Jung
Traditional multi-view stereo (MVS) methods rely heavily on photometric and geometric consistency constraints, but newer machine learning-based MVS methods check geometric consistency across multiple source views only as a post-processing step. In this paper, we present a novel approach that explicitly encourages geometric consistency of reference view depth maps across multiple source views at different scales during learning (see Fig. 1). We find that adding this geometric consistency loss significantly accelerates learning by explicitly penalizing geometrically inconsistent pixels, reducing the training iteration requirements to nearly half that of other MVS methods. Our extensive experiments show that our approach achieves a new state-of-the-art on the DTU and BlendedMVS datasets, and competitive results on the Tanks and Temples benchmark. To the best of our knowledge, GC-MVSNet is the first attempt to enforce multi-view, multi-scale geometric consistency during learning.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Reconstruction | DTU | GC-MVSNet | Acc | 0.330 | #5 of 24 | Archive leaderboard | report |
| 3D Reconstruction | DTU | GC-MVSNet | Comp | 0.260 | #5 of 24 | Archive leaderboard | report |
| 3D Reconstruction | DTU | GC-MVSNet | Overall | 0.295 | #5 of 24 | Archive leaderboard | report |
| Point Clouds | Tanks and Temples | GC-MVSNet | Mean F1 (Advanced) | 38.74 | #8 of 21 | Archive leaderboard | report |
| Point Clouds | Tanks and Temples | GC-MVSNet | Mean F1 (Intermediate) | 62.74 | #8 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