Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells

by   Xinyi Ye, et al.

Learning-based multi-view stereo (MVS) methods deal with predicting accurate depth maps to achieve an accurate and complete 3D representation. Despite the excellent performance, existing methods ignore the fact that a suitable depth geometry is also critical in MVS. In this paper, we demonstrate that different depth geometries have significant performance gaps, even using the same depth prediction error. Therefore, we introduce an ideal depth geometry composed of Saddle-Shaped Cells, whose predicted depth map oscillates upward and downward around the ground-truth surface, rather than maintaining a continuous and smooth depth plane. To achieve it, we develop a coarse-to-fine framework called Dual-MVSNet (DMVSNet), which can produce an oscillating depth plane. Technically, we predict two depth values for each pixel (Dual-Depth), and propose a novel loss function and a checkerboard-shaped selecting strategy to constrain the predicted depth geometry. Compared to existing methods,DMVSNet achieves a high rank on the DTU benchmark and obtains the top performance on challenging scenes of Tanks and Temples, demonstrating its strong performance and generalization ability. Our method also points to a new research direction for considering depth geometry in MVS.


page 4

page 6

page 8

page 12

page 13

page 14

page 15

page 16


MVS^2: Deep Unsupervised Multi-view Stereo with Multi-View Symmetry

The success of existing deep-learning based multi-view stereo (MVS) appr...

Rethinking Disparity: A Depth Range Free Multi-View Stereo Based on Disparity

Existing learning-based multi-view stereo (MVS) methods rely on the dept...

Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation and Focal Loss

Depth estimation is solved as a regression or classification problem in ...

ARAI-MVSNet: A multi-view stereo depth estimation network with adaptive depth range and depth interval

Multi-View Stereo (MVS) is a fundamental problem in geometric computer v...

DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo

We propose a novel approach for deep learning-based Multi-View Stereo (M...

Joint Prediction of Monocular Depth and Structure using Planar and Parallax Geometry

Supervised learning depth estimation methods can achieve good performanc...

iMVS: Improving MVS Networks by Learning Depth Discontinuities

Existing learning-based multi-view stereo (MVS) techniques are effective...

Please sign up or login with your details

Forgot password? Click here to reset