DeepAI AI Chat
Log In Sign Up

Detail-preserving and Content-aware Variational Multi-view Stereo Reconstruction

by   Zhaoxin Li, et al.

Accurate recovery of 3D geometrical surfaces from calibrated 2D multi-view images is a fundamental yet active research area in computer vision. Despite the steady progress in multi-view stereo reconstruction, most existing methods are still limited in recovering fine-scale details and sharp features while suppressing noises, and may fail in reconstructing regions with few textures. To address these limitations, this paper presents a Detail-preserving and Content-aware Variational (DCV) multi-view stereo method, which reconstructs the 3D surface by alternating between reprojection error minimization and mesh denoising. In reprojection error minimization, we propose a novel inter-image similarity measure, which is effective to preserve fine-scale details of the reconstructed surface and builds a connection between guided image filtering and image registration. In mesh denoising, we propose a content-aware ℓ_p-minimization algorithm by adaptively estimating the p value and regularization parameters based on the current input. It is much more promising in suppressing noise while preserving sharp features than conventional isotropic mesh smoothing. Experimental results on benchmark datasets demonstrate that our DCV method is capable of recovering more surface details, and obtains cleaner and more accurate reconstructions than state-of-the-art methods. In particular, our method achieves the best results among all published methods on the Middlebury dino ring and dino sparse ring datasets in terms of both completeness and accuracy.


page 1

page 3

page 6

page 7

page 8

page 10

page 11

page 13


Multi-View Azimuth Stereo via Tangent Space Consistency

We present a method for 3D reconstruction only using calibrated multi-vi...

POEM: Reconstructing Hand in a Point Embedded Multi-view Stereo

Enable neural networks to capture 3D geometrical-aware features is essen...

Multi-View Stereo Representation Revisit: Region-Aware MVSNet

Deep learning-based multi-view stereo has emerged as a powerful paradigm...

Efficient Multi-view Performance Capture of Fine-Scale Surface Detail

We present a new effective way for performance capture of deforming mesh...

PiMPeR: Piecewise Dense 3D Reconstruction from Multi-View and Multi-Illumination Images

In this paper, we address the problem of dense 3D reconstruction from mu...

Multi-View Stereo with Asymmetric Checkerboard Propagation and Multi-Hypothesis Joint View Selection

In computer vision domain, how to fast and accurately perform multiview ...

Mesh-based Camera Pairs Selection and Occlusion-Aware Masking for Mesh Refinement

Many Multi-View-Stereo algorithms extract a 3D mesh model of a scene, af...