Corpus ID: 236469083

Improving Multi-View Stereo via Super-Resolution

  title={Improving Multi-View Stereo via Super-Resolution},
  author={Eugenio Lomurno and Andrea Romanoni and Matteo Matteucci},
Today, Multi-View Stereo techniques are able to reconstruct robust and detailed 3D models, especially when starting from high-resolution images. However, there are cases in which the resolution of input images is relatively low, for instance, when dealing with old photos, or when hardware constrains the amount of data that can be acquired. In this paper, we investigate if, how, and how much increasing the resolution of such input images through Super-Resolution techniques reflects in quality… Expand

Figures from this paper


Plane Completion and Filtering for Multi-View Stereo Reconstruction
This work presents an effective pipeline for large-scale 3D reconstruction which extends existing methods in several ways and introduces an outlier filtering considering the MVS geometry and proposes a plane completion method based on growing superpixels allowing a generic generation of high-quality 3D models. Expand
3D Appearance Super-Resolution With Deep Learning
Experimental results demonstrate that the proposed networks successfully incorporate the 3D geometric information and super-resolve the texture maps. Expand
A Multi-view Stereo Benchmark with High-Resolution Images and Multi-camera Videos
This benchmark is the first to cover the important use case of hand-held mobile devices while also providing high-resolution DSLR camera images and provides data at significantly higher temporal and spatial resolution. Expand
Perceptual Deep Depth Super-Resolution
This work demonstrates that a simple visual appearance-based loss, when used with either a trained CNN or simply a deep prior, yields significantly improved 3D shapes, as measured by a number of existing perceptual metrics. Expand
TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo
This paper generates novel PatchMatch hypotheses so to expand reliable depth estimates in neighboring untextured regions and proposes a depth refinement step to filter wrong estimates and to fill the gaps on both the depth maps and normal maps while preserving the discontinuities. Expand
Multi-Scale Frequency Reconstruction for Guided Depth Map Super-Resolution via Deep Residual Network
A data-driven approach based on the deep convolutional neural network with global and local residual learning to restore the depth structure from coarse to fine via multi-scale frequency synthesis is proposed. Expand
A Super-Resolution Framework for High-Accuracy Multiview Reconstruction
A variational framework to estimate super-resolved texture maps on a 3D geometry model of a surface from multiple images allows to recover textured models with significantly higher level ofdetail than the individual input images. Expand
Super-resolution Keyframe Fusion for 3D Modeling with High-Quality Textures
We propose a novel fast and robust method for obtaining 3D models with high-quality appearance using commodity RGB-D sensors. Our method uses a direct key frame-based SLAM front end to consistentlyExpand
DeepMVS: Learning Multi-view Stereopsis
The results show that DeepMVS compares favorably against state-of-the-art conventional MVS algorithms and other ConvNet based methods, particularly for near-textureless regions and thin structures. Expand
Point-Based Multi-View Stereo Network
This work introduces Point-MVSNet, a novel point-based deep framework for multi-view stereo (MVS), which directly processes the target scene as point clouds and allows higher accuracy, more computational efficiency and more flexibility than cost-volume-based counterparts. Expand