Towards high-resolution large-scale multi-view stereo

Hiep, Vu Hoang; Keriven, Renaud; Labatut, Patrick; Pons, Jean-Philippe

doi:10.1109/cvprw.2009.5206617

Cited by 48 publications

(41 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Scene reconstruction Traditional methods for scene reconstruction first generate a sparse reconstruction using large-scale structure-from-motion [1], then perform Multi-View Stereo (MVS) [7,38] or variational optimization [13] to reconstruct dense scene models. However, most such techniques assume a single appearance, or else simply recover an average appearance of the scene.…”

Section: Related Workmentioning

confidence: 99%

Neural Rerendering in the Wild

Meshry

Goldman

Khamis

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

206

141

View full text Add to dashboard Cite

We explore total scene capture -recording, modeling, and rerendering a scene under varying appearance such as season and time of day. Starting from internet photos of a tourist landmark, we apply traditional 3D reconstruction to register the photos and approximate the scene as a point cloud. For each photo, we render the scene points into a deep framebuffer, and train a neural network to learn the mapping of these initial renderings to the actual photos. This rerendering network also takes as input a latent appearance vector and a semantic mask indicating the location of transient objects like pedestrians. The model is evaluated on several datasets of publicly available images spanning a broad range of illumination conditions. We create short videos demonstrating realistic manipulation of the image viewpoint, appearance, and semantic labeling. We also compare results with prior work on scene reconstruction from internet photos.

show abstract

Section: Related Workmentioning

confidence: 99%

Neural Rerendering in the Wild

Meshry

Goldman

Khamis

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

206

141

View full text Add to dashboard Cite

show abstract

“…Many ways have been proposed to set these energy terms [13,15,18,22,23,33]. In an evaluation [25] on the Strecha dataset [30], we found that a constant visibility cost ( Fig.…”

Section: Global Meshing By Labatut Et Almentioning

confidence: 99%

“…Aside from octree-based approaches, there is also a considerable amount of work that is based on the Delaunay tetrahedralization of the 3D points [13,15,18,22,23,33]. Opposed to octree-based approaches, the Delaunay tetrahedralization splits the space into uneven tetrahedra and thus grants these approaches the unique capability to close holes of arbitrary size for any point density.…”

Section: Related Workmentioning

confidence: 99%

Scalable Surface Reconstruction from Point Clouds with Extreme Scale and Density Diversity

Mostegel

Prettenthaler

Fraundorfer

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

In this paper we present a scalable approach for robustly computing a 3D surface mesh from multi-scale multi-view stereo point clouds that can handle extreme jumps of point density (in our experiments three orders of magnitude). The backbone of our approach is a combination of octree data partitioning, local Delaunay tetrahedralization and graph cut optimization. Graph cut optimization is used twice, once to extract surface hypotheses from local Delaunay tetrahedralizations and once to merge overlapping surface hypotheses even when the local tetrahedralizations do not share the same topology. This formulation allows us to obtain a constant memory consumption per sub-problem while at the same time retaining the density independent interpolation properties of the Delaunay-based optimization. On multiple public datasets, we demonstrate that our approach is highly competitive with the state-of-the-art in terms of accuracy, completeness and outlier resilience. Further, we demonstrate the multi-scale potential of our approach by processing a newly recorded dataset with 2 billion points and a point density variation of more than four orders of magnitude -requiring less than 9GB of RAM per process. * Results incorporated in this paper received funding from the European Unions Horizon 2020 research and innovation programme under grant agreement No 730294 and the EC FP7 project 3D-PITOTI (ICT-2011-600545). 2.5 km 500 m 50 m 50 cm 5 cm arXiv:1705.00949v1 [cs.CV]

show abstract

“…According to [22], MVS methods can be categorized into four groups, voxel-based methods [5,29,26], surface evolution based methods [4,11,3], patch-based methods [9,17,7] and depth map based methods [36,8,19]. The voxel-based methods are often constrained by their predefined voxel grid resolution.…”

Section: Related Workmentioning

confidence: 99%

Multi-Scale Geometric Consistency Guided Multi-View Stereo

Tao

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

194

206

View full text Add to dashboard Cite

In this paper, we propose an efficient multi-scale geometric consistency guided multi-view stereo method for accurate and complete depth map estimation. We first present our basic multi-view stereo method with Adaptive Checkerboard sampling and Multi-Hypothesis joint view selection (ACMH). It leverages structured region information to sample better candidate hypotheses for propagation and infer the aggregation view subset at each pixel. For the depth estimation of low-textured areas, we further propose to combine ACMH with multi-scale geometric consistency guidance (ACMM) to obtain the reliable depth estimates for low-textured areas at coarser scales and guarantee that they can be propagated to finer scales. To correct the erroneous estimates propagated from the coarser scales, we present a novel detail restorer. Experiments on extensive datasets show our method achieves state-of-the-art performance, recovering the depth estimation not only in low-textured areas but also in details.

show abstract

Towards high-resolution large-scale multi-view stereo

Cited by 48 publications

References 42 publications

Neural Rerendering in the Wild

Neural Rerendering in the Wild

Scalable Surface Reconstruction from Point Clouds with Extreme Scale and Density Diversity

Multi-Scale Geometric Consistency Guided Multi-View Stereo

Contact Info

Product

Resources

About