Super‐Resolution of Point Set Surfaces Using Local Similarities

Hamdi-Cherif, Azzouz; Digne, Julie; Chaine, Raphaëlle

doi:10.1111/cgf.13216

Cited by 15 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, researchers have attempted to apply the end-to-end learning methods to repair point cloud. Cherif et al [46] tried to enhance the resolution of point clouds using the local similarity at a small scale on the surface. Yu et al [47] present a data-driven up-sampling architecture which can learn multi-level features per point and expand the point set in feature space.…”

Section: B Related Workmentioning

confidence: 99%

Fast Generation of High Fidelity RGB-D Images by Deep-Learning with Adaptive Convolution

Xian

Zhang

Dai

et al. 2020

Preprint

View full text Add to dashboard Cite

Using the raw data from consumer-level RGB-D cameras as input, we propose a deep-learning based approach to efficiently generate RGB-D images with completed information in high resolution. To process the input images in low resolution with missing regions, new operators for adaptive convolution are introduced in our deep-learning network that consists of three cascaded modules -the completion module, the refinement module and the super-resolution module. The completion module is based on an architecture of encoder-decoder, where the features of input raw RGB-D will be automatically extracted by the encoding layers of a deep neural-network. The decoding layers are applied to reconstruct the completed depth map, which is followed by a refinement module to sharpen the boundary of different regions. For the super-resolution module, we generate RGB-D images in high resolution by multiple layers for feature extraction and a layer for up-sampling. Benefited from the adaptive convolution operators proposed in this paper, our results outperform the existing deep-learning based approaches for RGB-D image complete and super-resolution. As an endto-end approach, high fidelity RGB-D images can be generated efficiently at the rate of 22 frames per second.

show abstract

Section: B Related Workmentioning

confidence: 99%

Fast Generation of High Fidelity RGB-D Images by Deep-Learning with Adaptive Convolution

Xian

Zhang

Dai

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…It processes a pixel using not only its own neighborhood but also all pixels with a similar neighborhood, even if they are distant. Non-local analysis has also been used to analyze images and videos together in [4]; it has been extended to 3D surfaces for denoising [5] [6], super-resolution [7], for surface reconstruction using the famous Point Set Surface framework [8], and surface inpainting [9] by copying similar patches to missing regions. It has also been exploited in the context of shape resampling and consolidation.…”

Section: Related Workmentioning

confidence: 99%

Sparse Geometric Representation Through Local Shape Probing

Digne,

Valette,

Chaine

2016

Preprint

Self Cite

View full text Add to dashboard Cite

We propose a new shape analysis approach based on the non-local analysis of local shape variations. Our method relies on a novel description of shape variations, called Local Probing Field (LPF), which describes how a local probing operator transforms a pattern onto the shape. By carefully optimizing the position and orientation of each descriptor, we are able to capture shape similarities and gather them into a geometrically relevant dictionary over which the shape decomposes sparsely. This new representation permits to handle shapes with mixed intrinsic dimensionality (e.g. shapes containing both surfaces and curves) and to encode various shape features such as boundaries. Our shape representation has several potential applications; here we demonstrate its efficiency for shape resampling and point set denoising for both synthetic and real data.

show abstract

“…Another approach to improve lossy-geometry compression is to perform some form of interpolation with the downscaled voxels. Although there are many interpolation or superresolution (SR) methods for PC geometry [10], [11], [12], [13], [14], [15], [16], [17], they are not well-suited for the octree structure used in G-PCC. Recently, Borges et al [18] proposed the use of LUTs relating the downsampled neighbourhood of a given voxel with its children occupancy to super-resolve voxelized PCs downsampled at arbitrary fractional scales.…”

Section: Introductionmentioning

confidence: 99%

Using Fractional Super-Resolution to Improve Lossy Compression of Point Cloud Geometry

Borges,

Ferreira,

Garcia

et al. 2023

JCIS

View full text Add to dashboard Cite

We present a method for post-processing point clouds’ geometric information by applying a previously proposed fractional super-resolution technique to clouds compressed and decoded with MPEG’s G-PCC codec. In some sense, this is a continuation of that previous work, which requires only a downscaled point cloud and a scaling factor, both of which are provided by the G-PCC codec. For non-solid point clouds, an a priori down-scaling is required for improved efficiency. The method is compared to the GPCC itself, as well as machine-learning-based techniques. Results show a great improvement in quality over GPCC and comparable performance to the latter techniques, with the advantage of not needing any kind of previous training.

show abstract

Super‐Resolution of Point Set Surfaces Using Local Similarities

Abstract: Abstract

Cited by 15 publications

References 35 publications

Fast Generation of High Fidelity RGB-D Images by Deep-Learning with Adaptive Convolution

Fast Generation of High Fidelity RGB-D Images by Deep-Learning with Adaptive Convolution

Sparse Geometric Representation Through Local Shape Probing

Using Fractional Super-Resolution to Improve Lossy Compression of Point Cloud Geometry

Contact Info

Product

Resources

About