3D Point Cloud Enhancement Using Graph-Modelled Multiview Depth Measurements

@article{Zhang20203DPC,
  title={3D Point Cloud Enhancement Using Graph-Modelled Multiview Depth Measurements},
  author={Xue Zhang and Gene Cheung and Jiahao Pang and Dong Tian},
  journal={2020 IEEE International Conference on Image Processing (ICIP)},
  year={2020},
  pages={3314-3318}
}
  • Xue Zhang, Gene Cheung, Dong Tian
  • Published 11 February 2020
  • Computer Science
  • 2020 IEEE International Conference on Image Processing (ICIP)
A 3D point cloud is often synthesized from depth measurements collected by sensors at different viewpoints. The acquired measurements are typically both coarse in precision and corrupted by noise. To improve quality, previous works denoise a synthesized 3D point cloud a posteriori, after projecting the imperfect depth data onto the 3D space. Instead, we enhance depth measurements on the sensed images a priori, exploiting inherent 3D geometric correlation across views, before synthesizing a 3D… 

Figures and Tables from this paper

Graph-Based Depth Denoising & Dequantization for Point Cloud Enhancement

TLDR
This work model depth formation as a combined process of signal-dependent noise addition and non-uniform log-based quantization and optimize the objective efficiently using accelerated gradient descent (AGD), where the optimal step size is approximated via Gershgorin circle theorem (GCT).

Feature Graph Learning for 3D Point Cloud Denoising

TLDR
This work alternately optimize the diagonal and off-diagonal entries of a Mahalanobis distance matrix and constrain the Schur complement of sub-matrix to be positive definite (PD) via linear inequalities derived from the Gershgorin circle theorem.

References

SHOWING 1-10 OF 34 REFERENCES

Precision Enhancement of 3-D Surfaces from Compressed Multiview Depth Maps

TLDR
This work proposes an alternating projection algorithm, inspired by the theory of projection onto convex sets (POCS), which at convergence returns a 3-D surface that satisfies three sets of conditions: spatial smoothness prior, quantization bin constraints in the block transform domain, and inter-view consistency.

Local 3D Point Cloud Denoising via Bipartite Graph Approximation & Total Variation

TLDR
Experimental results show that compared to state-of-the-art schemes with similar complexity, the proposed algorithm achieves the best overall denoising performance objectively and subjectively.

3D Point Cloud Denoising Using Graph Laplacian Regularization of a Low Dimensional Manifold Model

TLDR
This paper extends a previously proposed low-dimensional manifold model for the image patches to surface patches in the point cloud, and seeks self-similar patches to denoise them simultaneously using the patch manifold prior, and proposes a new discrete patch distance measure to quantify the similarity between two same-sized surface patches for graph construction that is robust to noise.

Reconstruction-Based Pairwise Depth Dataset for Depth Image Enhancement Using CNN

TLDR
Experimental results show that the network trained with the pairwise dataset can enhance the input depth images to become comparable with 3D reconstructions obtained from depth streams, and can accelerate the convergence of dense 3D reconstruction results.

Point Cloud Denoising via Moving RPCA

We present an algorithm for the restoration of noisy point cloud data, termed Moving Robust Principal Components Analysis (MRPCA). We model the point cloud as a collection of overlapping

Geometric distortion metrics for point cloud compression

TLDR
The intrinsic resolution of the point clouds is proposed as a normalizer to convert the mean square errors to PSNR numbers and this method could better track the perceived quality than the point-to-point approach while requires limited computations.

Learning Dynamic Guidance for Depth Image Enhancement

TLDR
A weighted analysis representation model for guided depth image enhancement is proposed, which advances the conventional methods in two aspects: task driven learning and dynamic guidance.

Region-Aware 3-D Warping for DIBR

TLDR
A region-aware 3-D warping approach for DIBR in which warped frames are reasonably divided beforehand so that only the indispensable regions are used, which can achieve significant computation savings without sacrificing synthesis quality.

Multiframe demosaicing and super-resolution of color images

TLDR
A fast and robust hybrid method of super-resolution and demosaicing, based on a maximum a posteriori estimation technique by minimizing a multiterm cost function is proposed.

Graph-Based Blind Image Deblurring From a Single Photograph

TLDR
This paper argues that a skeleton image—a proxy that retains the strong gradients of the target but smooths out the details—can be used to accurately estimate the blur kernel and has a unique bi-modal edge weight distribution, and designs a reweighted graph total variation (RGTV) prior that can efficiently promote a bi- modal edge Weight distribution given a blurry patch.