Point Cloud Inpainting on Graphs from Non-Local Self-Similarity

Fu, Zeqing; Hu, Wei

doi:10.1109/icip.2018.8451550

Cited by 19 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These deep learning-based methods aim to remove noise while preserving the geometric shape and detailed information of the original point cloud as much as possible. Additionally, there are some methods, 31 , 32 which are used for point cloud inpainting, they can recover the missing parts of the point cloud during capture. However, due to different types of distortions, these methods cannot be integrated into the V-PCC standard.…”

Section: Related Workmentioning

confidence: 99%

Video-based point cloud compression artifact removal based on the geometry video enhancement

Wu,

Shen,

Chen

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

Video-based point cloud compression projects dynamic point clouds to 2D videos called geometry videos and texture videos for compression and transmission. In the geometry video, the pixel values represent the positions of each point in the point cloud. Due to distortion of the geometry video, there are some holes and noise points in the reconstructed point cloud. The previous methods for enhancing 2D images or videos can be applied to improve the quality of geometry videos. However, there will still be limitations in the reconstructed 3D point cloud because these methods do not take into account the feature of the 3D point cloud, such as the shape changes and surface orientations. To overcome these limitations, we propose an enhancement network specifically designed for point cloud enhancement through restoring geometry videos, which can calibrate the shape variations and surface orientations of point clouds. Specifically, the gradient information of the geometry video reflects the changes in pixel values, which correspond to changes in shape of the point cloud. Additionally, the normal vectors of the points in the point cloud provide the point cloud surface orientation information. To attain similarity of the shape changes, we design a two-branch network structure and utilize an additional branch comprising of gradient information restoring module to restore the gradient information of the geometry video. To ensure the consistency of point normal vectors, surface fitting and estimation module is designed to calculate the normal vectors of the points in distorted point cloud and the original point cloud through the geometry video, and then the difference of these normal vectors can be used to guide the restoration of the geometry video. Our method has been proved to be satisfactory through the validation experiments on currently available point cloud sequences.

show abstract

Section: Related Workmentioning

confidence: 99%

Video-based point cloud compression artifact removal based on the geometry video enhancement

Wu,

Shen,

Chen

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

“…Point Cloud Inpainting Some of the previous methods [3,4,5,8,25,29] have also explored inpainting in the point cloud domain. However, these methods either use ground truth during training [25,29], rely on template-matching within a data sample [4,5,8], or project a point cloud into 2D structured representation [3]. Our method is novel in the sense that it uses inpainting directly on the point clouds without any ground truth information while leveraging large datasets to learn domain-specific priors.…”

Section: Related Workmentioning

confidence: 99%

Self-Supervised Point Cloud Completion via Inpainting

Mittal¹,

Okorn²,

Jangid³

et al. 2021

Preprint

View full text Add to dashboard Cite

When navigating in urban environments, many of the objects that need to be tracked and avoided are heavily occluded. Planning and tracking using these partial scans can be challenging. The aim of this work is to learn to complete these partial point clouds, giving us a full understanding of the object's geometry using only partial observations. Previous methods achieve this with the help of complete, ground-truth annotations of the target objects, which are available only for simulated datasets. However, such ground truth is unavailable for real-world LiDAR data. In this work, we present a self-supervised point cloud completion algorithm, PointPnCNet, which is trained only on partial scans without assuming access to complete, ground-truth annotations. Our method achieves this via inpainting. We remove a portion of the input data and train the network to complete the missing region. As it is difficult to determine which regions were occluded in the initial cloud and which were synthetically removed, our network learns to complete the full cloud, including the missing regions in the initial partial cloud. We show that our method outperforms previous unsupervised and weakly-supervised methods on both the synthetic dataset, ShapeNet, and real-world LiDAR dataset, Semantic KITTI.

show abstract

“…Similarly, some work focuses on point cloud inpainting [37], [38], [39], wherein portions of point clouds lost during point cloud capture are completed. However, these methods do not work for compression artifact removal in V-PCC.…”

Section: Introductionmentioning

confidence: 99%

Video-based Point Cloud Compression Artifact Removal

Akhtar

Gao

et al. 2021

Preprint

View full text Add to dashboard Cite

Photo-realistic point cloud capture and transmission are the fundamental enablers for immersive visual communication. The coding process of dynamic point clouds, especially video-based point cloud compression (V-PCC) developed by the MPEG standardization group, is now delivering state-of-the-art performance in compression efficiency. V-PCC is based on the projection of the point cloud patches to 2D planes and encoding the sequence as 2D texture and geometry patch sequences. However, the resulting quantization errors from coding can introduce compression artifacts, which can be very unpleasant for the quality of experience (QoE). In this work, we developed a novel out-of-the-loop point cloud geometry artifact removal solution that can significantly improve reconstruction quality without additional bandwidth cost. Our novel framework consists of a point cloud sampling scheme, an artifact removal network, and an aggregation scheme. The point cloud sampling scheme employs a cube-based neighborhood patch extraction to divide the point cloud into patches. The geometry artifact removal network then processes these patches to obtain artifact-removed patches. The artifact-removed patches are then merged together using an aggregation scheme to obtain the final artifact-removed point cloud. We employ 3D deep convolutional feature learning for geometry artifact removal that jointly recovers both the quantization direction and the quantization noise level by exploiting projection and quantization prior. The simulation results demonstrate that the proposed method is highly effective and can considerably improve the quality of the reconstructed point cloud.

show abstract

Point Cloud Inpainting on Graphs from Non-Local Self-Similarity

Cited by 19 publications

References 23 publications

Video-based point cloud compression artifact removal based on the geometry video enhancement

Video-based point cloud compression artifact removal based on the geometry video enhancement

Self-Supervised Point Cloud Completion via Inpainting

Video-based Point Cloud Compression Artifact Removal

Contact Info

Product

Resources

About