Point cloud reconstruction
36 papers with code • 0 benchmarks • 0 datasets
This task aims to solve inherent problems in raw point clouds: sparsity, noise, and irregularity.
Benchmarks
These leaderboards are used to track progress in Point cloud reconstruction
Most implemented papers
Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification
fei960922/GPointNet
•
•
CVPR 2021
We propose a generative model of unordered point sets, such as point clouds, in the form of an energy-based model, where the energy function is parameterized by an input-permutation-invariant bottom-up neural network.
M^3VSNet: Unsupervised Multi-metric Multi-view Stereo Network
To improve the robustness and completeness of point cloud reconstruction, we propose a novel multi-metric loss function that combines pixel-wise and feature-wise loss function to learn the inherent constraints from different perspectives of matching correspondences.
Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes
lzqsd/TransparentShapeReconstruction
•
•
CVPR 2020
Recovering the 3D shape of transparent objects using a small number of unconstrained natural images is an ill-posed problem.
M^3VSNet: Unsupervised Multi-metric Multi-view Stereo Network
To improve the robustness and completeness of point cloud reconstruction, we propose a novel multi-metric loss function that combines pixel-wise and feature-wise loss function to learn the inherent constraints from different perspectives of matching correspondences.
From Image Collections to Point Clouds with Self-supervised Shape and Pose Networks
val-iisc/ssl_3d_recon
•
•
CVPR 2020
We learn both 3D point cloud reconstruction and pose estimation networks in a self-supervised manner, making use of differentiable point cloud renderer to train with 2D supervision.
Set Prediction without Imposing Structure as Conditional Density Estimation
davzha/DESP
•
•
ICLR 2021
In this paper, we propose an alternative to training via set losses by viewing learning as conditional density estimation.
Canonical Capsules: Self-Supervised Capsules in Canonical Pose
canonical-capsules/canonical-capsules
•
•
NeurIPS 2021
We propose a self-supervised capsule architecture for 3D point clouds.
3D Surface Reconstruction From Multi-Date Satellite Images
The reconstruction of accurate three-dimensional environment models is one of the most fundamental goals in the field of photogrammetry.
MPED: Quantifying Point Cloud Distortion based on Multiscale Potential Energy Discrepancy
Qi-Yangsjtu/MPED
•
•
In this paper, we propose a new distortion quantification method for point clouds, the multiscale potential energy discrepancy (MPED).
Patch-Based Deep Autoencoder for Point Cloud Geometry Compression
i2-multimedia-lab/pcc_patch
•
•
Unlike existing point cloud compression networks, which apply feature extraction and reconstruction on the entire point cloud, we divide the point cloud into patches and compress each patch independently.
