computer-vision-6

Point cloud reconstruction

3260 papers • 126 benchmarks • 313 datasets

This task aims to solve inherent problems in raw point clouds: sparsity, noise, and irregularity.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in point-cloud-reconstruction-6

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find point-cloud-reconstruction-6 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud

Ahmad El Sallab, Waleed Ali, Sherif Abdelkarim, Mohamed Zahran, Mahmoud Zidan•Mon Aug 06 2018

The main contribution is in extending the loss function of YOLO v2 to include the yaw angle, the 3D box center in Cartesian coordinates and the height of the box as a direct regression problem, which enables real-time performance, which is essential for automated driving.

162

Content

0

Paper Graph

SO-Net: Self-Organizing Network for Point Cloud Analysis

Gim Hee Lee, Jiaxin Li, Ben M. Chen•Sun Mar 11 2018

The proposed SO-Net, a permutation invariant architecture for deep learning with orderless point clouds, demonstrates performance that is similar with or better than state-of-the-art approaches in recognition tasks such as point cloud reconstruction, classification, object part segmentation and shape retrieval.

990 0

Paper Graph

PointMixer: MLP-Mixer for Point Cloud Understanding

François Rameau, In-So Kweon, Jaesik Park, Jaesung Choe, Chunghyun Park•Sun Nov 21 2021

This paper proposes PointMixer, a universal point set operator that facilitates information sharing among unstructured 3D points by simply replacing token-mixing MLPs with a softmax function, which can be broadly used in the network as inter-set mixing, intra- set mixing, and pyramid mixing.

118 0

Paper Graph

3D-LMNet: Latent Embedding Matching for Accurate and Diverse 3D Point Cloud Reconstruction from a Single Image

Mayank Agarwal, R. Venkatesh Babu, Priyanka Mandikal, L. NavaneetK.•Thu Jul 19 2018

3D-LMNet, a latent embedding matching approach for 3D reconstruction, is proposed, which outperform state-of-the-art approaches on the task of single-view3D reconstruction on both real and synthetic datasets while generating multiple plausible reconstructions, demonstrating the generalizability and utility of the approach.

170 0

Paper Graph

Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking

Yu-Wing Tai, Hongwei Yi, Mingyu Ding, Runze Zhang, Zizhuang Wei, Yisong Chen, Guoping Wang, Jianfeng Yan•Mon Jul 20 2020

An efficient and effective dense hybrid recurrent multi-view stereo net with dynamic consistency checking, namely D^{2}$HC-RMVSNet, for accurate dense point cloud reconstruction and dynamically aggregate geometric consistency matching error among all the views is proposed.

200 0

Paper Graph

3D-PSRNet: Part Segmented 3D Point Cloud Reconstruction From a Single Image

R. Venkatesh Babu, Priyanka Mandikal, L. NavaneetK.•Fri Sep 07 2018

It is demonstrated that jointly training for both reconstruction and segmentation leads to improved performance in both the tasks, when compared to training for each task individually.

47 0

Paper Graph

CAPNet: Continuous Approximation Projection For 3D Point Cloud Reconstruction Using 2D Supervision

Mayank Agarwal, R. Venkatesh Babu, Priyanka Mandikal, L. NavaneetK.•Tue Nov 27 2018

A novel differentiable projection module, called ‘CAPNet’, is introduced to obtain 2D masks from a predicted 3D point cloud reconstruction, and significantly outperform the existing projection based approaches on a large-scale synthetic dataset.

66 0

Paper Graph

Dense 3D Point Cloud Reconstruction Using a Deep Pyramid Network

R. Venkatesh Babu, Priyanka Mandikal•Mon Dec 31 2018

This work introduces DensePCR, a deep pyramidal network for point cloud reconstruction that hierarchically predicts point clouds of increasing resolution, and proposes an architecture that first predicts a low-resolution point cloud, and then hierarchically increases the resolution by aggregating local and global point features to deform a grid.

127 0

Paper Graph

Silhouette Guided Point Cloud Reconstruction beyond Occlusion

Derek Hoiem, Chuhang Zou•Sun Jul 28 2019

This paper proposes a method to reconstruct the complete 3D shape of an object from a single RGB image, with robustness to occlusion, and shows improvements for reconstruction of non-occluded and partially occluded objects by providing the predicted complete silhouette as guidance.

11 0

Paper Graph

Pyramid Multi-view Stereo Net with Self-adaptive View Aggregation

Yu-Wing Tai, Hongwei Yi, Mingyu Ding, Runze Zhang, Zizhuang Wei, Yisong Chen, Guoping Wang•Thu Dec 05 2019

This paper proposes an effective and efficient pyramid multi-view stereo (MVS) net with self-adaptive view aggregation for accurate and complete dense point cloud reconstruction and establishes a new state-of-the-art on the DTU dataset with significant improvements in the completeness and overall quality.

133 0

Paper Graph

Adding a benchmark result helps the community track progress.