3D Point Cloud Reconstruction

12 papers with code • 0 benchmarks • 2 datasets

Encoding and reconstruction of 3D point clouds.

Most implemented papers

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

maudzung/YOLO3D-YOLOv4-PyTorch 7 Aug 2018

LiDAR sensors are employed to provide the 3D point cloud reconstruction of the surrounding environment, while the task of 3D object bounding box detection in real time remains a strong algorithmic challenge.

SampleNet: Differentiable Point Cloud Sampling

itailang/SampleNet CVPR 2020

As the size of the point cloud grows, so do the computational demands of these tasks.

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

val-iisc/3d-psrnet 30 Sep 2018

We propose a mechanism to reconstruct part annotated 3D point clouds of objects given just a single input image.

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

val-iisc/capnet 28 Nov 2018

We consider the task of single image 3D point cloud reconstruction, and aim to utilize multiple foreground masks as our supervisory data to alleviate the need for large scale 3D datasets.

Learning to Sample

orendv/learning_to_sample CVPR 2019

We show that it is better to learn how to sample.

Dense 3D Point Cloud Reconstruction Using a Deep Pyramid Network

val-iisc/densepcr 25 Jan 2019

Through extensive quantitative and qualitative evaluation on synthetic and real datasets, we demonstrate that DensePCR outperforms the existing state-of-the-art point cloud reconstruction works, while also providing a light-weight and scalable architecture for predicting high-resolution outputs.

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

yhw-yhw/PVAMVSNet ECCV 2020

n this paper, we propose an effective and efficient pyramid multi-view stereo (MVS) net with self-adaptive view aggregation for accurate and complete dense point cloud reconstruction.

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.

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.