|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
We present a complete classification of all minimal problems for generic arrangements of points and lines completely observed by calibrated perspective cameras.
We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database.
Supervised 3D reconstruction has witnessed a significant progress through the use of deep neural networks.
Inspired by the recent success of methods that employ shape priors to achieve robust 3D reconstructions, we propose a novel recurrent neural network architecture that we call the 3D Recurrent Reconstruction Neural Network (3D-R2N2).
#5 best model for 3D Reconstruction on Data3D−R2N2
Representing the reconstruction volumetrically as a TSDF leads to most of the simplicity and efficiency that can be achieved with GPU implementations of these systems.
To amass training data for our model, we propose a self-supervised feature learning method that leverages the millions of correspondence labels found in existing RGB-D reconstructions.
#2 best model for 3D Reconstruction on Scan2CAD
We use the new method, SMPLify-X, to fit SMPL-X to both controlled images and images in the wild.
We provide an open-source C++ library for real-time metric-semantic visual-inertial Simultaneous Localization And Mapping (SLAM).
In this work, we introduce DeepSDF, a learned continuous Signed Distance Function (SDF) representation of a class of shapes that enables high quality shape representation, interpolation and completion from partial and noisy 3D input data.