no code implementations • • Oleg Voynov, Gleb Bobrovskikh, Pavel Karpyshev, Saveliy Galochkin, Andrei-Timotei Ardelean, Arseniy Bozhenko, Ekaterina Karmanova, Pavel Kopanev, Yaroslav Labutin-Rymsho, Ruslan Rakhimov, Aleksandr Safin, Valerii Serpiva, Alexey Artemov, Evgeny Burnaev, Dzmitry Tsetserukou, Denis Zorin
We expect our dataset will be useful for evaluation and training of 3D reconstruction algorithms and for related tasks.
We present Neural Kernel Fields: a novel method for reconstructing implicit 3D shapes based on a learned kernel ridge regression.
Simulating physical systems is a core component of scientific computing, encompassing a wide range of physical domains and applications.
We propose an unpaired learning method for depth super-resolution, which is based on a learnable degradation model, enhancement component and surface normal estimates as features to produce more accurate depth maps.
Recent advances in 3D semantic scene understanding have shown impressive progress in 3D instance segmentation, enabling object-level reasoning about 3D scenes; however, a finer-grained understanding is required to enable interactions with objects and their functional understanding.
We propose Deep Estimators of Features (DEFs), a learning-based framework for predicting sharp geometric features in sampled 3D shapes.
Shape retrieval and alignment are a promising avenue towards turning 3D scans into lightweight CAD representations that can be used for content creation such as mobile or AR/VR gaming scenarios.
Estimation of differential geometric quantities in discrete 3D data representations is one of the crucial steps in the geometry processing pipeline.
DensePose estimation task is a significant step forward for enhancing user experience computer vision applications ranging from augmented reality to cloth fitting.
We present Neural Splines, a technique for 3D surface reconstruction that is based on random feature kernels arising from infinitely-wide shallow ReLU networks.
After the transformation of frames into the latent space, our model predicts latent representation for the next frames in an autoregressive manner.
Ranked #12 on Video Prediction on Kinetics-600 12 frames, 64x64
We present a new method for vectorization of technical line drawings, such as floor plans, architectural drawings, and 2D CAD images.
Our method builds on the TetWild algorithm, replacing the rational triangle insertion with a new incremental approach to construct and optimize the output mesh, interleaving triangle insertion and mesh optimization.
We show that the gradient dynamics of such networks are determined by the gradient flow in a non-redundant parameterization of the network function.
The Finite Element Method (FEM) is widely used to solve discrete Partial Differential Equations (PDEs) in engineering and graphics applications.
RGBD images, combining high-resolution color and lower-resolution depth from various types of depth sensors, are increasingly common.
We introduce ABC-Dataset, a collection of one million Computer-Aided Design (CAD) models for research of geometric deep learning methods and applications.
We introduce an integrated meshing and finite element method pipeline enabling black-box solution of partial differential equations in the volume enclosed by a boundary representation.
Numerical Analysis Graphics