AIConfPaper
← Search

Denis Zorin

13 accepted papers

2023

Multi-Sensor Large-Scale Dataset for Multi-View 3D Reconstruction

Oleg Voynov, Gleb Bobrovskikh, Pavel Karpyshev, Saveliy Galochkin, Andrei-Timotei Ardelean, Arseniy Bozhenko +10
CVPR 2023poster

We present a new multi-sensor dataset for multi-view 3D surface reconstruction. It includes registered RGB and depth data from sensors of different resolutions and modalities: smartphones, Intel RealSense, Microsoft Kinect, industrial cameras, and structured-light scanner. The scenes are selected to…

Cited by 12Source ↗PDF ↗Scholar ↗
2022

Neural Fields As Learnable Kernels for 3D Reconstruction

Francis Williams, Zan Gojcic, Sameh Khamis, Denis Zorin, Joan Bruna, Sanja Fidler +1
CVPR 2022poster

We present Neural Kernel Fields: a novel method for reconstructing implicit 3D shapes based on a learned kernel ridge regression. Our technique achieves state-of-the-art results when reconstructing 3D objects and large scenes from sparse oriented points, and can reconstruct shape categories outside…

Cited by 82PDF ↗Scholar ↗
2021

An Extensible Benchmark Suite for Learning to Simulate Physical Systems

Karl Otness, Arvi Gjoka, Joan Bruna, Daniele Panozzo, Benjamin Peherstorfer, Teseo Schneider +1
NeurIPS 2021poster

Simulating physical systems is a core component of scientific computing, encompassing a wide range of physical domains and applications. Recently, there has been a surge in data-driven methods to complement traditional numerical simulation methods, motivated by the opportunity to reduce computationa…

Cited by 23Source ↗code ↗Scholar ↗
2021

Hardware Design and Accurate Simulation of Structured-Light Scanning for Benchmarking of 3D Reconstruction Algorithms

Sebastian Koch, Yurii Piadyk, Markus Worchel, Marc Alexa, Cláudio Silva, Denis Zorin +1
NeurIPS 2021poster

Images of a real scene taken with a camera commonly differ from synthetic images of a virtual replica of the same scene, despite advances in light transport simulation and calibration. By explicitly co-developing the Structured-Light Scanning (SLS) hardware and rendering pipeline we are able to achi…

Cited by 0Source ↗code ↗Scholar ↗
2021

Neural Splines: Fitting 3D Surfaces With Infinitely-Wide Neural Networks

Francis Williams, Matthew Trager, Joan Bruna, Denis Zorin
CVPR 2021poster

We present Neural Splines, a technique for 3D surface reconstruction that is based on random feature kernels arising from infinitely-wide shallow ReLU networks. Our method achieves state-of-the-art results, outperforming recent neural network-based techniques and widely used Poisson Surface Reconstr…

Cited by 79PDF ↗code ↗Scholar ↗
2021

Towards Part-Based Understanding of RGB-D Scans

Alexey Bokhovkin, Vladislav Ishimtsev, Emil Bogomolov, Denis Zorin, Alexey Artemov, Evgeny Burnaev +1
CVPR 2021poster

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. Thus, we propose…

Cited by 12PDF ↗Scholar ↗
2020

CAD-Deform: Deformable Fitting of CAD Models to 3D Scans

Vladislav Ishimtsev, Alexey Bokhovkin, Alexey Artemov, Savva Ignatyev, Matthias Niessner, Denis Zorin +1
ECCV 2020poster

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. Unfortunately, CAD models retrieval is limited by the availability of models in the common shape corpuses…

Cited by 32Source ↗PDF ↗code ↗Scholar ↗
2020

Deep Vectorization of Technical Drawings

Vage Egiazarian, Oleg Voynov, Alexey Artemov, Denis Volkhonskiy, Aleksandr Safin, Maria Taktasheva +2
ECCV 2020poster

We present a new method for vectorization of technical line drawings, such as floor plans, architectural drawings, and 2D CAD images. Our method includes (1) a deep learning-based cleaning stage to eliminate the background and imperfections in the image and fill in missing parts, (2) a transformer-b…

Cited by 73Source ↗PDF ↗code ↗Scholar ↗
2019

ABC: A Big CAD Model Dataset for Geometric Deep Learning

Sebastian Koch, Albert Matveev, Zhongshi Jiang, Francis Williams, Alexey Artemov, Evgeny Burnaev +3
CVPR 2019poster

We introduce ABC-Dataset, a collection of one million Computer-Aided Design (CAD) models for research of geometric deep learning methods and applications. Each model is a collection of explicitly parametrized curves and surfaces, providing ground truth for differential quantities, patch segmentation…

Cited by 613PDF ↗Scholar ↗
2019

Deep Geometric Prior for Surface Reconstruction

Francis Williams, Teseo Schneider, Claudio Silva, Denis Zorin, Joan Bruna, Daniele Panozzo
CVPR 2019poster

The reconstruction of a discrete surface from a point cloud is a fundamental geometry processing problem that has been studied for decades, with many methods developed. We propose the use of a deep neural network as a geometric prior for surface reconstruction. Specifically, we overfit a neural netw…

Cited by 225PDF ↗code ↗Scholar ↗
2019

Gradient Dynamics of Shallow Univariate ReLU Networks

Francis Williams, Matthew Trager, Daniele Panozzo, Claudio Silva, Denis Zorin, Joan Bruna
NeurIPS 2019poster

We present a theoretical and empirical study of the gradient dynamics of overparameterized shallow ReLU networks with one-dimensional input, solving least-squares interpolation. We show that the gradient dynamics of such networks are determined by the gradient flow in a non-redundant parameterizati…

Cited by 102Source ↗PDF ↗Scholar ↗
2019

Perceptual Deep Depth Super-Resolution

Oleg Voynov, Alexey Artemov, Vage Egiazarian, Alexander Notchenko, Gleb Bobrovskikh, Evgeny Burnaev +1
ICCV 2019poster

RGBD images, combining high-resolution color and lower-resolution depth from various types of depth sensors, are increasingly common. One can significantly improve the resolution of depth maps by taking advantage of color information; deep learning methods make combining color and depth information…

Cited by 53PDF ↗code ↗Scholar ↗