Author name cluster

Claudio Silva

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

NeurIPS Conference 2021 Conference Paper

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

Sebastian Koch
Yurii Piadyk
Markus Worchel
Marc Alexa
Claudio Silva
Denis Zorin
Daniele Panozzo

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 achieve negligible per-pixel difference between the real image and the synthesized image on geometrically complex calibration objects with known material properties. This approach provides an ideal test-bed for developing and evaluating data-driven algorithms in the area of 3D reconstruction, as the synthetic data is indistinguishable from real data and can be generated at large scale by simulation. We propose three benchmark challenges using a combination of acquired and synthetic data generated with our system: (1) a denoising benchmark tailored to structured-light scanning, (2) a shape completion benchmark to fill in missing data, and (3) a benchmark for surface reconstruction from dense point clouds. Besides, we provide a large collection of high-resolution scans that allow to use our system and benchmarks without reproduction of the hardware setup on our website: https: //geometryprocessing. github. io/scanner-sim

PDF Details

AAAI Conference 2020 Conference Paper

Learning Geo-Contextual Embeddings for Commuting Flow Prediction

Zhicheng Liu
Fabio Miranda
Weiting Xiong
Junyan Yang
Qiao Wang
Claudio Silva

Predicting commuting ﬂows based on infrastructure and landuse information is critical for urban planning and public policy development. However, it is a challenging task given the complex patterns of commuting ﬂows. Conventional models, such as gravity model, are mainly derived from physics principles and limited by their predictive power in real-world scenarios where many factors need to be considered. Meanwhile, most existing machine learning-based methods ignore the spatial correlations and fail to model the inﬂuence of nearby regions. To address these issues, we propose Geocontextual Multitask Embedding Learner (GMEL), a model that captures the spatial correlations from geographic contextual information for commuting ﬂow prediction. Speciﬁcally, we ﬁrst construct a geo-adjacency network containing the geographic contextual information. Then, an attention mechanism is proposed based on the framework of graph attention network (GAT) to capture the spatial correlations and encode geographic contextual information to embedding space. Two separate GATs are used to model supply and demand characteristics. To enhance the effectiveness of the embedding representation, a multitask learning framework is used to introduce stronger restrictions, forcing the embeddings to encapsulate effective representation for ﬂow prediction. Finally, a gradient boosting machine is trained based on the learned embeddings to predict commuting ﬂows. We evaluate our model using real-world dataset from New York City and the experimental results demonstrate the effectiveness of our proposed method against the state of the art.

PDF Details

NeurIPS Conference 2019 Conference Paper

Gradient Dynamics of Shallow Univariate ReLU Networks

Francis Williams
Matthew Trager
Daniele Panozzo
Claudio Silva
Denis Zorin
Joan Bruna

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 parameterization of the network function. We examine the principal qualitative features of this gradient flow. In particular, we determine conditions for two learning regimes: \emph{kernel} and \emph{adaptive}, which depend both on the relative magnitude of initialization of weights in different layers and the asymptotic behavior of initialization coefficients in the limit of large network widths. We show that learning in the kernel regime yields smooth interpolants, minimizing curvature, and reduces to \emph{cubic splines} for uniform initializations. Learning in the adaptive regime favors instead \emph{linear splines}, where knots cluster adaptively at the sample points.

PDF Details