Related papers: Generative Geostatistical Modeling from Incomplete…
Image synthesis approaches, e.g., generative adversarial networks, have been popular as a form of data augmentation in medical image analysis tasks. It is primarily beneficial to overcome the shortage of publicly accessible data and…
Data scarcity is a primary obstacle in developing robust Machine Learning (ML) models for detecting rapidly intensifying tropical cyclones. Traditional data augmentation techniques (rotation, flipping, brightness adjustment) fail to…
Rapid urbanization demands accurate and efficient monitoring of turbulent wind patterns to support air quality, climate resilience and infrastructure design. Traditional sparse reconstruction and sensor placement strategies face major…
Scattering transforms are a new type of summary statistics recently developed for the study of highly non-Gaussian processes, which have been shown to be very promising for astrophysical studies. In particular, they allow one to build…
Generative models such as denoising diffusion models are quickly advancing their ability to approximate highly complex data distributions. They are also increasingly leveraged in scientific machine learning, where samples from the implied…
Generating graph-structured data requires learning the underlying distribution of graphs. Yet, this is a challenging problem, and the previous graph generative methods either fail to capture the permutation-invariance property of graphs or…
Vision-based grasping of unknown objects in unstructured environments is a key challenge for autonomous robotic manipulation. A practical grasp synthesis system is required to generate a diverse set of 6-DoF grasps from which a…
Generative models based on diffusion have become the state of the art in the last few years, notably for image generation. Here, we analyse them in the high-dimensional limit, where data are formed by a very large number of variables. We…
Kinematic sensors are often used to analyze movement behaviors in sports and daily activities due to their ease of use and lack of spatial restrictions, unlike video-based motion capturing systems. Still, the generation, and especially the…
Spatial fields in the Earth and environmental sciences are often available at multiple scales or resolutions. While coarse-scale data (e.g., from global circulation models) are often abundant, they lack the local detail provided by…
Learning physical dynamics from data is a fundamental challenge in machine learning and scientific modeling. Real-world observational data are inherently incomplete and irregularly sampled, posing significant challenges for existing…
Data-driven design is emerging as a powerful strategy to accelerate engineering innovation. However, its application to vehicle wheel design remains limited due to the lack of large-scale, high-quality datasets that include 3D geometry and…
Diffusion-based image generators can now produce high-quality and diverse samples, but their success has yet to fully translate to 3D generation: existing diffusion methods can either generate low-resolution but 3D consistent outputs, or…
The advent of machine learning (ML) and computer vision has significantly accelerated seismic inversion workflows by reducing the computational cost of traditionally expensive iterative methods. However, the development and evaluation of ML…
When solving inverse problems in geophysical imaging, deep generative models (DGMs) may be used to enforce the solution to display highly structured spatial patterns which are supported by independent information (e.g. the geological…
High-quality 3D assets for traffic participants are critical for multi-sensor simulation, which is essential for the safe end-to-end development of autonomy. Building assets from in-the-wild data is key for diversity and realism, but…
Diffusion (score-based) generative models have been widely used for modeling various types of complex data, including images, audios, and point clouds. Recently, the deep connection between forward-backward stochastic differential equations…
Understanding how well a deep generative model captures a distribution of high-dimensional data remains an important open challenge. It is especially difficult for certain model classes, such as Generative Adversarial Networks and Diffusion…
Learning dynamical systems from sparse observations is critical in numerous fields, including biology, finance, and physics. Even if tackling such problems is standard in general information fusion, it remains challenging for contemporary…
Recent advancements in generative models have unlocked the capabilities to render photo-realistic data in a controllable fashion. Trained on the real data, these generative models are capable of producing realistic samples with minimal to…