Psoriasis

Scalable heliostat surface predictions from focal spots: Sim-to-Real transfer of inverse Deep Learning Raytracing

Concentrating Solar Power (CSP) plants are a key technology in the transition toward sustainable energy. A critical factor for their safe and efficient operation is the distribution of concentrated solar flux on the receiver. However, flux distributions from individual heliostats are sensitive to surface imperfections. Measuring these surfaces across many heliostats remains impractical in real-w...

Locally Orderless Images for Optimization in Differentiable Rendering

Problems in differentiable rendering often involve optimizing scene parameters that cause motion in image space. The gradients for such parameters tend to be sparse, leading to poor convergence. While existing methods address this sparsity through proxy gradients such as topological derivatives or lagrangian derivatives, they make simplifying assumptions about rendering. Multi-resolution image p...

Double Blind Imaging with Generative Modeling

Blind inverse problems in imaging arise from uncertainties in the system used to collect (noisy) measurements of images. Recovering clean images fro...

TS-Inverse: A Gradient Inversion Attack Tailored for Federated Time Series Forecasting Models

Federated learning (FL) for time series forecasting (TSF) enables clients with privacy-sensitive time series (TS) data to collaboratively learn accu...

TensoFlow: Tensorial Flow-based Sampler for Inverse Rendering

Inverse rendering aims to recover scene geometry, material properties, and lighting from multi-view images. Given the complexity of light-surface in...

Graph-CNNs for RF Imaging: Learning the Electric Field Integral Equations

Radio-Frequency (RF) imaging concerns the digital recreation of the surfaces of scene objects based on the scattered field at distributed receivers....

LATINO-PRO: LAtent consisTency INverse sOlver with PRompt Optimization

Text-to-image latent diffusion models (LDMs) have recently emerged as powerful generative models with great potential for solving inverse problems i...

InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciences

Plug-and-play diffusion priors (PnPDP) have emerged as a promising research direction for solving inverse problems. However, current studies prima...

GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance Modeling

We present GroomLight, a novel method for relightable hair appearance modeling from multi-view images. Existing hair capture methods struggle to bal...

Channel-wise Noise Scheduled Diffusion for Inverse Rendering in Indoor Scenes

We propose a diffusion-based inverse rendering framework that decomposes a single RGB image into geometry, material, and lighting. Inverse rendering...

A deep learning approach to inverse medium scattering: Learning regularizers from a direct imaging method

This paper aims to solve numerically the two-dimensional inverse medium scattering problem with far-field data. This is a challenging task due to th...

Reconstruct Anything Model: a lightweight foundation model for computational imaging

Most existing learning-based methods for solving imaging inverse problems can be roughly divided into two classes: iterative algorithms, such as plu...

FlowDPS: Flow-Driven Posterior Sampling for Inverse Problems

Flow matching is a recent state-of-the-art framework for generative modeling based on ordinary differential equations (ODEs). While closely related ...

Generative method for aerodynamic optimization based on classifier-free guided denoising diffusion probabilistic model

Inverse design approach, which directly generates optimal aerodynamic shape with neural network models to meet designated performance targets, has d...

Federated Inverse Probability Treatment Weighting for Individual Treatment Effect Estimation

Individual treatment effect (ITE) estimation is to evaluate the causal effects of treatment strategies on some important outcomes, which is a crucia...

Parameter estimation in fluid flow models from undersampled frequency space data

4D Flow MRI is the state of the art technique for measuring blood flow, and it provides valuable information for inverse problems in the cardiovascu...

Can Diffusion Models Provide Rigorous Uncertainty Quantification for Bayesian Inverse Problems?

In recent years, the ascendance of diffusion modeling as a state-of-the-art generative modeling approach has spurred significant interest in their u...

BAMBI integrates biostatistical and artificial intelligence methods to improve RNA biomarker discovery.

RNA biomarkers enable early and precise disease diagnosis, monitoring, and prognosis, facilitating personalized medicine and targeted therapeutic stra...

Split Gibbs Discrete Diffusion Posterior Sampling

We study the problem of posterior sampling in discrete-state spaces using discrete diffusion models. While posterior sampling methods for continuous...

FlexDrive: Toward Trajectory Flexibility in Driving Scene Reconstruction and Rendering

Driving scene reconstruction and rendering have advanced significantly using the 3D Gaussian Splatting. However, most prior research has focused on ...