1.2k citations · 1.3k across the 27 of their papers we have counts for
29 papers
Beyond Best-of-: Prior-Consistent DAPS for Ambiguous Nonlinear Inverse Problems
Merve Kocabas, Benjamin A. Burns, Andreas Geiger +2
Diffusion models have become strong priors for solving inverse problems. However, nonlinear inverse problems such as phase retrieval remain challenging when multiple measurement-co…
LACToS: Local Anomaly Detection via Conditional Typicality of Superpixels
Jihoon Hong, Alireza Kheirandish, Rohan Sanda +1
Local anomaly detection is the task of identifying spatially confined anomalous or out-of-distribution (OOD) regions within an otherwise in-distribution (ID) image. Most existing m…
Sparse Light Field Sampling Improves Casual 3D and 4D Reconstruction
Shamus Li, Ruiming Cao, Laura Waller +2
Many consumer smartphones, stereo cameras, and light field cameras record multiple synchronized viewpoints in a single exposure event. However, novel view synthesis pipelines commo…
PolyMerge: Compressing 3D Gaussian Splats with Polytope Coverings for Provably Safe Resource-Constrained Navigation
Jihoon Hong, Chih-Yuan Chiu, Sara Fridovich-Keil +1
Obstacle avoidance is essential for safe navigation and motion planning. Recent radiance field reconstruction methods enable object detection and modeling with high fidelity, but r…
KLIP: localized distribution shift detection via KL-divergence with diffusion priors in Inverse Problems
Alireza Kheirandish, Jihoon Hong, Sara Fridovich-Keil
Diffusion models have shown promising performance as data-driven priors for computational imaging, as well as some capacity to detect out-of-distribution (OOD) images. However, exi…
Bounding Global and Local Compression Error of Signal Parameterizations
Quang Luong Nhat Nguyen, Sara Fridovich-Keil
Differentiable signal parameterizations such as implicit neural representations (INRs) and hybrid models are increasingly central to computational imaging, yet principled tools for…
When, why, and how do diffusion posterior samplers fail? A finite-sample lens
Benjamin A. Burns, Sara Fridovich-Keil
Diffusion models have excellent capacity to model complex distributions of natural data, which has made them a popular and effective choice for posterior sampling in imaging invers…
3D Field of Junctions: A Noise-Robust, Training-Free Structural Prior for Volumetric Inverse Problems
Narges Moeini, Namhoon Kim, Justin Romberg +1
Volume denoising is a foundational problem in computational imaging, as many 3D imaging inverse problems face high levels of measurement noise. Inspired by the strong 2D image deno…
Perfusion Imaging and Single Material Reconstruction in Polychromatic Photon Counting CT
Namhoon Kim, Ashwin Pananjady, Amir Pourmorteza +1
Background: Perfusion computed tomography (CT) images the dynamics of a contrast agent through the body over time, and is one of the highest X-ray dose scans in medical imaging. Re…
Towards Distribution-Shift Uncertainty Estimation for Inverse Problems with Generative Priors
Namhoon Kim, Sara Fridovich-Keil
Generative models have shown strong potential as data-driven priors for solving inverse problems such as reconstructing medical images from undersampled measurements. While these p…
Patch-Based Diffusion for Data-Efficient, Radiologist-Preferred MRI Reconstruction
Rohan Sanda, Asad Aali, Andrew Johnston +3
Magnetic resonance imaging (MRI) requires long acquisition times, raising costs, reducing accessibility, and making scans more susceptible to motion artifacts. Diffusion probabilis…
A Recovery Guarantee for Sparse Neural Networks
Sara Fridovich-Keil, Mert Pilanci
We prove the first guarantees of sparse recovery for ReLU neural networks, where the sparse network weights constitute the signal to be recovered. Specifically, we study structural…
Grids Often Outperform Implicit Neural Representations at Compressing Dense Signals
Namhoon Kim, Sara Fridovich-Keil
Implicit Neural Representations (INRs) have recently shown impressive results, but their fundamental capacity, implicit biases, and scaling behavior remain poorly understood. We in…
Accurate, provable and fast polychromatic tomographic reconstruction: A variational inequality approach
Mengqi Lou, Kabir Aladin Verchand, Sara Fridovich-Keil +1
We consider the problem of signal reconstruction for computed tomography (CT) under a nonlinear forward model that accounts for exponential signal attenuation, a polychromatic X-ra…
Geometric Algebra Planes: Convex Implicit Neural Volumes
Irmak Sivgin, Sara Fridovich-Keil, Gordon Wetzstein +1
Volume parameterizations abound in recent literature, from the classic voxel grid to the implicit neural representation and everything in between. While implicit representations ha…
ThermalNeRF: Thermal Radiance Fields
Yvette Y. Lin, Xin-Yi Pan, Sara Fridovich-Keil +1
Thermal imaging has a variety of applications, from agricultural monitoring to building inspection to imaging under poor visibility, such as in low light, fog, and rain. However, r…
Solving Inverse Problems in Protein Space Using Diffusion-Based Priors
Axel Levy, Eric R. Chan, Sara Fridovich-Keil +3
The interaction of a protein with its environment can be understood and controlled via its 3D structure. Experimental methods for protein structure determination, such as X-ray cry…
Volumetric Reconstruction Resolves Off-Resonance Artifacts in Static and Dynamic PROPELLER MRI
Annesha Ghosh, Gordon Wetzstein, Mert Pilanci +1
Off-resonance artifacts in magnetic resonance imaging (MRI) are visual distortions that occur when the actual resonant frequencies of spins within the imaging volume differ from th…
Gradient Descent Provably Solves Nonlinear Tomographic Reconstruction
Sara Fridovich-Keil, Fabrizio Valdivia, Gordon Wetzstein +2
In computed tomography (CT), the forward model consists of a linear Radon transform followed by an exponential nonlinearity based on the attenuation of light according to the Beer-…
Neural Microfacet Fields for Inverse Rendering
Alexander Mai, Dor Verbin, Falko Kuester +1
We present Neural Microfacet Fields, a method for recovering materials, geometry, and environment illumination from images of a scene. Our method uses a microfacet reflectance mode…
K-Planes: Explicit Radiance Fields in Space, Time, and Appearance
Sara Fridovich-Keil, Giacomo Meanti, Frederik Warburg +2
We introduce k-planes, a white-box model for radiance fields in arbitrary dimensions. Our model uses d choose 2 planes to represent a d-dimensional scene, providing a seamless way…
Models Out of Line: A Fourier Lens on Distribution Shift Robustness
Sara Fridovich-Keil, Brian R. Bartoldson, James Diffenderfer +2
Improving the accuracy of deep neural networks (DNNs) on out-of-distribution (OOD) data is critical to an acceptance of deep learning (DL) in real world applications. It has been o…
When does dough become a bagel? Analyzing the remaining mistakes on ImageNet
Vijay Vasudevan, Benjamin Caine, Raphael Gontijo-Lopes +2
Image classification accuracy on the ImageNet dataset has been a barometer for progress in computer vision over the last decade. Several recent papers have questioned the degree to…
Plenoxels: Radiance Fields without Neural Networks
Alex Yu, Sara Fridovich-Keil, Matthew Tancik +3
We introduce Plenoxels (plenoptic voxels), a system for photorealistic view synthesis. Plenoxels represent a scene as a sparse 3D grid with spherical harmonics. This representation…