Frontier agentic AI models consistently fail at computational imaging tasks requiring physics-aware inversion, producing visually plausible but physically incorrect outputs.
Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
A Markov-modeled maximum likelihood estimator for multi-look holographic reconstruction achieves near-ideal performance under strong inter-look speckle correlation by outperforming methods that assume independence.
citing papers explorer
-
Does AI Understand Imaging? A Systematic Benchmark of Agentic AI for Computational Imaging Tasks
Frontier agentic AI models consistently fail at computational imaging tasks requiring physics-aware inversion, producing visually plausible but physically incorrect outputs.
-
Maximum Likelihood Reconstruction for Multi-Look Digital Holography with Markov-Modeled Speckle Correlation
A Markov-modeled maximum likelihood estimator for multi-look holographic reconstruction achieves near-ideal performance under strong inter-look speckle correlation by outperforming methods that assume independence.