2 papers
eess.IV2026
Structured SIR: Efficient and Expressive Importance-Weighted Inference for High-Dimensional Image Registration
Ivor J. A. Simpson, Neill D. F. Campbell
Image registration is an ill-posed dense vision task, where multiple solutions achieve similar loss values, motivating probabilistic inference. Variational inference has previously…
cs.CV2025
Structured Uncertainty Similarity Score (SUSS): Learning a Probabilistic, Interpretable, Perceptual Metric Between Images
Paula Seidler, Neill D. F. Campbell, Ivor J A Simpson
Perceptual similarity scores that align with human vision are critical for both training and evaluating computer vision models. Deep perceptual losses, such as LPIPS, achieve good…