deep learning 1depth reconstruction 1disparity estimation 1epipolar image processing 1fourier-based feature learning 1light-field imaging 1non-rigid deformation 1point cloud registration 1soft-tissue analysis 1statistical priors 1
From the 2 of 3 linked papers with an AI index.
3 papers
cs.CV2026
DINE: Distance Is Not Enough -- Learning Global Deformation Priors for Robust Soft-Tissue Point Cloud Registration
Sara Monji-Azad, Rohit Beer, Marvin Kinz +2
The paper introduces DINE, a framework that improves non-rigid soft-tissue point cloud registration by combining distance-based objectives with a learned global prior on deformatio…
cs.CV2026
Frequency-Structured Field Learning for Light-Field Disparity Estimation
Sara Monji-Azad, Yulin Liu, Jürgen Hesser
The paper proposes a new method, FreqLF, that estimates depth from light‑field images by learning a latent field of epipolar‑image features using a combination of global Fourier up…
cs.CV2025
DefTransNet: A Transformer-based Method for Non-Rigid Point Cloud Registration in the Simulation of Soft Tissue Deformation
Sara Monji-Azad, Marvin Kinz, Siddharth Kothari +5
Soft-tissue surgeries, such as tumor resections, are complicated by tissue deformations that can obscure the accurate location and shape of tissues. By representing tissue surfaces…