CV4MS@ICCV2025 is a half-day hybrid workshop, with both in-person and virtual attendance (via Zoom).
The schedule: TBD
Accepted papers will be presented as either oral or spotlight presentations. Regardless of the presentation format, all presenters will also have the opportunity to share their work during the workshop’s poster session, which will follow the oral presentations.
List of accepted papers
Oral presentations:
MatSSL: Robust Self-Supervised Representation Learning for Metallographic Image Segmentation, H.W. Lee et. al
Unlocking quantitative insights in EELS-based hyperspectral imaging with physics-driven non-negative matrix factorization, P.T. Besa et. al
Improving Multislice Electron Ptychography with a Generative Prior, C.H. Lee et. al
Automated Feature Tracking for Real-Time Kinematic Analysis and Shape Estimation of Carbon Nanotube Growth, K. Safavigerdini et. al
Neural Object Detection for 4D-STEM: High-Throughput Sub-Pixel Electron Diffraction Pattern Recognition, A. Genc et. al
Morphological Analysis of Semiconductor Microstructures using Skeleton Graphs, N. Nitta et. al
Spotlight presentations:
Application of Semantic Segmentation on SEM Images of Rubber Composites and Verification of Correlation with Material Properties, R. Asami et. al
Unveiling Process–Structure Mapping with a Deep Variational Autoencoder, A. Mishra et. al
Improving U-Net Confidence on TEM Image Data with L2-Regularization, Transfer Learning, and Deep Fine-Tuning, A. Ochoa et. al
AtomDiffuser: Time-Aware Degradation Modeling for Drift and Beam Damage in STEM Imaging, H. Wang et. al
AI-Driven Analysis of Fracture Types in Metallic Materials: Classification, Segmentation, and Quantification with Deep Neural Networks, A. Wójcicka et. al
A Transformer-Based GAN Architecture for Simulating Carbon Nanotube Structures in the Frequency Domain, M. Attari et. al
SAM- and μSAM- Based Inference of Nuclear Materials Processing History from SEM Imagery, M.V. Mendoza et. al