Read more
The two-volume set 15725 and 15726 constitutes the refereed proceedings of the 23rd Scandinavian Conference on Image Analysis, SCIA 2025, held in Reykjavik, Iceland, during June 23 25, 2025.
The 60 revised full papers presented in these proceedings were carefully reviewed and selected from 98 submissions. The papers are organized in the following topical sections:
Part I: Machine learning and deep learning; Segmentation, Grouping, and Shape; Vision for robotics and autonomous vehicles; Biometrics, faces, body gestures and pose; 3D vision from multiview and other sensors; and Vision applications and systems.
Part II: Datasets and evaluation; Image and video processing, analysis, and understanding; Detection, recognition, classification, and localization in 2D and/or 3D; Medical, biological, and cell microscopy; Explainable AI for CV; Vision + language (+ other modalities); Computational photography; Fairness; and Low·level and physics·based vision.
List of contents
.- Machine learning and deep learning.
.- FGGP: Fixed-Rate Gradient-First Gradual Pruning.
.- Addressing degeneracies in latent interpolation for diffusion models.
.- PHASE: Physiological Dynamics-Based Attention for SpO2 Estimation.
.- Non-stationary signal analysis: detrending and anomaly detection.
.- Centered Self-Attention Layers.
.- Deep Spatio-Temporal Neural Network for Air Quality Reanalysis.
.- Is Adversarial Training with Compressed Datasets Effective?.
.- Efficient Object-Centric Learning for Videos.
.- Out-of-Distribution Detection in Point-of-Care Ultrasound Breast Imaging using Variational Autoencoders.
.- Adversarially Informed Neural Fields for Computed Tomography Reconstruction.
.- Segmentation, Grouping, and Shape.
.- Statistical analysis of left ventricular remodeling following a myocardial infarct.
.- FAST-AID Brain: Fast and Accurate Segmentation Tool Using Artificial Intelligence Developed for Brain.
.- Data Augmentation-Based Unsupervised Domain Adaptation In Medical Imaging.
.- Diffusion Based Ambiguous Image Segmentation.
.- Vision for robotics and autonomous vehicles.
.- From Web Data to Real Fields: Low-Cost Unsupervised Domain Adaptation for Agricultural Robots.
.- Efficient Real-time Quadcopter Propeller Detection and Attribute Estimation with High resolution Event Camera.
.- Road Grip Uncertainty Estimation Through Surface State Segmentation.
.- Biometrics, faces, body gestures and pose.
.- Progressive Feature Learning for Realistic Cloth-Changing Gait Recognition.
.- Infused Suppression Of Magnification Artefacts For Micro-AU Detection.
.- Continuous Normalizing Flows for Uncertainty-Aware Human Pose Estimation.
.- 3D vision from multiview and other sensors.
.- Towards an AI-Powered Video Assistant Referee System (VARS) for Association Football.
.- Visual Re-Ranking with Non-Visual Side Information.
.- FACT: Multinomial Misalignment Classification for Point Cloud Registration.
.- Compressing 3D Gaussian Splatting by Noise-Substituted Vector Quantization.
.- NVSMask3D: Hard Visual Prompting with Camera Pose Interpolation for 3D Open Vocabulary Instance Segmentation.
.- CSI2Depth: Spatio-Temporal Depth Images from Wi-Fi CSI Data via.
.- Transformer Networks and conditional Generative Adversarial Networks.
.- Spherical Harmonics Grid for Fast Ultrasound 3D Reconstruction.
.- Vision applications and systems.
.- Semi-Supervised Contrastive Training for Similar Image Identification in a Large Collection of Historical Books.
.- pix2pockets: Single Image Ball Detection for Shot Suggestions in 8-Ball Pool.
.- Contour Detection in Glass Fiber Layups with Geometric Prior.
.- Evaluating the Accuracy and Reliability of Camera-Based Physiological and Motion Signal Extraction Techniques in Virtual Reality Training Environments.
.- Sex Classification from Human Scent Using Image Interpretation of 2D Gas Chromatography-Mass Spectrometry Data.
Summary
The two-volume set 15725 and 15726 constitutes the refereed proceedings of the 23rd Scandinavian Conference on Image Analysis, SCIA 2025, held in Reykjavik, Iceland, during June 23–25, 2025.
The 60 revised full papers presented in these proceedings were carefully reviewed and selected from 98 submissions. The papers are organized in the following topical sections:
Part I: Machine learning and deep learning; Segmentation, Grouping, and Shape; Vision for robotics and autonomous vehicles; Biometrics, faces, body gestures and pose; 3D vision from multiview and other sensors; and Vision applications and systems.
Part II: Datasets and evaluation; Image and video processing, analysis, and understanding; Detection, recognition, classification, and localization in 2D and/or 3D; Medical, biological, and cell microscopy; Explainable AI for CV; Vision + language (+ other modalities); Computational photography; Fairness; and Low·level and physics·based vision.
